DEVICES, SYSTEMS AND METHODS OF IDENTIFYING PLANTS, PLANT

MATERIAL AND PLANT STATE

Related Applications

[0001] The present application is related to U.S. provisional patent application no. 62/847,364, filed May 14, 2019, U.S. provisional patent application no.

62/801,583, filed February 5, 2019, U.S. provisional patent application no.

62/780,610, filed December 17, 2018, and U.S. provisional patent application no. 62/683,885, filed June 12, 2018, the content of these applications being

incorporated herein by reference.

Technical Field

[0002] The present disclosure relates to a precision agriculture system and related methods, to devices, systems and methods of identifying plants, plant material and plant states, to devices, systems and methods for multivariable optimization of plant growth and growth of other phototrophic organisms, and to devices, systems and methods of training machine learning/artificial intelligence controllers and algorithms for use in same.

Background

[0003] The identification of a plant can be a challenging problem, particularly when the person performing the identification is a layperson, when the appearance (morphology) of the plant is similar to other plants, when only a part of the plant is available for identification such as a cutting, leaves or buds (or flowers), and/or when the part of the plant is available for identification has been processed (e.g., dried, crushed, etc.). Similarly, the identification of a plant state, such as plant health and/or stage of development, can be a challenging problem. Thus, there exists a need for means of identifying a plant and/or a plant state.

[0004] Furthermore, plants are often grown at a large scale either outside or in artificial environments such as greenhouses, growth chambers, hydroponic, aquaponics, aeroponics and the like. Phototrophic organisms may also be similarly grown at large scale in artificial environments. The growing conditions affect the growth of the plants and phototrophic organisms in many ways including the size, health, cellular/chemical constituents of the plants.

[0005] The optimization of growing conditions is a multivariable problem, the variables of which may vary based on the type of plant or phototrophic organism being grown, the grower's objectives, customer demands, among other factors. Existing approaches to the optimization of growing conditions are often based on large sections of a growing environment, such as a grower facility, for simplicity and/or costs, which limits the ability to optimize growing conditions by the inability to control growing conditions on another other than a large scale. Thus, there remains a need for devices, systems and methods for multivariable optimization of plant growth and growth of other phototrophic organisms.

Brief Description of the Drawings

[0006] FIG. 1A is a schematic diagram of a growing system in accordance with one embodiment of the present disclosure.

[0007] FIG. IB is a block diagram of the growing system of FIG. 1A.

[0008] FIG. 2A is a block diagram of a grower sensor device in accordance with an example embodiment of the present disclosure.

[0009] FIG. 2B is a block diagram of a consumer sensor device in accordance with an example embodiment of the present disclosure.

[0010] FIG. 3A is a block diagram of a growing apparatus in accordance with one embodiment of the present disclosure.

[0011] FIG. 3B is a cross-sectional view of the growing apparatus of FIG. 3A.

[0012] FIG. 4 is a block diagram of an artificial intelligence controller of the growing system of FIG. 1 in accordance with one embodiment of the present disclosure. [0013] FIG. 5 is a flowchart of a method of multivariable optimization of plant growth in accordance with one example embodiment of the present disclosure.

[0014] FIG. 6 is a block diagram of a genetic algorithm controller for the growing system of FIG. 1A and IB in accordance with one embodiment of the present disclosure.

[0015] FIG. 7 is a flowchart of a method of multivariable optimization of plant growth in accordance with one example embodiment of the present disclosure.

[0016] FIG. 8A and 8B are example graphs illustrating the response of gas sensors of when exposed to the emissions of terpinolene and limonene,

respectively.

[0017] FIG. 9 is an example graph illustrating the response of gas sensors when exposed to different strains of cannabis.

[0018] FIG. 10 is an example graph illustrating a terpene profile of different strains of cannabis.

[0019] FIGs. 11A-C are flowcharts of a method of identifying a plant and/or a plant state in accordance with one example embodiment of the present disclosure.

[0020] FIG. 12 is a flowchart of a method of identifying a plant state in accordance with one example embodiment of the present disclosure.

[0021] FIG. 13 is a picture of a grower sensor device in accordance with one example embodiment of the present disclosure.

[0022] FIG. 14 is a visualisation of a mapping of terpene profiles to effects of consumption.

[0023] FIG. 15 is a flowchart of a method of formulating an infused

consumable product in accordance with one example embodiment of the present disclosure will be described. [0024] FIG. 16 is a schematic block diagram of a generative adversarial network for the growing system of FIG. 1A and IB in accordance with one embodiment of the present disclosure.

Detailed Description of Example Embodiments

[0025] The present disclosure is made with reference to the accompanying drawings, in which embodiments are shown. However, many different embodiments may be used, and thus the description should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same elements, and prime notation is used to indicate similar elements, operations or steps in alternative embodiments. Separate boxes or illustrated separation of functional elements of illustrated systems and devices does not necessarily require physical separation of such functions, as communication between such elements may occur by way of messaging, function calls, shared memory space, and so on, without any such physical separation. As such, functions need not be implemented in physically or logically separated platforms, although they are illustrated separately for ease of explanation herein. Different devices may have different designs, such that although some devices implement some functions in fixed function hardware, other devices may implement such functions in a programmable processor with code obtained from a machine-readable medium. Lastly, elements referred to in the singular may be plural and vice versa, except where indicated otherwise either explicitly or inherently by context.

[0026] The present disclosure relates to devices, systems and methods of identifying a plant and/or a plant state, to devices, systems and methods for multivariable optimization of plant growth and growth of other phototrophic organisms, and to devices, systems and methods of training machine

learning/artificial intelligence controllers and algorithms for use in same.

[0027] The present disclosure also relates to growing systems for plants and phototrophic organisms. The growing system is automated for growing plants in an artificial environment such as a greenhouse or an outdoor environment, such as a farm. The growing system comprises a network of sensors and effectors in communication with a control system. The sensors collect data relating to plants, growing conditions or operational parameters of the growing system which are provided to the control system. The control system determines the growing conditions that optimize one or more performance criteria (or objectives), determines whether any changes in the growing conditions are required, and if so, instructs the effectors to modify the growing conditions to match the determined optimal growing conditions. The performance criteria may be selectable based on the objectives of the grower, customer or other entity. The growing system of the present disclosure may control the growing conditions of individual plants. The growing system of the present disclosure may match individual growing conditions to the maturity and developmental stage of the individual plant in addition to other plant growth parameters. The growing system collects robust data analytics and provides an integrated growth solution that seeks to increase yield or productivity by generating a continuous feedback loop during the plant growth cycle. The growing system of the present disclosure may increase the yield quality and/or quantity of plant material produced may be increased by controlling the growing conditions of individual plants and optionally matching individual growing conditions to the maturity and developmental stage of the individual plant in addition to other plant growth parameters.

[0028] The teachings of the present disclosure may be used for precision agriculture by allowing real-time or near real-time identification of a plant and/or a plant state. The teachings of the present disclosure include a sensor module that may be used to different between aromatics and aromatic profiles of multiple aromatic compounds in real-time or near real-time or between other volatile compounds and volatile compound profiles of multiple volatile compounds in real- time or near real-time.

[0029] The teachings of the present disclosure may be applied to outdoor growing environments and indoor growing environments, with perhaps the greatest potential in the indoor growing environments. The market of commercial indoor growth of vegetables has been estimated to exceed 50 billion square feet with a total value of US $340 B worldwide not including the market for other types of plants and other phototrophic organisms such as cannabis and algae. The value of the North American cannabis industry has been estimated to exceed CAD $45 B by 2023. In addition, Canada's indoor growth technology market has been estimated to exceed CAD $50 B by 2022. The value of artificial intelligence in Canada's agricultural market has been estimated to exceed CAD $3.5 B by 2025 with a focus on Precision Agriculture. Each of these markets present opportunities for the teachings of the present disclosure. Thus, the addressable market for the teachings of the present disclosure is very large.

[0030] Although the teachings of may be applied to any plant or other phototrophic organism, embodiments of the present disclosure are directed towards the growth of "cannabis". The term cannabis in the present disclosure refers to all plants within the genus Cannabis, a genus of flowering plants in the family

Cannabaceae. Although the number of species within the genus is disputed, three species may be recognized : Cannabis sativa, Cannabis indica, and Cannabis ruderalis. Cannabis plants may also be differentiated by strains. A cannabis strain is a pure or hybrid variety of the plant genus Cannabis. In botanical nomenclature, a variety is a taxonomic rank below that of species and subspecies but above that of form.

[0031] A cannabinoid is one of a class of diverse chemical compounds that acts on cannabinoid receptors (also known as endocannabinoid system in cells that alter neurotransmitter release in the brain). At least 113 different cannabinoids have been isolated from the plant genus Cannabis. The particular cannabinoids and amounts thereof may vary by the Cannabis strain and state of the plant (e.g., plant health and/or state of development). Similarly, the particular cannabinoids and amounts thereof present in plant material may varies based on the Cannabis strain, state of the plant, type of plant material (e.g., leaf or bud/flowers), and type of processing (if any) among other possible factors. [0032] In accordance with one aspect of the present disclosure, there is provided a device, system and method of identifying a plant and/or a plant state (such as plant health and/or stage of development), and a method of learning to identify a plant and/or a plant state. The method uses non-destructive testing (NDT) and non-contact testing (NCT) to measure gases in the air surrounding a plant in real-time or near real-time, determine a gas profile for the measured gases, and identify the plant and/or plant state based on the gas profile. The method may also be used to identify and differentiate between volatile compounds such as aromatics.

[0033] In accordance with another aspect of the present disclosure, there is provided a system for controlling the growth of a plant, the system comprising : at least one sensor for detecting at least one growth parameter of the plant; at least one effector for modifying at least one growing condition of the plant; and a control unit in communication with the at least one sensor and the at least one effector, the control unit configured to: receive the at least one growth parameter from the at least one sensor; compare the at least one growth parameter to a corresponding target value, to assess the status of the plant; and issue commands to the effector based on the status of the plant, to modify at least one growing condition of the plant.

[0034] In some examples, the at least one growth parameter indicates the condition of the plant.

[0035] In some examples, the condition of the plant is indicated by leaf colour, leaf area, leaf temperature, stem thickness, root depth, root colour, a fungal infection, an insect infestation, or a combination thereof.

[0036] In some examples, the at least one growth parameter indicates the condition of the plant growth medium.

[0037] In some examples, the plant growth medium is soil, mineral-based media, polymer-based media, organic plant material, semi-solid agar, nutrient solution, or combinations thereof. [0038] In some examples, the condition of the plant growth medium is indicated by its nutrient content, pH, EC, moisture level, temperature, or

combinations thereof.

[0039] In some examples, the at least one growth parameter indicates the growth rate or maturity of the plant.

[0040] In some examples, the growth rate or maturity of the plant is indicated by the height of the plant, stem thickness, leaf area, the ambient light conditions, the ambient C0 ₂ levels, or combinations thereof.

[0041] In some examples, the at least one sensor is a thermometer, hygrometer, oxygen sensor, carbon dioxide meter, anemometer, light meter, photo sensor, camera, spectrometer, pH meter, EC meter, NPK meter, FLIR camera, caliper, or combinations thereof.

[0042] In some examples, the at least one growing condition of the plant is the ambient temperature, ambient humidity, C0 ₂ concentration, 0 ₂ concentration, air flow, lighting intensity, lighting frequency, lighting wavelength, growing media pH, growing media EC, moisture level of the growing media, temperature of the growing media, or combinations thereof.

[0043] In some examples, the effector is a heating system, an air conditioning system, a humidifier, a metered 02 source or mixer, a metered C02 source or mixer, a fan, a growth lamp, an LED array, a timer, a selective or filtered light source, a pH dosing unit, a metered nutrient source, a metered watering source, a growth media heating or chilling unit, or combinations thereof.

[0044] In some examples, the status of the plant is a growth stage, maturity level, a disease state, a nutritional deficiency, a metabolite concentration, a crop yield, or combinations thereof.

[0045] In some examples, the plant is an algae, land plant, or aquatic plant.

[0046] In some examples, the target value is pre-determined based on the species of the plant.

[0047] In some examples, the control unit is configured to receive a further input from the at least one sensor to monitor and validate the at least one growing condition of the plant, after modification thereof by the effector.

[0048] In some examples, the plant is cannabis and the target value is chosen to enhance the cannabinoid content of the plant.

[0049] In some examples, the status of the plant is a maturity level.

[0050] In some examples, the maturity level is a vegetative growth stage.

[0051] In some examples, the growing condition is a light frequency that is modified from a mostly on state to periods of 12 hours on and 12 hours off, to induce flowering.

[0052] In some examples, the maturity level is a flowering stage.

[0053] In some examples, the growing condition is a light wavelength that is modified to increase the intensity of UV light.

[0054] In some examples, the plant is grown in a greenhouse or growth chamber.

[0055] In accordance with a further aspect of the present disclosure, there is provided a method of controlling the growth of a plant, comprising : sensing at least one growth parameter of the plant; modulating at least one growing condition of the plant, based on the sensed at least one growth parameter; wherein the at least one growth parameter is the growth stage of the plant.

[0056] In some examples, the wherein the at least one growing condition includes at least one of lighting, C0 ₂ concentration, temperature, moisture levels, and nutrient levels.

[0057] In some examples, the modulating is with effect that maturation of the plant is encouraged. [0058] In some examples, the modulating is with effect that maturation of the plant is discouraged.

[0059] In accordance with a further aspect of the present disclosure, there is provided a method of controlling the growth of a plant, comprising : sensing at least one growth parameter of the plant; modulating at least one growing condition of the plant, based on the sensed at least one growth parameter; wherein the at least one growth parameter includes at least one condition of the plant; and the at least one condition of the plant includes at least one of the colour of the leaves, leaf area, leaf temperature, stem thickness, root depth, root coloration, the presence of a fungal or insect infestation, or a combination thereof.

[0060] In some examples, the wherein the at least one growing condition includes at least one of lighting, C0 ₂ concentration, temperature, moisture levels, and nutrient levels.

[0061] In accordance with a further aspect of the present disclosure, there is provided a method of controlling the growth of a plant, comprising : sensing at least one growth parameter of the plant; modulating at least one growing condition of the plant, based on the sensed at least one growth parameter; wherein the at least one growth parameter includes the height of the plant.

[0062] In some examples, the at least one growing condition includes at least one of lighting, C0 ₂ concentration, temperature, moisture levels, and nutrient levels.

[0063] In some examples, the modulating is with effect that growth of the plant is encouraged.

[0064] In some examples, the modulating is with effect that growth of the plant is discouraged.

[0065] In accordance with a further aspect of the present disclosure, there is a provided a machine-implemented method of multivariable optimization of plant growth, comprising : (i) generating a set of growing states as an initial population, each growing state defining a set of plant parameters measurable by one or a combination of plant growth sensors and environmental parameters measurable by one or a combination of environmental sensors; (ii) determining a fitness of each of the growing states via a fitness function, wherein the fitness function determines a fitness (performance) of each of the individual growing states in the set of growing states; (iii) selecting a plurality of individual growing states for a subsequent generation; (iv) generating a plurality of new growing states by performing a crossover of the selected individual growing states via a crossover algorithm; (v) determining whether the population has converged; and (vi) repeating operations (ii)-(v) in response to a determination that the population has not converged; (vii) outputting an optimized growing state in response to a determination that the population has converged.

[0066] In some examples, each growing state is encoded as a generic representation in the form of a bit string, wherein each plant parameter and environmental parameter is represented by a set of one or more octets.

[0067] In some examples, the bit string has a fixed length.

[0068] In some examples, the bit string has a variable length, wherein in each octet of the generic representation, a most significant bit (MSB) is used to indicate whether that octet is the last octet in the set of one or more octets for a given parameter.

[0069] In some examples, the fitness function outputs, for each of the individual growing states, a fitness score that defines the fitness of each of the individual growing states.

[0070] In some examples, the fitness score represents a probability that an individual growing state will be selected for reproduction.

[0071] In some examples, selecting the plurality of individual growing states for a subsequent generation comprises: selecting individual growing states determined to be the fittest (highest performing) from the set of all growing states via a selection function based on the fitness scores.

[0072] In some examples, the selection function is adapted to select individual growing states having a high fitness.

[0073] In some examples, the selection function is adapted to select the individual growing states having the highest fitness scores.

[0074] In some examples, the selection function is adapted to select individual growing states having a fitness score above a threshold fitness score in accordance with one or more particular selection criteria, which may be based on one or more performance criteria, plant parameters, environmental parameters or operational parameters.

[0075] In some examples, the selection function is adapted to select individual growing states having a fitness score above a threshold fitness score at random in accordance with a randomized selection algorithm.

[0076] In some examples, a pair of individual growing states is selected.

[0077] In some examples, the crossover algorithm stochastically generates new growing states from the pair of selected growing states, wherein the genetic representations of the pair of selected individual growing states are recombined with one or more different crossover operators, the new growing states

representing offspring of the previous generation of growing states.

[0078] In some examples, the crossover algorithm is chosen from one of a single-point crossover, a two-point crossover, a k-point crossover, a uniform crossover or special crossover.

[0079] In some examples, the crossover algorithm is a special crossover chosen from a partially matched crossover (PMX), a cycle crossover (CX), an order crossover operator (0X1), an order-based crossover operator (0X2), a position- based crossover operator (POS), a voting recombination crossover operator (VR), an alternating-position crossover operator (AP), a sequential constructive crossover operator (SCX), and an edge recombination operator (ERO).

[0080] In some examples, the method further comprises: generating one or more variations (mutations) in the plurality of new growing states (offspring) with a low random probability.

[0081] In some examples, generating one or more variations comprises switching bits in the bit string of affected growing states.

[0082] In some examples, determining whether the population has converged comprises determining whether the current generation has produced offspring which are significantly different from the previous generation.

[0083] In some examples, determining whether the population has converged comprises comparing the fitness of the new growing states of the current

generation (offspring) to the fitness of the growing states of the previous

generation, wherein the population is determined to have converged when the difference between the fitness of the new growing states and the fitness of the growing states of the previous generation is less than a threshold, and wherein the population is determined not to have converged when the difference between the fitness of the new growing states and the fitness of the growing states of the previous generation exceeds or is equal to the threshold.

[0084] In some examples, determining whether the population has converged comprises comparing the genetic representation of the new growing states

(offspring) to the fitness or genetic representation of the previous generation, wherein the population is determined to have converged when the difference between the genetic representation of the new growing states and the genetic representation of the growing states of the previous generation is less than a threshold, and wherein the population is determined not to have converged when the difference between the genetic representation of the new growing states and the genetic representation of the growing states of the previous generation exceeds or is equal to the threshold.

[0085] In some examples, each growing state further defines operational parameters determinable by the machine from a database, supplemental data sources, or measurable by one or more operational sensors.

[0086] In some examples, each growing state is encoded as a generic representation in the form of a bit string, wherein each plant parameter,

environmental parameter and operational parameter is represented by a set of one or more octets.

[0087] In accordance with a further aspect of the present disclosure, there is a provided machine-implemented method of identifying plant material, comprising : sensing via gas sensors a plurality of gases in the ambient air surrounding the plant material; determining a gas profile based on the sensed gases; and identifying the plant material based on the gas profile.

[0088] In some examples, the method further comprises displaying an identification of the identified plant material.

[0089] In some examples, the method further comprises: determining information associated with the identified plant material.

[0090] In some examples, the method further comprises: displaying an identification of the identified plant material along with the information associated with the identified plant material.

[0091] In some examples, the information comprises an effects profile associated with consumption of the identified plant material.

[0092] In some examples, the effects profile comprises any combination of psychological effects, physiological effects, therapeutic effects and/or side effects.

[0093] In some examples, the gas profile comprises one of a cannabinoid profile, a terpene profile, a flavonoid profile, or a combination of thereof.

[0094] In some examples, the gas profile comprises a terpene profile comprising a composition of a plurality of terpenes selected from the group consisting of any combination of pinene (typically a-pinene and/or p-pinene), myrcene, limonene, humulene, linalool, caryophyllene (typically b-caryophyllene), terpinolene, ocimene, camphene, terpineol, phellandrene, careen (typically Delta 3 carene), humulene, pulegone, sabinene, a-bisabolol (also known as levomenol and bisabolol), eucalyptol, trans-nerolido, borneol, valencene or geraniol.

[0095] In some examples, the gas profile comprises a terpene profile comprising a composition of a plurality of terpenes selected from the group consisting of any combination of pinene, myrcene, limonene, humulene, linalool, caryophyllene, or terpinolene.

[0096] In some examples, each gas sensor in the plurality of gas sensors is preferentially sensitive to one or more gases, each gas sensor in the plurality of gas sensors outputting a voltage representative voltage of the sensed gases.

[0097] In some examples, determining the gas profile based on the sensed gases comprises determining from a library of gas profiles an gas profile matching the sensed gases by comparing a composition of the sensed gases to a composition of gases in each gas profile in the library of gas profiles.

[0098] In some examples, identifying the plant material based on the gas profile comprises: determining from a library of plant profiles the plant material based on the matching gas profile by comparing the matching gas profile to each plant profile in the library of plant profiles.

[0099] In some examples, the gas profile comprises one of a cannabinoid profile, a terpene profile, a flavonoid profile, or a combination of thereof.

[00100] In some examples, the gas profile comprises a terpene profile comprising a composition of a plurality of terpenes selected from the group consisting of any combination of pinene (typically a-pinene and/or D-pinene), myrcene, limonene, humulene, linalool, caryophyllene (typically b-caryophyllene), terpinolene, ocimene, camphene, terpineol, phellandrene, careen (typically Delta 3 carene), humulene, pulegone, sabinene, a-bisabolol (also known as levomenol and bisabolol), eucalyptol, trans-nerolido, borneol, valencene or geraniol.

[00101] In some examples, the gas profile comprises a terpene profile comprising a composition of a plurality of terpenes selected from the group consisting of any combination of pinene, myrcene, limonene, humulene, linalool, caryophyllene, or terpinolene.

[00102] In some examples, the plant profiles correspond to cannabis strains.

[00103] In some examples, the method further comprises: sensing via photo sensors one or more light spectra; wherein the plant material is identified based on both the gas profile and the sensed one or more light spectra.

[00104] In some examples, the photo sensors comprise one or more

spectrometers and/or one or more cameras.

[00105] In some examples, the photo sensors comprise a Raman spectrometer and a camera.

[00106] In some examples, the one or more light spectra comprise two or more of a UV spectrum, visible light spectrum, IR spectrum, and NIR spectrum.

[00107] In some examples, the sensing is performed by a first computing device and the determining, identifying, and displaying are performed by a second computing device in communication with the first computing device. [00108] In some examples, the method further comprises: wirelessly transmitting the sensed data from the first computing device to the second computing device.

[00109] In some examples, the first computing device is a sensor device and the second computing device is a personal wireless communication device.

[00110] In some examples, the sensor device and personal wireless

communication device are coupled via a short range wireless communication protocol.

[00111] In some examples, the short range wireless communication protocol is Bluetooth.

[00112] In accordance with a further aspect of the present disclosure, there is a provided a machine-implemented method of identifying a plant and/or a plant state, comprising : sensing via gas sensors a plurality of gases in the ambient air surrounding a plant; determining a gas profile based on the sensed gases; sensing via photo sensors one or more light spectra of the plant; and identifying a plant and/or a plant state based on the gas profile and the sensed one or more light spectra.

[00113] In some examples, the method further comprises displaying an identification of the plant and/or the plant state.

[00114] In some examples, the method further comprises determining information associated with the identified plant and/or the plant state.

[00115] In some examples, the method further comprises displaying an identification of the plant and/or the plant state and the information associated with the identified plant and/or the plant state.

[00116] In some examples, the information comprises an effects profile associated with consumption of plant material based on the identified plant and/or the plant state.

[00117] In some examples, the effects profile comprises any combination of psychological effects, physiological effects, therapeutic effects and/or side effects.

[00118] In some examples, the information comprises a plurality of effects profiles, each effects profile being associated with consumption of plant material based on the identified plant and/or the plant state and a type of consumption.

[00119] In some examples, the gas profile comprises one of a cannabinoid profile, a terpene profile, a flavonoid profile, or a combination of thereof.

[00120] In some examples, the gas profile comprises a terpene profile comprising a composition of a plurality of terpenes selected from the group consisting of any combination of pinene (typically a-pinene and/or p-pinene), myrcene, limonene, humulene, linalool, caryophyllene (typically b-caryophyllene), terpinolene, ocimene, camphene, terpineol, phellandrene, careen (typically Delta 3 carene), humulene, pulegone, sabinene, a-bisabolol (also known as levomenol and bisabolol), eucalyptol, trans-nerolido, borneol, valencene or geraniol.

[00121] In some examples, the gas profile comprises a terpene profile comprising a composition of a plurality of terpenes selected from the group consisting of any combination of pinene, myrcene, limonene, humulene, linalool, caryophyllene, or terpinolene.

[00122] In some examples, each gas sensor in the plurality of gas sensors is preferentially sensitive to one or more gases, each gas sensor in the plurality of gas sensors outputting a voltage representative voltage of the sensed gases.

[00123] In some examples, determining the gas profile based on the sensed gases comprises determining from a library of gas profiles an gas profile matching the sensed gases by comparing a composition of the sensed gases to a composition of gases in each gas profile in the library of gas profiles.

[00124] In some examples, identifying the plant and/or the plant state based on the gas profile comprises determining from a library of plant profiles one or more of the plant or the plant state based on the matching gas profile by comparing the matching gas profile to each plant profile in the library of plant profiles.

[00125] In some examples, the gas profile comprises one of a cannabinoid profile, a terpene profile, a flavonoid profile, or a combination of thereof.

[00126] In some examples, the gas profile comprises a terpene profile comprising a composition of a plurality of terpenes selected from the group consisting of any combination of pinene (typically a-pinene and/or p-pinene), myrcene, limonene, humulene, linalool, caryophyllene (typically b-caryophyllene), terpinolene, ocimene, camphene, terpineol, phellandrene, careen (typically Delta 3 carene), humulene, pulegone, sabinene, a-bisabolol (also known as levomenol and bisabolol), eucalyptol, trans-nerolido, borneol, valencene or geraniol.

[00127] In some examples, the gas profile comprises a terpene profile comprising a composition of a plurality of terpenes selected from the group consisting of any combination of pinene, myrcene, limonene, humulene, linalool, caryophyllene, or terpinolene.

[00128] In some examples, the plant profiles correspond to cannabis strains.

[00129] In some examples, thephoto sensors comprise one or more

spectrometers and/or one or more cameras.

[00130] In some examples, the photo sensors comprise a Raman spectrometer and a camera.

[00131] In some examples, the one or more light spectra comprise two or more of a UV spectrum, visible light spectrum, IR spectrum, and NIR spectrum. [00132] In some examples, the sensing is performed by a first computing device and the determining, identifying, and displaying are performed by a second computing device in communication with the first computing device.

[00133] In some examples, the method further comprises: wirelessly transmitting the sensed data from the first computing device to the second computing device.

[00134] In some examples, the first computing device is a sensor device and the second computing device is a personal wireless communication device.

[00135] In some examples, the sensor device and personal wireless

communication device are coupled via a short range wireless communication protocol.

[00136] In some examples, the short range wireless communication protocol is Bluetooth.

[00137] In some examples, the method further comprises: sensing via one or more particulate sensors particulates in the ambient air surrounding the plant; wherein the plant and/or the plant state is identified based on the gas profile, the sensed one or more light spectra, and one or more types and an amount or concentration of particulates sensed by the particulate sensors.

[00138] In some examples, the plant state comprises plant health and/or stage of development.

[00139] In some examples, the plant health is identified.

[00140] In some examples, identifying the plant state comprises: determining the plant health.

[00141] In some examples, determining the plant health comprises: identifying any diseases or infestations from molds, fungi, yeasts, spores, insects or other pest organisms.

[00142] In some examples, the method further comprises: determining whether the plant health matches criteria for quarantine or isolation; and

generating an alert when the plant health matches criteria for quarantine or isolation.

[00143] In some examples, the alert includes a plant identifier identifying the plant.

[00144] In some examples, the alert comprises one or more of a geolocation of the plant, such as a GNSS location, a map indicating the geolocation of the plant within a growing environment, such as a greenhouse, or directions to the

geolocation of the plant from a reference location.

[00145] In some examples, generating the alert comprises: generating an electronic message; and sending the electronic message to one or more designated addresses.

[00146] In some examples, generating the alert comprises: displaying the alert on a display of a user terminal.

[00147] In accordance with a further aspect of the present disclosure, there is a provided a machine-implemented method of determining a plant state,

comprising : sensing via particulate sensors particulates in the ambient air surrounding a plant; determining one or more types and an amount or

concentration of particulates the output by the particulate sensors; and determining whether the types and amount or concentration of the particulates in the ambient air surrounding the plant match criteria for quarantine or isolation.

[00148] In some examples, determining whether the types and amount or concentration of the particulates in the ambient air surrounding the plant match criteria for quarantine or isolation comprises: determining whether to quarantine or isolate the plant in accordance with the sensed data by comparing the types and amount or concentration of the particulates in the ambient air surrounding the plant to types of particulates predetermined to be harmful and a threshold amount or concentration of particulates for quarantine or isolation.

[00149] In some examples, the method further comprises: determining to quarantine or isolate the plant in response to a determination that the types of particulates in the ambient air include one or more types of particulates

predetermined to be harmful and the amount or concentration of the particulates predetermined to be harmful in the ambient air exceeds the threshold amount or concentration of particulates for quarantine or isolation.

[00150] In some examples, the types of particulates predetermined to be harmful comprise any combination of molds, fungi, yeasts, spores or pollen.

[00151] In accordance with a further aspect of the present disclosure, there is a provided a machine-implemented method of determining a plant state,

comprising : scanning a plant with a plurality of sensors to generate sensor data; determining a plant state based on the sensor data; and determining an action to be performed based on the plant state.

[00152] In some examples, the action is selected from one of the group comprising modifying current environment or growing conditions of the plant, maintaining environment or growing conditions of the plant, quarantining or isolating the plant, or harvesting the plant.

[00153] In some examples, the plant state comprises plant health and/or stage of development.

[00154] In some examples, the method further comprises: while a sensor device carrying the sensors is in a metering mode: determining a distance to the plant or plant material via a proximity sensors; in response to determining the distance to the plant or plant material is exceeds the proximity threshold,

prompting a user to move the sensor device towards the plant or plant material until the determined distance is within the proximity threshold; in response to determining the distance to the plant or plant material is within the proximity threshold, scanning the plant or plant material with the sensors.

[00155] In some examples, the proximity threshold is calibrated to a sensitivity of the sensors.

[00156] In accordance with a further aspect of the present disclosure, there is a provided a handheld computing device, comprising: a plurality of sensors; a processor coupled to the sensors; wherein the processor is configured to perform the methods described above.

[00157] In some examples, the sensors comprises a plurality of gas sensors for sensing a plurality of gases in ambient air, a plurality of photo sensors for sensing one or more light spectra, and one or more particulate sensors particulates in ambient air.

[00158] In accordance with a further aspect of the present disclosure, there is a provided a growing system, comprising : a plurality of sensors for sensing one or both of parameters of a plant or parameters of an environment in which the plant is being grown; an environmental control system for controlling one or more growing conditions of the plant; a controller coupled to the plurality of sensors and configured to: receive sensor data from the plurality of sensors; determine whether parameters based at least in part on the sensor data match one or more

performance criteria; and cause the environmental control system to perform an adjustment to at least one growing condition of the plant in response to a

determination that the parameters do not match the one or more performance criteria.

[00159] In some examples, the controller is configured to: cause the

environmental control system to maintain existing growing conditions of the plant in response to a determination that the parameters match the one or more performance criteria.

[00160] In some examples, the controller is configured to: generate a first notification regarding the determination that the parameters do not match the one or more performance criteria.

[00161] In some examples, the controller is configured to: generate a second notification including a description of the adjustment to the at least one growing condition of the plant.

[00162] In some examples, the first notification and second notification are provided in the same electronic message.

[00163] In some examples, the first notification and second notification are displayed at the same time.

[00164] In some examples, the plurality of sensors comprise a plurality of sensors for sensing parameters of the one or more plant and a plurality of environmental sensors for sensing parameters of the environment in which the plant are being grown.

[00165] In some examples, the controller is configured to: determine the adjustment based on the sensor data and the one or more performance criteria, wherein one or more subsystems of the environmental control system is adjusted by the determined adjustment.

[00166] In some examples, the adjustment specifies one or more subsystems of the environmental control system to be adjusted, and one or both of a type and amount of adjustment for each of the or more subsystems of the environmental control system to be adjusted.

[00167] In some examples, the controller is configured to receive input from a user input device or connected computing device, wherein the parameters are based on the sensor data and input received from a user input device or connected computing device.

[00168] In some examples, the plant is a cannabis plant and the input comprises an amount of any one of cannabinoids measured in harvested plant material, cannabis terpenes measured in harvested plant material, cannabis flavonoids measured in harvested plant material, or a combination of thereof.

[00169] In some examples, the plurality of sensors comprise gas sensors and the one or more performance criteria comprise a gas profile of the air surrounding the plant.

[00170] In some examples, the gas profile comprises an aromatic profile of the air surrounding the plant.

[00171] In some examples, the plant is a cannabis plant and the gas profile comprises any one of a cannabinoid profile, a cannabis terpene profile, a cannabis flavonoid profile, or a combination of thereof.

[00172] In some examples, the cannabinoid profile represents a composition of cannabinoids in the air surrounding the plant, the cannabis terpene profile

represents a composition of cannabis terpenes in the air surrounding the plant, and the cannabis flavonoid profile represents a composition of cannabis flavonoids in the air surrounding the plant.

[00173] In some examples, the terpene profile comprises a composition of a plurality of terpenes selected from the group consisting of any combination of pinene, myrcene, limonene, humulene, linalool, caryophyllene, or terpinolene.

[00174] In some examples, the terpene profile comprises a composition of a plurality of terpenes selected from the group consisting of any combination of pinene (typically a-pinene and/or b-pinene), myrcene, limonene, humulene, linalool, caryophyllene (typically b-caryophyllene), terpinolene, ocimene, camphene, terpineol, phellandrene, careen (typically Delta 3 carene), humulene, pulegone, sabinene, a-bisabolol (also known as levomenol and bisabolol), eucalyptol, trans- nerolido, borneol, valencene, or geraniol.

[00175] In some examples, the cannabinoid profile comprises a composition of a plurality of terpenes selected from the group consisting of any combination of tetrahydrocannabinol (THC), cannabidiol (CBD), cannabinol (CBN), tetrahydrocannabinolic acid (THCA), CBDA (cannabidiolic acid), CBG (cannabigerol), cannabichromene (CBC), cannabicyclol (CBL), cannabivarin (CBV),

tetrahydrocannabivarin (THCV), CBDV (cannabidivarin), cannabichromevarin

(CBCV), cannabigerovarin (CBGV), cannabigerol monomethyl ether (CBGM), cannabielsoin (CBE), or cannabicitran (CBT).

[00176] In some examples, the cannabis flavonoid profile comprises a composition of a plurality of terpenes selected from the group consisting of any combination of anthocyanidins, flavan-3-ols, flavonols, flavones, flavanones, or isoflavones.

[00177] In some examples, the cannabis flavonoid profile comprises a composition of a plurality of terpenes selected from the group consisting of any combination of cannaflavin A, cannaflavin B, cannaflavin C, b-sitosterol, vitexin, isovitexin, apigenin, kaempferol, quercetin, luteolin, or orientin.

[00178] In some examples, the one or more performance criteria comprise a plant state, and the controller is configured to determine a plant state from the sensor data.

[00179] In some examples, the plurality of sensors comprises gas sensors for sensing a plurality of gases in the ambient air surrounding the plant, and wherein controller is configured to: determine a gas profile based on the sensed gases;

determine the plant state from the gas profile.

[00180] In some examples, the plurality of sensors comprises photo sensors one or more light spectra of the plant, wherein controller is configured to:

determine the plant state from the gas profile and the sensed one or more light spectra.

[00181] In some examples, the photo sensors comprise one or more

spectrometers and/or one or more cameras.

[00182] In some examples, the photo sensors comprise a Raman spectrometer and a camera. [00183] In some examples, the one or more light spectra comprise two or more of a UV spectrum, visible light spectrum, IR spectrum, and NIR spectrum.

[00184] In some examples, the plurality of sensors comprises one or more particulate sensors particulates in the ambient air surrounding the plant, wherein controller is configured to: determine the plant state from the gas profile, the sensed one or more light spectra, and one or more types and an amount or concentration of particulates sensed by the particulate sensors.

[00185] In some examples, the plurality of sensors comprises photo sensors one or more light spectra of the plant, wherein controller is configured to:

determine the plant state from the sensed one or more light spectra.

[00186] In some examples, the plurality of sensors comprises one or more particulate sensors particulates in the ambient air surrounding the plant, wherein controller is configured to: determine the plant state from an amount or

concentration of particulates sensed by the particulate sensors.

[00187] In some examples, the plant state comprises plant health and/or stage of development.

[00188] In some examples, the plant is a cannabis plant and the one or more performance criteria comprise an amount of specific cannabinoids in harvested plant material.

[00189] In some examples, the one or more performance criteria defines an amount of tetrahydrocannabinol (THC), cannabidiol (CBD), cannabinol (CBN), tetrahydrocannabinolic acid (THCA), CBDA (cannabidiolic acid), CBG (cannabigerol), cannabichromene (CBC), cannabicyclol (CBL), cannabivarin (CBV),

tetrahydrocannabivarin (THCV), CBDV (cannabidivarin), cannabichromevarin

(CBCV), cannabigerovarin (CBGV), cannabigerol monomethyl ether (CBGM), cannabielsoin (CBE), or cannabicitran (CBT).

[00190] In some examples, the one or more performance criteria defines an amount of one or both of THC and CBD. [00191] In some examples, the one or more performance criteria comprise an amount of harvested plant material.

[00192] In some examples, the amount of harvested plant material is based on one or more of a weight of harvested plant material, a number of harvested floral buds, or weight of harvested floral buds.

[00193] In some examples, the one or more performance criteria comprises a color profile of the plant.

[00194] In some examples, the color profile is based color wavelength, intensity, absorbance, fluorescence, and scattering.

[00195] In some examples, the one or more performance criteria comprises a light profile in which the intensity, timing/frequency and wavelength of light is defined over a threshold duration.

[00196] In some examples, the threshold duration is a 24 hour duration.

[00197] In some examples, the ambient light in the environment of the plant is measured by one or more photo sensors , wherein the ambient light is adjusted by one or more LED modules to provide supplemental light at an intensity,

time/frequency and wavelength so that the ambient light measured by the one or more photo sensors matches the light profile.

[00198] In some examples, the one or more performance criteria comprise an audio profile, wherein ambient audio in the environment surrounding the plant is measured by one or more microphones or audio sensors, wherein the ambient audio is adjusted via speakers by reproducing sounds, tones or music so that the ambient audio measured by the one or more microphones or audio sensors matches the audio profile.

[00199] In some examples, the one or more performance criteria comprise a growth stage of the plant, wherein the sensors determine a current growth stage of the plant and the controller causes the one or more subsystems of the environmental control system to adjust the at least one growing condition to optimize the at least one growing condition for the current growth stage of the plant.

[00200] In some examples, the one or more subsystems of the environmental control system are adjusted to encourage rapid maturation of the plant through to the vegetative stage, after which growing conditions are sequentially modified to encourage flowering, pollination, and seed-setting, respectively.

[00201] In some examples, the one or more subsystems of the environmental control system are adjusted at the onset of fruiting to encourage fruit development and ripening.

[00202] In some examples, the performance criteria comprises a condition of the plant.

[00203] In some examples, the plant comprises one or a combination of a color of the leaves, leaf surface area, leaf temperature, stem thickness, root depth, root coloration, or the presence of a fungal or insect infestation.

[00204] In some examples, the one or more performance criteria comprise a condition of a growth medium in which the plant being grown.

[00205] In some examples, the condition of the growth medium comprises a nutrient content, pH, moisture level, or temperature of the soil.

[00206] In some examples, the one or more performance criteria comprise a cost, revenue or profit.

[00207] In some examples, the growing system further comprises: a plant growth apparatus housing the plant being grown within a growth medium, the plant growth apparatus carrying at least some of the plurality of sensors.

[00208] In some examples, the plant growth apparatus houses an individual plant. [00209] In some examples, the growing system simultaneously senses and controls the growing conditions of a plurality of plants in one or more growing facilities.

[00210] In some examples, the growing system individually controls the growing conditions of each plant via one or more effectors provided for each plant.

[00211] In some examples, the controller is machine learnt.

[00212] In some examples, the controller applies machine learning.

[00213] In some examples, at least some of the sensors are carried by a plurality of first sensor devices located in a growing facility in which the plant are grown, wherein the plurality of first sensor devices wirelessly communicate with the controller.

[00214] In some examples, the plurality of first sensor devices are configured to be handheld.

[00215] In some examples, the plurality of first sensor devices are configured to be portable.

[00216] In some examples, the growing system further comprises: a

conveyance control subsystem configured to convey the plurality of first sensor devices around the growing facility.

[00217] In some examples, the conveyance control subsystem comprises one or more of a crawler which traverses an overhead track or gantry scaffold of the growing facility, drone, unmanned aerial vehicle (UAV), or other robotic vehicle or system.

[00218] In some examples, the crawler, drone or UAV may be remotely controlled by a user or robotically controlled, either autonomously or semi- autonomously.

[00219] In some examples, at least some of the sensors are carried by a plurality of second sensor devices which located remotely from the growing facility in which the plant are grown, wherein the plurality of second sensor devices wirelessly communicate with the controller, wherein the sensor data provided by the plurality of second sensor devices is associated with plant material derived from plant grown in the growing facility.

[00220] In some examples, the plurality of second sensor devices are configured to be handheld.

[00221] In some examples, the plurality of second sensor devices are configured to be portable.

[00222] In some examples, the controller is configured to: encode at least some of the sensor data as a visual representation, wherein the visual

representation provides a parameter for determining whether parameters based at least in part on the sensor data match the one or more performance criteria.

[00223] In some examples, the controller is configured to: generate a visual representation based on at least some of the sensor data, wherein the visual representation provides a parameter for determining whether parameters based at least in part on the sensor data match the one or more performance criteria.

[00224] In some examples, the controller is configured to: determine one or more growth parameters or plant conditions based on at least some of the sensor data, wherein the growth parameter or plant condition provides a parameter for determining whether parameters based at least in part on the sensor data match the one or more performance criteria.

[00225] In some examples, the controller is configured to: determine one or more growth parameters or plant conditions based on at least some of the current sensor data and historical sensor data, wherein the growth parameter or plant condition provides a parameter for determining whether parameters based at least in part on the sensor data match the one or more performance criteria.

[00226] In some examples, the one or more growth parameters or plant conditions comprise the one or more performance criteria.

[00227] In some examples, the one or more performance criteria comprise one or more of leaf colour, leaf area, leaf temperature, stem thickness, root depth, root colour, the presence of floral buds, the size of floral buds, a gas profile of the air surrounding the plant, presence of mold, fungi, yeast, spores, insects or other pest organisms, or a combination thereof.

[00228] In some examples, the one or more performance criteria comprise a condition of the growth medium.

[00229] In some examples, the condition of the growth medium is indicated by its nutrient content, pH, EC, moisture level, temperature, or combinations thereof.

[00230] In some examples, the one or more performance criteria comprise a growth rate or a maturity level of the plant.

[00231] In some examples, the growth rate or maturity level of the plant is indicated by the height of the plant, stem thickness, leaf area, the presence of floral buds, the size of floral buds, a gas profile of the air surrounding the plant, or combinations thereof.

[00232] In some examples, the maturity level is a vegetative growth stage.

[00233] In some examples, the maturity level is a flowering, budding or fruiting stage.

[00234] In some examples, the one or more performance criteria are

dependent on the type of plant.

[00235] In some examples, the at least one growing condition that is adjusted comprises at least one of lighting, C0 ₂ concentration, temperature, moisture levels, nutrient levels, gas profile or a combination thereof.

[00236] In some examples, the at least one growing condition that is adjusted is a spectrum and/or intensity of lighting. [00237] In some examples, the sensors comprise one or more of a thermometer, hygrometer, oxygen sensor, carbon dioxide meter, anemometer, light meter, photo sensor, camera, spectrometer, pH meter, EC meter, NPK meter, FLIR camera, caliper, or combinations thereof.

[00238] In some examples, the one or more performance criteria comprise one or more of ambient temperature, ambient humidity, C0 ₂ concentration, 0 ₂ concentration, air flow, lighting intensity, lighting frequency, lighting wavelength, growing media pH, growing media EC, moisture level of the growing media, temperature of the growing media, or combinations thereof.

[00239] In some examples, the environmental control system is coupled to one or more effectors selected from the group consisting of a heating system, an air conditioning system, a humidifier, a metered 02 source or mixer, a metered C02 source or mixer, a fan, a growth lamp, an LED array, a timer, a selective or filtered light source, a pH dosing unit, a metered nutrient source, a metered watering source, a growth media heating or chilling unit, or combinations thereof.

[00240] In some examples, the adjustment encourages maturation of the plant or discourages maturation of the plant.

[00241] In some examples, the adjustment encourage the content of specific cannabinoids, specific cannabis terpenes, specific cannabis flavonoids, or a specific combination thereof.

[00242] In accordance with a further aspect of the present disclosure, there is a provided a machine-implemented method for controlling plant growth,

comprising : receiving sensor data from a plurality of sensors for sensing one or both of parameters of one or more plants or parameters of an environment in which the one or more plants are being grown; determining whether parameters based at least in part on the sensor data match one or more performance criteria; and causing the environmental control system to perform an adjustment to at least one growing condition of the one or more plants in response to a determination that the parameters do not match the one or more performance criteria. [00243] In accordance with a further aspect of the present disclosure, there is a provided a computing device, comprising a processor configured to perform the method of described above.

[00244] In accordance with a further aspect of the present disclosure, there is a provided a plurality of sensors for sensing one or both of parameters of a plant or parameters of an environment in which the plant is being grown; an environmental control system for controlling one or more growing conditions of the plant; a controller coupled to the plurality of sensors and configured to: receive sensor data from the plurality of sensors; determine whether parameters based at least in part on the sensor data match one or more performance criteria; andgenerate a notification in response to a determination that the parameters do not match the one or more performance criteria.

[00245] In accordance with a further aspect of the present disclosure, there is a provided a machine-implemented method for monitoring plant growth,

comprising : receiving sensor data from a plurality of sensors for sensing one or both of parameters of one or more plants or parameters of an environment in which the one or more plants are being grown; determining whether parameters based at least in part on the sensor data match one or more performance criteria; and generating a notification in response to a determination that the parameters do not match the one or more performance criteria.

[00246] In accordance with a further aspect of the present disclosure, there is a provided a computing device, comprising a processor configured to perform the method of described above.

[00247] In accordance with a further aspect of the present disclosure, there is a provided a plurality of sensors for sensing parameters of phototrophic organisms or parameters of an environment in which the phototrophic organisms are being grown; an environmental control system for controlling one or more growing conditions of the phototrophic organisms; a controller coupled to the plurality of sensors and configured to: receive sensor data from the plurality of sensors;

determine whether parameters based at least in part on the sensor data match one or more performance criteria; and cause the environmental control system to perform an adjustment to at least one growing condition of the phototrophic organisms in response to a determination that the parameters do not match the one or more performance criteria.

[00248] In accordance with a further aspect of the present disclosure, there is a provided a machine-implemented method for controlling the growth of phototrophic organisms, comprising : receiving sensor data from a plurality of sensors for sensing one or both of parameters of phototrophic organisms or parameters of an environment in which the phototrophic organisms are being grown; determining whether parameters based at least in part on the sensor data match one or more performance criteria; and causing the environmental control system to perform an adjustment to at least one growing condition of the phototrophic organisms in response to a determination that the parameters do not match the one or more performance criteria.

[00249] In accordance with a further aspect of the present disclosure, there is a provided a computing device, comprising a processor configured to perform the method of described above.

[00250] In accordance with a further aspect of the present disclosure, there is a provided a growing system, comprising : a plurality of sensors for sensing parameters of phototrophic organisms or parameters of an environment in which the phototrophic organisms are being grown; an environmental control system for controlling one or more growing conditions of the phototrophic organisms; a controller coupled to the plurality of sensors and configured to: receive sensor data from the plurality of sensors; determine whether parameters based at least in part on the sensor data match one or more performance criteria; and generate a notification in response to a determination that the parameters do not match the one or more performance criteria.

[00251] In accordance with a further aspect of the present disclosure, there is a provided a machine-implemented method for monitoring the growth of phototrophic organisms, comprising : receiving sensor data from a plurality of sensors for sensing one or both of parameters of phototrophic organisms or parameters of an environment in which the phototrophic organisms are being grown; determining whether parameters based at least in part on the sensor data match one or more performance criteria; andgenerating a notification in response to a determination that the parameters do not match the one or more performance criteria.

[00252] In accordance with a further aspect of the present disclosure, there is a provided a computing device, comprising a processor configured to perform the method of described above.

[00253] In accordance with a further aspect of the present disclosure, there is a provided a method of formulating an infused consumable product, comprising: receiving a consumable product profile specifying an effects profile; and

determining an active ingredient profile specifying a plurality of active ingredients matching the consumable product profile, wherein the active ingredient profile specifies a combination of one or more cannabinoids and one or more terpenes.

[00254] In some examples, the active ingredient profile specifies one or more cannabinoids, one or more terpenes, and a relative amount of each of the cannabinoids and terpenes.

[00255] In some examples, the active ingredient profile specifies a combination of one or more cannabinoids, one or more terpenes and one or more flavonoids.

[00256] In some examples, the active ingredient profile specifies one or more cannabinoids, one or more terpenes, one or more flavonoids and a relative amount of each of the cannabinoids, terpenes and flavonoids.

[00257] In some examples, the effects profile specifies any combination of psychological effects, physiological effects, therapeutic effects and/or side effects.

[00258] In some examples, the effects profile specifies any combination of one or more desired psychological effects, one or more undesired psychological effects, one or more desired physiological effects, one or more undesired physiological effects, one or more desired therapeutic effects, one or more undesired therapeutic effects, one or more medical conditions treated desired to be treated, one or more medical conditions treated undesired to be treated, one or more desired side effects or one or more undesired side effects.

[00259] In some examples, the effects profile further specifies an intensity of each specified psychological effect, physiological effect, therapeutic effect and side effect.

[00260] In some examples, the consumable product profile further specifies a consumable product type.

[00261] In some examples, the method further comprises: determining a consumable product type based on the active ingredient profile.

[00262] In some examples, the method further comprises: determining an amount of each active ingredient in the active ingredient profile based on the product type and the intensity of each specified psychological effect, physiological effect, therapeutic effect and side effect.

[00263] In some examples, the consumable product type is selected from one of the group consisting of a food, a beverage or a capsule.

[00264] In some examples, the consumable product profile further specifies a food type selected from the group consisting of baked goods, candy, oils and diary products.

[00265] In some examples, the baked goods food type is selected from the group consisting of potato chips, nacho chips, crackers, cookies, brownies, cakes and cupcakes.

[00266] In some examples, the candy food type is selected from the group consisting of gummy candies, hard candies, and chocolates.

[00267] In some examples, the diary product type is selected from the group consisting of yogurt, cheese, butter and cream. [00268] In some examples, the beverage type is selected from the group consisting of water, soda or pop, tea, herbal tea, coffee, caffeinated energy drink, non-caffeinated energy drink, liquid meal replacement, beer, bhang lassi, bhang thandai, wine, liquor-based mixed beverage, or tincture.

[00269] In some examples, the method further comprises: preparing a food or beverage infused with the combination of active ingredients in the active ingredient profile in the relative amounts.

[00270] In some examples, the method further comprises: preparing a composition of the active ingredients in the active ingredient profile and a carrier.

[00271] In some examples, the method further comprises: preparing a food or beverage infused with the composition.

[00272] In some examples, the method further comprises: determining an amount of each active ingredient in the active ingredient profile based on the intensity of each specified psychological effect, physiological effect, therapeutic effect and side effect.

[00273] In accordance with a further aspect of the present disclosure, there is a provided a computing device having a processor and a memory coupled to the processor, the memory having tangibly stored thereon executable instructions for execution by the processor, wherein the executable instructions, when executed by the processor, cause the computing device to perform the methods described herein.

[00274] In accordance with a further aspect of the present disclosure, there is provided a non-transitory machine readable medium having tangibly stored thereon executable instructions for execution by a processor of a computing device, wherein the executable instructions, when executed by the processor, cause the computing device to perform the methods described herein.

Growing system [00275] Reference is first made to FIGs. 1A and IB which illustrates a growing system 100 in accordance with one embodiment of the present disclosure. The growing system 100 is used to control the growing conditions of a grower facility 105. The growing system 100 may be used for multivariable optimization of plant growth. The grower facility 105 is typically an indoor growing environment such as a greenhouse. The grower facility 105 is used to grow plants or other phototrophic organisms such as algae. For convenience, the phototrophic organisms grown in the grower facility 105 will be referred to hereinafter as plants 10. The plants 10 may be grown in a growing apparatus, an example of which is described below. In some embodiments, an individual growing apparatus 300 may be used to grow an individual plant 10.

[00276] The growing system 100 may be used to monitor and adjust growing conditions via an environmental control system 210 in response to sensor data as described more fully below. The growing system 100 comprises the environmental control system 210, a plurality of grower sensor devices 110, a plurality of consumer sensor devices 120, a plurality of plant sensors 132, a plurality of environmental sensors 134, a plurality of operational sensors (or meters) 136, each of which is coupled to an artificial intelligence (AI) controller 150 of the growing system 100.

[00277] The AI controller 150 comprises a number of functional modules such as an application server module 160 providing various server-side application support, an access control module 204 controlling access to and communication with the AI controller 150, an analytics module 206, an AI module 208 providing machine learning/artificial intelligence functionality, and a plurality of databases 205. Alternatively, in other embodiments the application server 160 may be distinct from the AI controller 150. The analytics module 206 may perform analytics such as data mining, trend detection, pattern detection, and product tracking.

[00278] The AI controller 150 may communicate with third party servers 235 and/or third party systems 260 via one or more communications networks such as the Internet. The AI controller 150 is typically located behind a firewall 215 to protect the AI controller 150. The third party servers 235 may be used to access external data sources 255 such as databases providing supplemental data (e.g., operational data or cost data) which may be used by the AI controller 150 in decision making. The third party servers 235 may be operated by utility companies providing utilities (e.g., power, water, gas, nutrients, etc.) to the grower facility 105 and the supplemental data may comprise current and/or past utility (costs) prices. The cost data is typically associated with a date/time, thereby allowing the AI controller 150 to utilize cost information in decision making. The costs may be positive or negative depending on the particular type of utility, the particular utility provider, and the particular demand at a particular date and time. For example, electricity prices may be negative when sufficient excess electrical capacity exists in the electrical grid, effectively paying an operator of the growing system 100 to consume power. Third party systems 260, which may be operated by

clients/customers or governments/regulators, may communicate with the AI controller 150 and/or application server 160 connected to the AI controller 150 through the firewall 215 when authorized and authenticated.

[00279] Data and communications exchanged between devices in the growing system 100, and other devices that communicate with the growing system 100, may be encrypted for security using, for example, Transport Layer Security (TLS), its predecessor Secure Sockets Layer (SSL), or other cryptographic protocols for secure communication.

[00280] TLS and SSL encrypt network connections above the transport layer using symmetric cryptography for privacy and a keyed message authentication code for message reliability. When data is secured using TSL or SSL, cryptographic keys for communication are typically stored in a persistent memory of the participating communication devices. In some examples, some of the data exchanged within the growing system 100 may be secured via blockchain- encrypted data packets which may be part of a so-called "seed to sale" blockchain managed by, or for, the grower. Other data, such as a control signals and

messages sent from the AI controller 150 to the environmental control system 210 may not be part of the blockchain but may still be encrypted for security. [00281] The grower sensor devices 110, consumer sensor devices 120, plant sensors 132, environmental sensors 134, and operational sensors 136 communicate with the AI controller 150 by means of either a wired or wireless connection. The grower sensor devices 110 typically communicate with the AI controller 150 via a wireless connection. The grower sensor devices 110 may communicate with the AI controller 150 via a wireless transceiver of the grower sensor devices 110 allows the grower sensor devices 110 to connected to a wireless local area network

(WLAN) or wireless wide area network (WWAN) to which the AI controller 150 is connected, either directly or indirectly. In embodiments in which the AI controller 150 is connected to a WLAN, the WLAN is Wi-Fi™ network and the wireless transceiver of the grower sensor devices 110 is, or comprises, a Wi-Fi™ transceiver. In embodiments in which the AI controller 150 is connected to a WWAN, the WWAN is cellular radio access network (CRAN) and the wireless transceiver of the grower sensor devices 110 is, or comprises, a cellular transceiver. The AI controller 150 may be located remotely from the grower facility 105 or on the same physical premise as the grower facility 105.

[00282] The plant sensors 132 and environmental sensors 134 may be battery powered or connected to a low-voltage electrical power supply. The grower sensor devices 110 and consumer sensor devices 120 are typically battery powered, for example, via rechargeable battery. The operational sensors 136 are typically part of, and powered by, a respective environmental control system 210.

[00283] Although the grower sensor devices 110 are shown connecting directly to the AI controller 150 in FIG. 1A and IB, the grower sensor devices 110 may connect indirectly to the AI controller 150 via a personal wireless communication device 130, a growing apparatus 300 (FIGs. 3A and 3B) or other communication device to which it is connected or tethered, by means of either a wired or wireless connection.

[00284] The AI controller 150 may communicate with the consumer sensor devices 120 via the application server 160 via one or more wireless connections or links. Alternatively, the consumer sensor devices 120 may communicate with the AI controller 150 without the application server 160 as an intermediary. The consumer sensor devices 120 comprise a plurality of sensors for sensing one or more parameters of a plant or plant material such as cuttings, leaves, buds (or flowers), etc., which may be unprocessed or processed (e.g., dried and/or crushed, etc.).

The wireless connection between a consumer sensor device 120 and the application server 160 may be provided by a pair of wireless connections: (1) a short-range wireless connection, such as a Bluetooth® connection, to a personal wireless communication device 130 of a consumer, such as a smartphone or tablet, to which the consumer sensor device 120 is connected or tethered; and (2) a long-range wireless connection, such as a cellular radio access network (CRAN) connection, between the personal wireless communication device 130 and the application server 160 (or AI controller 150).

Plant Sensors

[00285] The plant sensors 132 senses or monitors one or more parameters of one or more plants 10 (referred to as "plant parameters"), which may be grown in a growing apparatus 300 (FIGs. 3A and 3B). The parameters sensed by the plant sensors 132 may comprise, but are not limited to, any combination of a gas profile (e.g., a volatile compound profile or aromatic profile) of gases emitted by the plants 10, airborne particulates emitted by the plants 10, color of the leaves or other plant feature, plant maturity, plant height, plant weight, plant weight. The sensed parameters may be used to identify a plant 10 and/or state of the plant 10, such as the plant health or stage of development. For example, the sensed parameters may be used to detect leaf discoloration, plant diseases and/or infestations from molds, fungi, yeasts, spores, insects or other pest organisms.

[00286] The plant sensors 132 may comprise, but are not limited to, any combination of a photo sensor (or photo sensor) for determining a color of the leaves or other parts of the plants 10, a digital camera for imaging the plants 10, an infrared (IR) sensor or camera for infrared imaging of the plants 10, a three- dimensional (3D) scanner, a LiDAR (Light Detection and Ranging) module, RADAR module, SONAR module or other time-of-flight (TOF) module sensor for generating a 3D model of the plants 10, a strain gauge for measuring a weight of the plants 10, or a digital caliper for measuring a thickness of the stem of the plants 10, for example, at a fixed height from the ground or a growing surface on which the plants 10 are positioned (which may be a growing table or a base of a growing apparatus 300 (FIGs. 3A and 3B) in which the plants 10 are being grown).

[00287] The photo sensor may comprise one or more cameras and/or one or more spectrometers which obtain one or more light spectra from a plant 10 or plant component such as a leaf. The spectrometer may comprise one or more of the following devices, possibly operating in combination or conjunction : a Raman spectrometer containing a light source, lens, grating and detector; a different type of spectrometer such as an infrared absorption spectrometer, a mass spectrometer, or an atomic absorption spectrometer; a different kind of device containing a detector sensitive to the wavelength composition of the electromagnetic radiation transmitted through, reflected by, or radiated by, a plant 10 or plant component. The cameras and/or spectrometers may be used to obtain a plurality of light spectra of the same plant sample at approximately the same time, the light spectra in the plurality of light spectra being different from each other. The light spectra may be obtained under different lighting conditions. In one example, a camera is used to obtain a first light spectrum (such as a color photograph) and a

spectrometer, such as a Raman spectrometer, is used to obtain a second light spectrum (such as a Raman, emission, reflection, diffusion, or transmission spectrum).

[00288] Alternatively, or in addition to the above, the photo sensor may comprise a laser or other suitable light emitter paired with a light detector having a lock-in amplifier. The laser and light detector may be located on opposites of a plant 10 or plant component (e.g., leaf, canopy, etc.) and configured such that light that is emitted from the laser and passes through the leaf, canopy or other part of the plant 10 is detected by the light detector despite the presence/interference of other light sources such as sunlight or artificial lights in the grower facility 105 (e.g., overhead lights or LED modules of a growing apparatus). The lock-in amplifier may be configured to extract light pulses emitted at frequencies corresponding to those of the light emitter from the light detected by the light detector. For example, the lock-in amplifier may be configured to extract

florescence at 590 nm or a band of wavelengths centred at or around 590 nm. The detected light may be analyzed to evaluate a color profile (or light spectra) of the leaf, canopy or other part of the plant 10. The color profile/light spectra may be based on color (e.g., wavelength), intensity, absorption or absorbance,

fluorescence, and scattering. Changes in the color profile/light spectra of the leaf, canopy or other part of the plant 10 may be analyzed over the lifecycle of the plant 10.

[00289] In some examples, the photo sensors comprise a Raman spectrometer and a camera. In some examples, the one or more light spectra comprise two or more of a UV spectrum, visible light spectrum, IR spectrum, NIR spectrum, or full spectrum (e.g., UV to IR). In some examples, the one or more light spectra a sub- spectrum of visible light such as red or blue. Depending on the camera sensor and spectrometer capabilities, the above-noted light spectra may be captured by one or both of a camera or spectrometer comprising the photo sensors.

[00290] The digital camera may be a stereoscopic or 3D camera, and may capture one or both of digital photographic images or digital video. Data from one or more of the cameras, 3D scanner, LiDAR module, RADAR and SONAR module may be used to generate a 3D model of the plants 10, for example in the form of a point cloud, to determine a plant height, canopy size or other physical parameters of the plants 10 or possibly the presence of molds, fungi, yeasts, spores, insects or other pest organisms. A point cloud is a set of data points in a 3D coordinate system, in which each data point has three coordinates, namely x, y, and z coordinates, which determine where the data point is located along x, y, and z axes of the 3D coordinate system, respectively.

Environmental Sensors

[00291] The environmental sensors 134 sense or detect one or more

parameters of an environment of one or more plants 10, which may be grown in a growing apparatus. The sensed parameters may comprise a parameter of the air surrounding the plant 10 and/or a parameter of a growth medium 20 in which the plants 10 are being grown. The environmental sensors 134 sense environmental parameters of the grower facility 105 rather than parameters of attributable to plants 10. Environmental sensors of the same type may be located throughout the grower facility to sense or detect environmental parameters throughout the grower facility 105, such as microclimates.

[00292] The environmental sensors 134 may comprise, but are not limited to, any combination of a temperature sensor (e.g., thermometer) for measuring the ambient air temperature, a temperature sensor (e.g., thermometer) for measuring the growth medium (e.g., soil) temperature, a hygrometer for measuring humidity of the ambient air, a hygrometer for measuring humidity of the growth medium (e.g., soil), an 0 ₂ sensor, a C0 ₂ sensor, one or more particulate sensors, a microphone or ambient audio or acoustic sensor for measuring sound (for example, ambient sound), an anemometer for measuring air currents, a light sensor/meter for measuring an amount of light (e.g., lumens), a photo sensor for sensing wavelengths of light, a digital camera, an infrared sensor or camera, a

spectrometer, a pH sensor/meter for measuring the pH of the growth medium (e.g., soil), an EC (electrical conductivity) meter for measuring a salinity of the growth medium (e.g., soil), a nutrient sensor such as a nitrogen-phosphorus- potassium (NPK) sensor/meter for measuring nutrients in the growth medium (e.g., soil), or a radiation sensor such as a Geiger counter for measuring radiation levels.

[00293] One or more particulate sensors 248 may be used to sense or detect harmful particulates so that affected plants 10 to determine whether to admit a person or object into an area of the grower facility 105 such as a room, zone, salon or the like. The particulate sensors 248 may be located at doors, for example, on one or both sides of doors between rooms, zones, salons or the like within the grower facility 105. Door sensors, proximity sensors or motion sensors (not shown) may detect persons or objects (e.g., drones, unmanned aerial vehicles (UAVs), etc.) approaching and attempting to move between rooms, zones, salons or the like and trigger an air blast to remove particulates from persons or objects. The air may then be sensed for particulates via the particulate sensors 248 and, if harmful particulates such as molds, fungi, yeasts, spores or pollen are sensed or detected, entry into the next room, zone, or salon may be denied, for example, by a door control system (not shown).

Operational Sensors

[00294] The operational sensors 136 sense, detect or monitor an operational parameter of the growing system 100 or grower facility 105 in which the growing system 100 is operated. The operational sensors 136 may comprise, but are not limited to, an electrical power consumption meter, a water consumption meter, a gaseous consumption meter, and a nutrient consumption meter. The operational data acquired by the operational sensors 136 is stored in a sensor database by the AI controller 150. The AI controller 150 may retrieve operational data, including cost data, from the databases 205 and external data sources 255 when needed. The operational parameters and data may be used to determine a cost for the growing system 100 or grower facility 105 in which the growing system 100 is operated. Depending on the input type, some operational data may be attributable to one or more individual plant 10 whereas other operational data is only attributable to the growing system 100 or grower facility 105 in which the growing system 100 is operated. Thus, in some embodiments, some operational data may be directly associated with a plant 10 or growing apparatus via a respective device ID and/or plant ID and other operational data is only indirectly associated with a respective device ID and/or plant ID.

Application Server

[00295] The application server 160 provides cloud services such as data storage, user access, and analytics performed by the analytics module 206 of the AI controller 150 to growers and consumers. The analytics may include data mining, trend detection, pattern detection, and product tracking. The product tracking may be based on a blockchain managed by, or for, the grower, which may be part of a so-called "seed to sale" blockchain.

Environmental Control Systems [00296] The AI controller 150 communicates with the environmental control system 210 to adjust the growing conditions in response to control decisions made by the AI controller 150 based on sensor data. The environmental control system 210 comprises a lighting control subsystem 212, a HVAC (heating, ventilation, and air conditioning) control subsystem 214, a nutrient supply control subsystem 216, and the operational sensors 136. The environmental control system 210 may also comprise one or more of a conveyance control subsystem 218 and a vertical lift control subsystem 220, described more fully below. Alternatively, the conveyance control subsystem 218 and the vertical lift control subsystem 220 may be omitted or part of another control system of the grower facility 105. The conveyance control subsystem 218 may comprise one or more of a crawler which traverses an overhead track or gantry scaffold of the grower facility 105, an aerial drone or UAV, or other robotic vehicle or system. The crawler, drone or UAV may be remotely controlled by a user or robotically controlled, either autonomously or semi- autonomously.

[00297] The HVAC control subsystem 214 may include a gas supply subsystem for delivering heated or cooled air, oxygen, carbon dioxide, or possibly other gases to the plants 10. Alternatively, the gas supply subsystem may be a separate control subsystem. The environmental control system 210 is used to control the

environmental and/or growing conditions of plants 10 in the grower facility 105 such as the intensity and/or wavelength light, C0 ₂ concentration in the air, temperature, airflow, air humidity, growth medium (e.g., soil) moisture level, growth medium (e.g., soil) nutrient level, and the like in response to control decisions based on sensor data (e.g., environmental conditions and state of the plants 10). In some embodiments, local environmental conditions may be modified on per plant basis, for example, when each plant is grown in its own growing apparatus.

[00298] Each of the subsystem of the environmental control system 210 comprises one or more effectors 205 that vary based on the particular subsystem. The effectors 205 establish and/or modify the growing conditions including, but not limited to, atmospheric, lighting, nutrient, and other conditions under which the plant 10 is grown. The effectors 205 may comprise, but are not limited to, any combination of lights (such as LED modules) coupled to the lighting control subsystem 212, fans coupled to the HVAC control subsystem 214, gas outlets (or dispensers) coupled to gas supplies of the HVAC control subsystem 214, and liquid outlets (or dispensers) coupled to the nutrient supply control subsystem 216 for dispense water, nutrients or growth medium conditioners such as pH modifiers.

[00299] A particular plant sensor 132, environmental sensor 134, or operational sensor 136 may be used for more than one function. Alternatively, a dedicated sensor may be used for each function. The sensors 132, 134, 136 and effectors 205 may be of various types as appropriate for the application. Examples are provided below:

Table 1 : Exemplary Sensors and Effectors

[00300] It will be appreciated that the above-described growing system is provided for the purpose of illustration only, and that the above-described growing system comprises one possible configuration of a multitude of possible

configurations. Suitable variations in the connection between devices of the growing system will be understood to a person of skill in the art and are intended to fall within the scope of the present disclosure. For example, one or more

communication networks that are not shown, such as the Internet, may connect devices or communications networks in the growing system of the present disclosure.

Grower sensor device

[00301] Reference is next made to FIG. 2A and 13 which show a grower sensor device 110 in accordance with example embodiments of the present disclosure.

FIG. 2A is a simplified block diagram of the grower sensor device 110 in accordance with an example embodiment of the present disclosure. FIG. 13 is a picture of a grower sensor device in accordance with one example embodiment of the present disclosure. The grower sensor device 110 may be used to acquire sensor data to help determine the real-time growth and plant parameters of a plant or other phototrophic organism for the purposes determining the growth condition or state of the plant or other phototrophic organism based upon the acquired sensor data, and to identify a plant and/or plant state. The grower sensor device 110 may be handheld, or attached to a drone, UAV, or other robotic vehicle or system of a conveyance control subsystem 218 which may be remotely controlled by a user or robotically controlled, either autonomously or semi-autonomously.

[00302] The grower sensor device 110 comprises a plurality of plant sensors 240 that sense or detect one or more parameters of one or more plants 10. A grower sensor device 110 may be used to sense parameters of an individual plant 10 or a single grower sensor device 110 may be used to sense parameters for multiple plants 10, depending on the embodiment. For example, a grower sensor device 110 may be provided for each plant 10 in the grower facility 105 in some embodiments. The grower sensor devices 110 may be portable, moveable or fixed. For example, the grower sensor devices 110 may be configured to be mounted to a growing apparatus, possibly removable mounted. The grower sensor module 110 may have a housing adapted to be removably mounted to a frame of the growing apparatus. Alternatively, the grower sensor devices may be configured to be mounted to a crawler which traverses an overhead track or gantry scaffold of the grower facility 105, drone, or UAV of the conveyance control subsystem 218 which traverses the grower facility 105. Alternatively, the grower sensor devices 110 may be configured to be handheld by a user who may traverse the grower facility 105. The grower sensor devices 110 is an integrated sensor module that provides an Internet of Things (IoT) based sensor pack/module for an individual plant 10 or multiple plants 10, depending on the embodiment. Typically, a grower sensor device 110 is only provided for an individual plant 10 when the plant 10 is a high value plant 10, such as cannabis.

[00303] The grower sensor device 110 includes a controller comprising at least one processor 202 (such as a microprocessor) which controls the overall operation of the grower sensor device 110. The processor 202 is coupled to a plurality of components via a communication bus (not shown) which provides a communication path between the components and the processor 202.

[00304] The processor 202 is coupled to Random Access Memory (RAM) 222, Read Only Memory (ROM) 224, persistent (non-volatile) memory 226 such as flash memory, and a communications module 230 comprising one or more wireless transceivers 230 for exchanging radio frequency signals with a wireless communication devices and networks, one or more input devices and one or ore more output devices.

[00305] The grower sensor device 110 may comprise a touchscreen 232. A graphical user interface (GUI) of the grower sensor device 110 may be rendered and displayed on the touchscreen 232 by the processor 202. A user may interact with the GUI using the touchscreen 232 and optionally other input devices (e.g., buttons, dials) to display relevant information, such as sensor data, battery level, etc. The GUI may comprise a series of traversable content specific menus. The grower sensor device 110 may also comprise a speaker (or tone generator) 252 for generating audible notifications or alarms, one or more light emitting diodes (LEDs) 254 for generating visual notifications or alarms, and a data port 258 such as serial data port (e.g., Universal Serial Bus (USB) data port) of data input/output (I/O).

[00306] The communication module 230 may comprise any combination of a long-range wireless communication module, a short-range wireless communication module, or a wired communication module (e.g., Ethernet or the like). The long- range wireless communication module comprises one or more radio frequency (RF) transceivers for communicating with a radio access network (e.g., cellular network). The RF transceivers may communicate with any one of a plurality of fixed

transceiver base stations of a cellular network within its geographic coverage area. The long-range wireless communication module may also comprise a wireless local area network (WLAN) transceiver for communicating with a WLAN via a WLAN access point (AP). The WLAN may comprise a Wi-Fi wireless network which conforms to IEEE 802.1 lx standards (sometimes referred to as Wi-Fi®) or other communication protocol. The short-range wireless communication module enables wireless communication between the grower sensor device 110 and other

proximate systems or devices such a personal wireless communication device (e.g., smartphone or tablet). The short-range communication module may comprise devices, associated circuits and components for providing various types of short- range wireless communication such as Bluetooth™, RFID (radio frequency

identification), near field communication (NFC), IEEE 802.15.3a (also referred to as UltraWideband (UWB)), Z-Wave, ZigBee, ANT/ANT+ or infrared (e.g., Infrared Data Association (IrDA) communication).

[00307] Operating system software 282 executed by the processor 202 is stored in the persistent memory 226 but may be stored in other types of memory devices, such as ROM 224 or similar storage element. A number of applications 282 executed by the processor 202 are also stored in the persistent memory 226. The applications 282 include a Web browser 284, a plant ID application 286 for identifying a plant and/or a plant state, and a plant management application 288 for inputting and reporting data to the AI controller 150 by a user such as a master grower and/or querying and retrieving information about a plant. Other applications such as mapping, navigation, media player, telephone and messaging applications, etc. are also stored in the memory 226. The plant ID application 286 or plant management application 288, when executed by the processor 202, allows the grower sensor device 120 to communicate with the AI controller 150. Substantially the same functionality as the plant ID application 286 and/or plant management application 288 may be obtained by using the Web browser 284 to access a website of the application server 160 in some embodiments.

[00308] The plant ID application 286 and plant management application 288 are configured to allow the grower sensor device 110 to securely and wirelessly communicate with the AI controller 150. The applications 286, 288 may provide the AI controller 150 with a device ID and/or a plant ID in communications with the AI controller 150 to associate the data with the same grower sensor device 110, growing apparatus 300 or plant 10. The information exchanged with the AI controller 150 may comprise plant information, environmental information, and operating information.

[00309] The plant information may comprise any one or a combination of a lot number, a customer number, an order/transaction number, a plant species, a plant type (e.g., genus, species, strain, variety, etc.), family/origin information, a mother plant from which a cutting from the plant was grown was taken, terpene profile, one or more amounts (e.g., wt.%) of cannabinoids (such as tetrahydrocannabinol (THC) and cannabidiol (CBD)), one or more ratios of cannabinoids (such as THC to CBD (THC:CBD)), cannabinoid profile, combined terpene and cannabinoid profile, or one or more plant measurements such as stem thickness, canopy thickness or size. The amounts of cannabinoids, ratios of cannabinoids and plant measurements are determined by an inspection/analysis. The dates of the inspection/analysis may be included in the plant information

[00310] The plant information may be derived directly from plant sensors 132 or may be input by an inspector such as a master grower (e.g., such as plant height, stem diameter, qualitative assessments of the plant condition, including color, and any other observational data) via a user interface of the personal wireless communication device 130 or AI controller 150. Qualitative assessments may be based on a numeric scale that attempts to quantify qualitative

assessments, e.g. a numeric scale ranging from "1" to "10" in which "1" is extremely bad and "10" is extremely good. Alternatively, quality labels such as "good" or bad" may be used. Sensed/measured data is typically time stamped, for example, with a Julian date.

[00311] The environmental information comprises environmental data sensed from the environmental sensors 134 associated with the respective device ID and/or plant ID.

[00312] The memory 226 also stores a variety of data 290. The data 290 may comprise sensor data sensed by sensors 240, user data 284 comprising user preferences, settings and optionally personal media files (e.g., music, videos, directions, etc.), a download cache comprising data downloaded via the wireless transceivers 230, and saved files. System software, software modules, specific device applications, or parts thereof, may be temporarily loaded into a volatile store, such as RAM 222, which is used for storing runtime data variables and other types of data or information. Communication signals received by the mobile device 200 may also be stored in RAM 222. Although specific functions are described for various types of memory, this is merely one example, and a different assignment of functions to types of memory may be used in other embodiments. [00313] The grower sensor device 110 may also include a battery 228 as a power source, such as one or more rechargeable batteries that may be charged, for example, through charging circuitry coupled to a battery interface such as the serial data port 258. The battery 228 provides electrical power to at least some of the components of the grower sensor device 110, and the battery interface 226 provides a mechanical and electrical connection for the battery 228. The battery interface 226 is coupled to a regulator (not shown) which provides power to the circuitry of the grower sensor device 110.

[00314] The plant sensors 240 comprise any combination of one or more gas sensors 242, one or more photo sensors such as one or more spectrometers 244 and/or one or more cameras 246, one or more particulate sensors 248, and one or more proximity sensors 250 for measuring a proximity of components of plants 10 to the grower sensor device 110. The grower sensor device 110 may also comprise any combination of a positioning sensor system such as a Global Navigation

Satellite System (GNSS), a e.g. Global Positioning System (GPS) sensor, or other location determining system (e.g., cellular triangulation), for example, for

determining a precise location within the grower facility 105, an accelerometer, or an ultrasonic sensor. The plant sensors 240 may also comprise any of the other plant sensors 132 or environmental sensors 134 described above.

[00315] The gas sensors 242 sense or detect gas emitted by the one or more plants 10. Each of the gas sensors 242 is configured to sense or detect one or more gases in the ambient air surrounding the one or more plants 10. The gas sensors 242, or a processor of the grower sensor device 110, may determine an amount of various gases in the ambient air surrounding the one or more plants 10 sensed or detected gases and may determine a gas profile of the air surrounding the one or more plants 10 based on the sensed or detected gases. The gas sensors 242 may comprise a portable gas chromatograph for sensing or measuring the gas content of the ambient air surrounding the one or more plants 10.

[00316] The particulate sensors 248 sense or detect particulates such as, but not limited to, molds, fungi, yeasts, spores and pollen. The particulate sensors 248 may be a dust sensor, as an optical dust sensor, an example of which is the compact optical dust sensor model GP2Y1010AU0F from Sharp Corporation (Japan). The particulate sensors 248 may be used to sense or detect harmful particulates so that affected plants 10 may be quarantined or isolated for treatment or destruction, as described below.

[00317] As described above, the grower sensor device 110 may be portable or moveable, allowing it to be moved periodically from one plant 10 to another or from one set of plants 10 to another, to collect a set of plant parameters and

environmental parameters for each plant 10 at a grower facility 105. The portability of the grower sensor device 110 may reduce operational costs by allowing fewer sensor devices. Additionally, the use of the same sensors in the grower sensor devices 110 may reduce calibration errors and data correlation errors.

[00318] The communications module 230 may include a short-range

communication module such as an RFID or NFC reader configured to read a unique smart tag 342 (FIGs. 3A and 3B) of each plant 10 or a scanner/camera configured to read a QR code 344 (FIGs. 3A and 3B) of each plant 10 to correlate the sensed data to a specific plant 10. The smart tag 342 or QR code 344 may be affixed to a growing apparatus 300 (FIGs. 3A and 3B), growing table, or the plant 10 itself. Alternatively, the specific plant identity may be confirmed or determined based on location information.

[00319] The grower sensor device 110 may be handheld or transported by a robotically controlled vehicular platform such as a drone, UAV, or other robotic vehicle or system of the conveyance control subsystem 218. A solar charging platform may be provided to allow the battery 228 of the grower sensor device 110 to recharge through solar photovoltaics (PV) panels or other means. The robotically controlled vehicular platform may be an autonomous platform requiring minimal human supervision.

[00320] The sensed data may be consolidated and used for purposes of informing embedded artificial intelligence, cloud-based or cloud-assisted artificial intelligence, other related systems, or human cultivators, to help guide growth decisions. The grower sensor device 110 may track individual plants 10 through means that may include, but are not limited to, smart tags, QR codes, bar codes, or other direct or remote means, and tracking will comprise correlation of the acquired sensor data to the tracked plant 10. Additionally, other data acquired by other sensors 132, 134, 136 or systems for the purposes of correlation to plant growth parameters and such correlation may be used to further inform users, embedded artificial intelligence systems, cloud-based or cloud-assisted artificial intelligence systems, other related systems, or human cultivators. The grower sensor device 110 may allow a rapid identification of a plant and/or determination of the state of a plant or phototrophic organism (e.g., health or state of development), which may be used to provide input to an integrated or external artificial intelligence system for the purpose of assisting in optimization of productivity, yield, or to selectively favor certain desired qualities or features of a given plant or phototrophic organism. Multi-sensor analytics and diagnostics may be applied to assess the real-time state of development of the target plant or phototrophic organism.

Consumer sensor device

[00321] Reference is next made to FIG. 2B which illustrates in simplified block diagram form a consumer sensor device 120 in accordance with an example embodiment of the present disclosure. The consumer sensor device 120 is similar to the grower sensor device 110 in many respects. The primary difference between the consumer sensor device 120 and the grower sensor device 110 is that the consumer sensor device 120 typically has a subset of the plant sensors 240 of the grower sensor device 110. However, the plant sensors 240 of the consumer sensor device 120 may comprise any of the other plant sensors 132 or environmental sensors 134 described above.

[00322] The plant sensors 240 of the consumer sensor device 120 may be configured to sense or detect one or more parameters of plant material such as cuttings, leaves, buds (or flowers), or the like rather than whole plants 10 as in the case of grower sensor device 120. In the shown embodiment, the plant sensors 240 comprise one or more gas sensors 241, one or more photo sensors such as one or more spectrometers 243 and/or one or more cameras 245, and one or more proximity sensors 249 but no particulate sensors. The gas sensors 241,

spectrometers 243, cameras 245 and proximity sensors 249 may be the same as the gas sensors 242, photo sensors 244, cameras 246 and proximity sensors 250 of the grower sensor devices 110 for easier data comparisons. A plant ID application 287 for identifying a plant and/or a plant state is provided by the consumer sensor device 120. However, the functionality, capabilities and GUI of the plant ID application 287 are typically different from the plant ID application 286 of the grower sensor device 110.

[00323] The consumer sensor device 120 may be used to identity a plant 10 and/or plant material and attempt to verify a plant identification provided by a seller of the plant 10 and/or plant material in a retail environment. The

identification may be on the sensed data acquired by the plant sensors 241 of the consumer sensor device 120 and/or a blockchain-based ID assigned by a

grower/supplier of the plant 10 and/or plant material. When both sensor data and blockchain data by the consumer sensor device 120, the consumer sensor device 120 provides two-factor identification and verification of the plant 10 and/or plant material, increasing the confidence and certainty of retail consumers.

AI controller

[00324] Reference is next made to FIG. 4 which illustrates the

components of the AI controller 150 of the growing system 100 of FIGs. 1A and IB in accordance with one example embodiment of the present

disclosure. The AI controller 150 in the shown embodiment is provided by a single computing device. In other embodiments, the AI controller 150 may be provided by more than one computing device. Various functions of the AI controller 150 may be distributed amongst the computing devices. The AI controller 150 may be used to monitor, control and adjust the growing

conditions of plants 10 in the grower facility 105. In some embodiments, the

AI controller 150 may be used to monitor, control and adjust the growing

conditions of each plant 10 independently, either periodically or continuously.

[00325] The AI controller 150 may communicate with grower sensor devices 110, sensors 132, 134, 136, and the environmental control system 210 of more than one grower facility 105, and to consumer sensor devices 120 located virtually anywhere. When the AI controller 150 acquires data from multiple grower facilities 105, acquired data may be associated with a facility ID as well as any other IDs. The AI controller 150 may be located remotely from the grower facilities 105. Each grower facility 105 to which the AI controller 150 is connected may be operated by the same or different entities. Each grower facility 105 to which the AI controller 150 is connected may grow one or more types of plants or other phototrophic organisms (e.g., different genus, species, strain, variety, etc.). Similarly, the grower facilities 105 to which the AI controller 150 is connected may grow the same or different types of plants or other phototrophic organisms. The AI controller 150 applies machine learning/artificial intelligence to the sensor data acquired by the sensors of each grower facility 105 to which it is connected to optimize plant growth in accordance with configurable performance criteria which may consider a combination of plant parameters, environmental parameters, and operating parameters such as costs, as described below. The performance criteria may be applied to multiple grower facilities 105, a single grower facility or a part thereof (for example, based on the type of plant, differing consumer demands, etc.). The AI controller 150 may therefore learn from sensor data acquired from multiple grower facilities 105.

[00326] In the shown embodiment, the AI controller 150 comprises at least one processor 402 (such as a microprocessor) which controls the overall operation of the AI controller 150. The processor 402 is coupled to a plurality of components via a communication bus (not shown) which provides a communication path between the components and the processor 402. The processor 402 is coupled to RAM 422, ROM 424, persistent (non-volatile) memory 426 such as flash memory, and a communication module 428. The AI controller 105 may also comprise, or be connected to, input devices 434 such as a keyboard, mouse, touchscreen or like, a display 436, a microphone 440 and a speaker 442, one or more data ports 444 such as serial data ports for data I/O (e.g., USB data ports), and a power supply 450.

[00327] The communication module 428 provides wired and/or wireless communication capabilities that may be used for communication with the sensors 132, 134, 136, grower sensor devices 110, consumer sensor devices 120, personal wireless communication device 130, application servers 160, environmental control system 210, and third party servers 235, among other possible devices.

[00328] As noted above, the AI controller 150 comprises, or is coupled to, a plurality of databases 205 such as a sensor database, plant database, tracking database, control database, and analytics database. The databases 205 store a variety of data relating to the plants 10 including, but not limited to, sensor data with respect to a plurality of growth cycles, utility consumption data relating to the operation of the growing system 100, and cost data relating to the operation of the growing system 100. The sensor data may be associated with a device ID, a plant ID and/or a crop ID, and a time stamp (e.g., date and time). The utility

consumption data and cost data are facility-based and are not associated with a particular device (e.g., grower sensor device 110) or plant 10 and so may be associated with a crop ID and one or more key dates rather than a device ID or plant ID in some embodiments. The control database stores information about control data and instructions provided to the environmental control system 210.

The control data and instructions may also be associated with a device ID, a plant ID and/or a crop ID, and a time stamp.

[00329] As noted above, a blockchain or similar distributed ledger may be used to record custody, ownership and/or location of plants 10, plant material (e.g., cuttings, leaves, buds, etc.) and/or growing apparatuses 300. The blockchain may be maintained by nodes of a blockchain network. A node is a processing unit and may be a computer of a grower or retailer, a personal wireless communication device 130 of a consumer, the AI controller 150, grower sensor module 110, consumer sensor module 120, wireless transceiver 330, smart label 340 or smart tag 342 among other possibilities. Each node maintaining the blockchain having been authorized and authenticated before being added as a node to the blockchain network.

[00330] The memory 426 may store operating system software 452, a GUI module 454 for user interaction, a number of applications 456 including a machine learning/artificial intelligence module 208, other applications 464, and data 470. The AI module 208 may be, or comprise, for example, a genetic algorithm (GA) controller 460 and/or generative adversarial network (GAN) 462. Although examples of machine learning/artificial intelligence modules such as a genetic algorithm controller 460 that employs a genetic algorithm have been described, in other embodiments a machine learning/artificial intelligence based controller that applies a different heuristic algorithm or other machine learning/artificial

intelligence approach may be used.

Growing Apparatus

[00331] A growing apparatus may be used to grow one or more plants 10. FIG. 3A and 3B illustrate a growing apparatus 300 in accordance with one embodiment of the present disclosure. FIG. 3A is a block diagram of the growing apparatus 300. FIG. 3B is a cross-sectional view of the growing apparatus 300.

[00332] The plants 10 grown in the grower facility 105 are optionally grown in a growing apparatus such as the growing apparatus 300. Each growing apparatus 300 is used to grow one or more plants 10 in a growth medium 20 such as soil. Various types of growth media are contemplated as appropriate for the application, including soil, mineral-based growth media, polymer-based growth media, organic plant materials, semi-solid agars, nutrient solutions, and combinations thereof. The number of plants 10 grown in a growing apparatus 300 may depend on the size of the growing apparatus 300, the size and/or type of the plants 10, among other factors. Typically, a grower sensor device 110 is only provided for an individual plant 10 when the plant 10 is a high value plant 10, such as cannabis. In some embodiments, the growing system 100 may comprise a plurality of growing apparatuses 300 and the AI controller 150 may be used to individually control the growing apparatuses 300. [00333] The growing apparatus 300 comprises a plurality of plant sensors 132, a plurality of environmental sensors 134 and a plurality of effectors 205. The sensors 132, 134 and optionally effectors 205 are connected to a communications module, such as a wireless transceiver 330, that allows communication between the sensors 132, 134 and optionally effectors 205 and the AI controller 150. The sensors 132, 134 and optionally effectors 205 may connect to the AI controller 150 via wireless connection of a WLAN (e.g., Wi-Fi network) which may be used to communicate with the AI controller 150, for example, via the Internet. The wireless transceiver 330 may be encoded with a unique device identifier (ID) that may be used to uniquely identify a growing apparatus 300. The device ID may be a MAC (media access control) address or other unique ID. The device ID may be correlated to a plant ID. The AI controller 150 may be used to individually control effectors 205 of each growing apparatus 300 in the grower facility 105. The sensors 132, 134 and optionally effectors 205 may incorporate a wireless communication module for wireless communication with the wireless transceiver 330, for example via a short- range communication protocol such as Bluetooth®, or may be connected to the wireless transceiver 330 via wired connection. Alternatively, rather than a wireless transceiver 330, the sensors 132, 134 and optionally effectors 205 may connect to the AI controller 150 via wired connection of a local area network (LAN) which may be used to communicate with the AI controller 150, for example, via the Internet.

[00334] The growing apparatus 300 comprises a housing that comprises a frame 312. The frame 312 comprises at least one horizontal member 314 and at least one vertical member 316. In the shown embodiment, the frame 312 is in the form of spike design. In other embodiments, the frame 312 may have a cage design. Although not shown, the growing apparatus 300 may comprise an enclosure (not shown) that partially or completely isolates the one or more plants 10 being grown therein from one or more growing conditions. For example, the growing apparatus 300 may comprise a shield, hood or cover that isolates the one or more plants 10 being grown therein, for example, from ambient light. For another example, the air within the enclosure may be sealed from the ambient air of the facility in which the growing apparatus 300 is located. By totally or partially isolating the growing apparatus 300 and the plant 10, one or more growing conditions within the growing apparatus 300 may be more fully controlled.

[00335] The frame 312 carries sensors, such as plant sensors 132 and environmental sensors, and effectors 205 of various types, depending on the embodiment. The sensors 132, 134 and effectors 205 may be partially enclosed with the frame 312, such as within the frame members 314, 316, or mounted thereto, depending on the embodiment. The plant sensors 132 may be positioned on the horizontal member 314 so as to be above the plants 10 to monitor the condition and/or size of the canopy, the condition and/or size of floral buds, along the vertical member 316 to monitor the condition and/or size of the plant 10 below the canopy (e.g., the stem), and/or within the growth medium 20 to monitor the condition of the growth medium 20 and/or the root system of the plant 10. The effectors 205 may be positioned similarly to the sensors 132, 134 as required for a given application.

[00336] The frame 312 may also support one or more plants 10 being grown in the growing apparatus 300. The sensors 132, 134, effectors 205 and the wireless transceiver 330 are mounted or otherwise integrated within the frame 312. The horizontal member 314 of the frame 312 carries the wireless transceiver 330 in the shown embodiment. Alternatively, the sensors 132, 134, effectors 205 and wireless transceiver 330 may be carried by separate housings rather than being integrated within the frame 312 of the grown apparatus 300.

[00337] The effectors 205 of the growing apparatus 300 comprises one or more LED modules 326 (only one being shown), each coupled to the lighting control subsystem 212, that are carried by the horizontal member 314 of the frame 312 of the growing apparatus 300. The LED modules 326 may be carried by the vertical members 316 instead of, or in addition to, the horizontal member 314 in other embodiments. When a number of LED modules 326 are provided for a given growing apparatus 300, the LED modules 326 may be arranged along the length of the horizontal member 314 to provide light of a defined spectrum and intensity to the plant 10 below. A single or multiple types of LED module may be used in a given growing apparatus 300, depending on the embodiment. Different types of LED modules may be used in different growing apparatuses 300 during training of the AI controller 150, or if different plants 10 are grown in the grower facility 105. The LED module 326 may comprise a full or near-full natural light spectrum LED module, depending on the type of plant 10 being grown. In other embodiments, the LED modules 326 may comprise a blue LED emitting a blue light spectrum and a red LED emitting a red light spectrum. Dedicated blue and red LED modules 326 may be provided to control exposure of the plant 10 to blue and red wavelengths, which may result in improve growth or plant characteristics, depending on the type of plant 10 being grown. The LED modules 326 may be flashed to save power. In other embodiments, the LED modules 326 may comprise a UV module.

[00338] The vertical member 316 comprises an upper portion 318 and a lower portion 320. The upper portion 318 carries one or more gas outlets 322 through which oxygen, carbon dioxide, air and/or other gases are delivered to one or more plants 10 via the HVAC control subsystem 214 or dedicated gas supply subsystem. For example, gas outlets 322 may be used to provide a constant flow of gases to the one or more plants 10 in the growing apparatus 300 at a set flow rate. These gases may be mixed by the HVAC control subsystem 214 or dedicated gas supply subsystem to a specific concentration, for example a specific concentration of C0 ₂ and/or 0 ₂ , prior to dispensing the gases via the gas outlets 322. The lower portion 320 carries one or more liquid outlets 324 through which water, nutrients, pH adjustment agents and other nutrient or growth medium conditioners are delivered to the growth medium 20 of the plant 10.

[00339] The growing apparatus 300 may be modularly constructed, for example, for easier movement between operational areas of the grower facility 105. For example, the grower facility may have a number of operational areas in which activates realign to the development stage of the plant 10 may be performed, such as seeding (also known as planting or potting), growing, flowering/budding and harvesting. The frame 112 of the growing apparatus 300 may be modularly constructed to be moved between the operational areas of the facility, placed on a work table, and optionally stored or mounted in a receptacle of a racking system, which may be configured for vertical farming which modules are arranged in an array having horizontally and vertically located (e.g., stacked) receptacles each for receiving a growing apparatus 300. The racking system may, for example, be configured as a rectilinear array of rows and columns of receptacles. The frame module may be adapted for use with the conveyance control subsystem 218 and/or vertical lift control subsystem 220 of the environmental control system 210.

[00340] The growing apparatus 300 may comprise a smart tag 342, such as RFID tag, NFC tag or other short-range wireless communication tag. The smart tag 342 may be embedded in a smart label 340, sticker or other visual marker affixed to the growing apparatus 300. A QR code 344 may be provided by the smart label 340 in which the smart tag 342 is embedded, or a separate label, sticker or other visual marker. The use of both the smart tag 342 and the QR code 344 affixed to a growing apparatus 300 provides increased flexibility in tracking the growing apparatuses 300 and plants throughout the grower facility 105. Alternatively, only one of the smart tag 342 or QR code 344 may be used. The smart tag 342 and QR code 344 may encode the same or different data. The smart tag 342 and/or QR code 344 may encode the device ID and/or plant ID and optionally other

information. The data encoded on the smart tag 342 and/or QR code 344 is typically data that is fixed and does not vary with the lifecycle of the plants 10 (e.g., growth or stage) such as the device ID and/or plant ID. Variable data relating to the plants 10, the environment or operating parameters are typically stored in a sensor database in association with the device ID and/or plant ID.

[00341] A personal wireless communication device 130 (FIGs. 1A and IB) such as a smartphone having a smart tag reader suitable for the smart tags 342 and/or a QR code reader such as a camera and QR reader software module may be used to read the smart tags 342 and/or QR code 344. The smart tag 342 and/or QR code 344 may be used by the personal wireless communication device 130 to read encoded data, such as NFC and/or the QR encoded data from the smart tag 342 and/or QR code 344. A processor of the personal wireless communication device 130 then decodes and parses the encoded data to extract a device ID and/or plant ID from the encoded data retried by the personal wireless communication device. The device ID and/or plant ID may be used by the personal wireless communication device to exchange data with the AI controller 150 about a particular growing apparatus 300 or plants 10 contained therein. The personal wireless communication device 130 may be provided with the plant management application for interfacing and communicate with the AI controller 150.

[00342] In other embodiments, a grower sensor device 110 may be used with a growing apparatus 300. The grower sensor device 110 may be affixed to a growing apparatus 300, at least temporarily. This allows the sensors 132, 134 to be omitted from the growing apparatus 300 or reduced in number and/or type. This allows the grower sensor device 110 to communicate sensor data to the sensors 132, 134, potentially obviating the need for a wireless transceiver 330 or wired connection between the sensors 132, 134 and the sensors 132, 134. This may also obviate the need for a personal wireless communication device 130 to connect to the AI controller 150.

Identification of a plant and/or a plant state

[00343] The gas sensors 242 or a computing device such as a grower sensor device 110, a consumer sensor device 120, a personal wireless communication device 130 coupled to a consumer sensor device 120 or the AI controller 150 may determine an amount of various gases in the ambient air surrounding the one or more plants 10 or plant material that is sensed or detected gases, as described above. A gas profile of the air surrounding the one or more plants 10 or plant material based on the sensed or detected gases may also be determined. Each of the gas sensors 242 is configured to sense or detect one or more gases in the ambient air surrounding the one or more plants 10. The gas sensors that are provided by the host device (e.g., grower sensor device 110, consumer sensor device 120, growing apparatus 300, etc.) may vary depending on the type of plant being grown or type of plant material, the desired accuracy, and/or cost

constraints.

[00344] The gas sensors 242 are configured to be preferentially sensitive to one or more gases. However, the gas sensors 242 are also responsive to other gases to a lesser degree. Typically, the gas sensors 242 output a voltage that corresponds to the sensed/detected one or more gases. The gas sensors 242 may be calibrated to the one or more gases to which the gas sensors 242 are

preferentially sensitive so that the output voltage may be used to determine an amount or percentage of the respective gase(s) in the air. The output of the gas sensors 242 may be used to two ways. In a first mode, the output of the gas sensors 242 may be used to independently determine an amount of the one or more primary gases which the individual gas sensors 242 are configured or intended to sense or detect. In a second mode, the output of the gas sensors 242 may be used in combination or conjunction to determine an amount of secondary gases which the gas sensors 242 are not configured or intended to sense or detect. For example, the output of the gas sensors 242 may be used to detect and measure the amount of volatile compounds and/or complex hydrocarbons such as, but not limited to, volatile organic compounds, aromatic compounds, terpenes and/or cannabinoids. An example of the gas sensors 242 that may be used is provided below:

Table 1 : Gas Sensor Sensitivities

[00345] Examples of suitable gas sensors are those made by Waveshare International Limited (China) and SparkFun Electronics, Inc. (United States of America). A different set of gas sensors 242 may be used in other examples.

[00346] The output of the gas sensors 242 may be used to determine a gas profile of the air surrounding one or more plants 10 or plant material based on the sensed or detected gases. The gas profile acts as a fingerprint or signature of plant emissions that may be used to identify plants or plant material and/or plant states. The gas sensors 242 enable the gas profile to be measured and tracked. The gas profile may comprise a volatile compound profile of chemicals that have a high vapor pressure at ordinary room temperature (such as volatile organic carbons (VOCs)) or an aromatic profile of aromatic compounds. Within the present disclosure, the term aromatic compound is not limited to compounds based on one or more planar rings and instead means any chemical compound that emits an aroma (e.g., smell, odor fragrance, scent, perfume, whiff, etc.). When plant 10 is cannabis, the gas profile may be a terpene profile based a composition of cannabis terpenes in the air surrounding the plant 10. Alternatively, the gas profile (e.g., a volatile compound profile or aromatic profile) may be based on cannabinoids, cannabis flavonoids, or any combination of cannabinoids, cannabis terpenes and cannabis flavonoids. Thus, the gas profile may comprise any combination of a cannabinoid profile, a terpene profile and a flavonoid profile.

[00347] In some examples, the terpene profile may define a specific amount, range or relative abundance of various cannabis terpenes including, but not limited to, any combination of pinene (typically a-pinene and/or b-pinene), myrcene, limonene, humulene, linalool, caryophyllene (typically b-caryophyllene),

terpinolene, ocimene, camphene, terpineol, phellandrene, careen (typically Delta 3 carene), humulene, pulegone, sabinene, a-bisabolol (also known as levomenol and bisabolol), eucalyptol, trans-nerolido, borneol, valencene, geraniol or other desired cannabis terpene. In another example, terpene profile specifies a composition of a plurality of terpenes selected from the group consisting of any combination of pinene, myrcene, limonene, humulene, linalool, caryophyllene, or terpinolene.

[00348] For each of a number of cannabis varieties, an amount of the cannabis terpenes in the air surrounding the plant 10 may be determined. Table 2 provides an example terpene composition mapping of the terpenes pinene, myrcene, limonene, humulene, linalool, caryophyllene, and terpinolene, denoted T1...T7, respectively for seven cannabis strains, denoted VI to V7, with the particular composition of the terpenes for each strain denoted C, , where / is the terpene and j is the cannabis strain.

Table 2: Terpene Profiles for Cannabis Strains

[00349] For each of a number of cannabis strains, a sensor response to the emissions of the cannabis strain may be determined for each of the gas sensors 242. Table 3 provides an example response of the gas sensors, denoted A...H for seven cannabis strains, denoted VI to V7, with the particular sensor response for each cannabis strain denoted S, _j , where / is the terpene and j is the cannabis strain.

Table 3: Sensor Response for Cannabis Strains

[00350] In some examples, a cannabinoid profile may specify a composition of a plurality of terpenes selected from the group consisting of any combination of tetrahydrocannabinol (THC), cannabidiol (CBD), cannabinol (CBN), tetrahydrocannabinolic acid (THCA), CBDA (cannabidiolic acid), CBG (cannabigerol), cannabichromene (CBC), cannabicyclol (CBL), cannabivarin (CBV),

tetrahydrocannabivarin (THCV), CBDV (cannabidivarin), cannabichromevarin

(CBCV), cannabigerovarin (CBGV), cannabigerol monomethyl ether (CBGM), cannabielsoin (CBE), or cannabicitran (CBT).

[00351] In some examples, a cannabis flavonoid profile may specify a composition of a plurality of terpenes selected from the group consisting of any combination of anthocyanidins, flavan-3-ols, flavonols, flavones, flavanones, or isoflavones. In other examples, cannabis flavonoid profile may specify a

composition of a plurality of terpenes selected from the group consisting of any combination of cannaflavin A, cannaflavin B, cannaflavin C, b-sitosterol, vitexin, isovitexin, apigenin, kaempferol, quercetin, luteolin, or orientin.

[00352] The gas profile is compared to a plurality of reference gas profiles, and in response to the gas profile being within a tolerance threshold of a reference gas profile, a matching gas profile and the corresponding plant and/or plant state is determined or identified. A plant state may be a condition of plant health and/or stage of development (or age). An example of a stage of development is flowering or budding. It will be appreciated the gas profile varies depending on the type of plant and the plant state. Examples of health include a disease state, a nutritional concentration or state, a metabolite concentration, among others.

[00353] The gas profile may be based on raw data, derived data or possibly visual representations thereof. It will be appreciated that some types of analyses are more effective and/or more efficient when performed upon images or other visual representations of source data rather than the data itself. For example, a comparison of cannabinoid profiles, terpene profiles, flavonoid profile or a

combination thereof may be performed based on visual representations generated (or encoded) based on the sensed data and/or derived data.

[00354] FIG. 8A and 8B are graphs illustrating the response of the gas sensors of Table 1 when exposed to the emissions of two terpenes: terpinolene and limonene. In FIG. 8A and 8B the output of the gas sensors is shown as a voltage, however, the output of the gas sensor may be calibrated to PPM or other measure of concentration or amount. As illustrated in FIG. 8A, three tests and the average thereof demonstrate a high degree of repeatability for terpinolene. As illustrated in FIG. 8B, two tests and the average thereof demonstrate a high degree of repeatability for limonene.

[00355] FIG. 9 is a graph illustrating the response of gas sensors similar to those of Table 1 when exposed to five different strains of cannabis, namely:

Blackberry Kush (BK), Lemon Thai Kush (LTK), Girl Scout Cookie (GSC), Northern Lights (NL) and Original Gangster Kush (OGK). In FIG. 9 the output of the gas sensors is shown as a voltage, however, the output of the gas sensor may be calibrated to PPM or other measure of concentration or amount. As illustrated in FIG. 9, each of the different strains of cannabis has a different senor response based on the corresponding gas profile of respective strain of cannabis that allows different strains of cannabis to be differentiated based on the output of the plurality of gas sensors.

[00356] FIG. 10 is an example graph illustrating a terpene profile of different strains of cannabis. As shown in FIG. 10, different strains of cannabis can be differentiated by a respective terpene profile. In the shown embodiment, each terpene profile is based the amount or relative abundance of a-pinene, myrcene, limonene, humulene, linalool, b-caryophyllene, terpinolene, and ocimene.

[00357] Each reference gas profile and/or cannabis strain may be mapped to an effects profile that may specify any combination of psychological effects, physiological effects, therapeutic effects and/or side effects. The therapeutic effects may specify medical conditions treated. Thus, for a consumer using the consumer sensor device 120, in response to determining a matching gas profile and/or cannabis strain corresponding to the sensed or detected gases, a GUI may be displayed identifying the identified gas profile and/or cannabis strain and any combination of psychological effects, physiological effects, therapeutic effects and/or side effects associated with the identified gas profile and/or cannabis strain. FIG. 14 is a visualisation of a mapping of the gas profile to effects. In the shown example, the gas profile is a terpene profile that comprises 8 different terpenes but the terpene profile may be based on any number or combination of terpenes, cannabinoids and/or flavonoids.

[00358] For example, the psychological effects may be provided via a

qualitative or quantitative measure in terms of any combination of relaxation, happiness, euphoria, upliftedness and/or sleepiness associated with the identified gas profile and/or cannabis strain, the therapeutic effects may be provided via a qualitative or quantitative measure in terms of any combination of stress, pain, depression, insomnia, lack of appetite, associated with the identified terpene profile and/or cannabis strain, and the side effects may be provided via a qualitative or quantitative measure in terms of any combination of dry mouth, dry eyes, dizziness, paranoia, or anxiety associated with the identified terpene profile and/or cannabis strain.

[00359] For another example, medical conditions treated may be categorized by the following categories: (1) pain/sleep; (2) gastrointestinal; (3)

mood/behaviour; (4) neurological; and (5) other. Examples of medical conditions that may be treated in the pain/sleep category include inflammation, arthritis, pain, insomnia, fibromyalgia, spinal injury, phantom limb, migraine/headache, cramps and sleep apnea. Examples of medical conditions that may be treated in the gastrointestinal category include appetite loss, anorexia, cachexia, gastrointestinal disorders, nausea, diabetes, and Crohn's disease. Examples of medical conditions that may be treated in the mood/behaviour category include anxiety, ADD/ADHD, stress, bipolarism, OCD, PTSD, and depression. Examples of medical conditions that may be treated in the neurological category include Tourette's syndrome, epilepsy, seizures, multiple sclerosis, Alzheimer's disease, Parkinson's disease, spasticity, osteoporosis, and ALS. Examples of medical conditions that may be treated in the other category include cancer, muscular dystrophy, HIV/AIDS, glaucoma,

hypertension, fatigue and asthma.

[00360] Referring now to FIG. 11A, a method 1100 of identifying a plant and/or a plant state in accordance with one example embodiment of the present disclosure will be described. The method 1100 may be performed by a host device such as a grower sensor device 110, a consumer sensor device 120, a personal wireless communication device 130 coupled to a consumer sensor device 120 or the AI controller 150. When performed by the grower sensor device 110 or consumer sensor device 120, the method 1100 may be encoded by the plant ID application. The host device may have a setting whether a plant 10 or plant material is being analysed and identified by the method 1100 and optionally possibly a type of plant 10 or plant material being analysed and identified by the method 1100. For example, if the plant species (e.g., cannabis) is specified, the method maybe used to identify subspecies (e.g., strains). When a plant 10 is being analysed, the host device may have a setting whether the plant, plant state, or both are being analysed and identified by the method 1100. The settings may be stored by the plant ID application. The settings may be configurable by a user or fixed.

[00361] At operation 1102, the gas sensors 242 sense a plurality of gases in the ambient air surrounding plant 10 or plant material.

[00362] At operation 1104, the gas sensors 242 or a processor of a host device determine a gas profile based on the sensed gases.

[00363] At operation 1106, the processor of the host device identifies a plant and/or plant state corresponding to the determined gas profile. When a plant 10 is being analysed and identified, one or both of a plant or plant state corresponding to the determined gas profile is determined based on the settings of the host device. When plant material is being analysed and identified, typically a plant

corresponding to the determined gas profile is determined based on the settings of the host device.

[00364] At operation 1108, the processor of the host device may optionally determine information about the plant and/or plant state such as the effects profile associated with the identified plant, plant material and/or plant state.

[00365] At operation 1110, the identified plant and/or plant state and optionally information is output. The outputting may comprise displaying the identified plant and/or plant state and optionally information such as the effects profile on a display of the host device and/or wirelessly transmitting the identified plant and/or plant state and optionally information to the AI controller 150.

[00366] Referring now to FIG. 11B, a method 1120 of identifying a plant and/or a plant state in accordance with one example embodiment of the present disclosure will be described.

[00367] At operation 1122, the photo sensors sense one or more light spectra of a plant 10 or plant material. The photo sensors may comprise one or more spectrometers and/or one or more cameras, such as those of the grower sensor device 110 or consumer sensor device.

[00368] At operation 1126, the processor of the host device identifies a plant and/or plant state corresponding to the one or more light spectra. When a plant 10 is being analysed and identified, one or both of a plant or plant state is determined based on the settings of the host device. When plant material is being analysed and identified, typically a plant is determined based on the settings of the host device.

[00369] At operation 1128, the processor of the host device may optionally determine information about the plant and/or plant state such as the effects profile associated with the identified plant, plant material and/or plant state.

[00370] At operation 1130, the identified plant and/or plant state and optionally information is output. The outputting may comprise displaying the identified plant and/or plant state and optionally information such as the effects profile on a display of the host device and/or wirelessly transmitting the identified plant and/or plant state and optionally information to the AI controller 150.

[00371] Referring now to FIG. 11C, a method 1140 of identifying a plant and/or a plant state in accordance with one example embodiment of the present disclosure will be described. The method 1140 combines or conjoins the methods 1100 and 1120 described above by using both gas sensors 242 and photo sensors.

[00372] At operation 1102, the gas sensors 242 sense a plurality of gases in the ambient air surrounding plant 10 or plant material.

[00373] At operation 1104, the gas sensors 242 or a processor of a host device determine a gas profile based on the sensed gases.

[00374] At operation 1122, the photo sensors sense one or more light spectra of a plant 10 or plant material. The photo sensors may comprise one or more spectrometers and/or one or more cameras, such as those of the grower sensor device 110 or consumer sensor device.

[00375] At operation 1146, the processor of the host device identifies a plant and/or plant state corresponding to the determined gas profile and the one or more light spectra. When a plant 10 is being analysed and identified, one or both of a plant or plant state is determined based on the settings of the host device. When plant material is being analysed and identified, typically a plant is determined based on the settings of the host device.

[00376] At operation 1158, the processor of the host device may optionally determine information about the plant and/or plant state such as the effects profile associated with the identified plant, plant material and/or plant state.

[00377] At operation 1110, the identified plant and/or plant state and optionally information is output. The outputting may comprise displaying the identified plant and/or plant state and optionally information such as the effects profile on a display of the host device and/or wirelessly transmitting the identified plant and/or plant state and optionally information to the AI controller 150.

Formulating an infused consumable product

[00378] Referring now to FIG. 15, a method 1500 of formulating an infused consumable product in accordance with one example embodiment of the present disclosure will be described. The method 1500 is performed at least in part by a processor of a computing device such as a computer. [00379] At operation 1502, a processor of the computing device receives a consumable product profile specifying an effects profile. The effects profile may specify any combination of psychological effects, physiological effects, therapeutic effects and/or side effects. The effects profile may specify any combination of one or more desired psychological effects, one or more undesired psychological effects, one or more desired physiological effects, one or more undesired physiological effects, one or more desired therapeutic effects, one or more undesired therapeutic effects, one or more medical conditions treated desired to be treated, one or more medical conditions treated undesired to be treated, one or more desired side effects or one or more undesired side effects. The effects profile may further specify an intensity of each specified psychological effect, physiological effect, therapeutic effect and side effect.

[00380] At operation 1504, the processor of the computing device determines an active ingredient profile specifying a plurality of active ingredients matching the consumable product profile. The active ingredient profile specifies a combination of one or more cannabinoids and one or more terpenes. The active ingredient profile may specify one or more cannabinoids, one or more terpenes, and a relative amount of each of the cannabinoids and terpenes. The active ingredient profile may specify a combination of one or more cannabinoids, one or more terpenes and one or more flavonoids. The active ingredient profile may specify one or more

cannabinoids, one or more terpenes, one or more flavonoids and a relative amount of each of the cannabinoids, terpenes and flavonoids.

[00381] The consumable product profile may further specify a consumable product type. Alternatively, at operation 1506 the processor of the computing device determines a consumable product type based on the active ingredient profile. The consumable product type may be selected from one of the group consisting of a food, a beverage or a capsule. The food type may be selected from the group consisting of baked goods, candy, oils and diary products. The baked goods food type may be selected from the group consisting of potato chips, nacho chips, crackers, cookies, brownies, cakes and cupcakes. The candy food type may be selected from the group consisting of gummy candies, hard candies, and chocolates. The diary product type may be selected from the group consisting of yogurt, cheese, butter and cream. The beverage type may be selected from the group consisting of water, soda or pop, tea, herbal tea, coffee, caffeinated energy drink, non-caffeinated energy drink, liquid meal replacement, beer, bhang lassi, bhang thandai, wine, liquor-based mixed beverage, or tincture.

[00382] At operation 1508, the processor of the computing device determines an amount of each active ingredient in the active ingredient profile based on the product type and an intensity of each specified psychological effect, physiological effect, therapeutic effect and side effect.

[00383] At operation 1510, processor of the computing device causes a food or beverage infused with the combination of active ingredients in the active ingredient profile in the relative amounts to be prepared. The preparation may be performed by a food and/or beverage system or machine coupled to the computing device, such as a smart food and/or beverage preparation system or machine with pre- loaded food and/or beverage ingredients. The preparation of the food or beverage may comprise preparing a composition of the active ingredients in the active ingredient profile and a carrier, and preparing a food or beverage infused with the composition.

Identifying plants for quarantine or isolation

[00384] Referring now to FIG. 12, a method 1200 of identifying a quarantine or isolation in accordance with one example embodiment of the present disclosure will be described. The method 1200 may be performed by a host device such as a grower sensor device 110, a consumer sensor device 120, a personal wireless communication device 130 coupled to a consumer sensor device 120 or the AI controller 150. When performed by the grower sensor device 110 or consumer sensor device 120, the method 1200 may be encoded by the plant ID application.

[00385] At operation 1204, particulate sensors sense or detect particulates in the ambient air surrounding a plant 10. [00386] At operation 1206, the processor of the host device determines one or more types and an amount or concentration of particulates the output by the particulate sensors.

[00387] At operation 1206, the processor of the host device determines whether the types and amount or concentration of the particulates in the ambient air surrounding the plant match criteria to quarantine or isolate the plant 10. In some examples, the processor of the host device determines whether to quarantine or isolate the plant 10 in accordance with the sensed data by comparing the types and amount or concentration of the particulates in the ambient air surrounding the plant to types of particulates predetermined to be harmful and a threshold amount or concentration of particulates for quarantine or isolation. The types of particulates predetermined to be harmful comprise any combination of molds, fungi, yeasts, spores or pollen.

[00388] At operation 1208, the processor of the host device determines to quarantine or isolate the plant 10 in response to a determination that the types of particulates in the ambient air include one or more types of particulates

predetermined to be harmful and the amount or concentration of the particulates predetermined to be harmful in the ambient air exceeds the threshold amount or concentration of particulates for quarantine or isolation.

[00389] At operation 1210, the processor of the host device generates a notification or alert of the determination to quarantine or isolate the plant 10.

Multivariable optimization of plant growth and growth of other phototrophic organisms

[00390] Referring now to FIG. 5, a method 500 of multivariable optimization of plant growth and growth of other phototrophic organisms in accordance with an example embodiment of the present disclosure will be described. The method 500 may be performed in real-time or near real-time in either continuously, on-demand, or at regularly programmed intervals. The method 500 is based on one or more configurable performance criteria which may consider a combination of plant parameters, environmental parameters, and operating parameters such as costs, as described below.

[00391] At operation 502, the sensors 132, 134 and optionally operational sensors 136 are used to sense one or more parameters of a plant being growing in a growing apparatus 300, one or more parameters of an environment of the plant 10, and optionally one or more operational parameter of the growing system 100 or facility. The sensor data collected by the sensors is sent to the controller 150 via the wireless transceiver 330. The sensor data comprise multiple different types of data from different types of sensors, depending on the embodiment. The sensor data may be contained in a data packet or message, with the sensor data from each of the respective sensor sensors contained individually in a respective field.

[00392] At operation 504, the controller 150 compares one or more

parameters based at least on part on the sensor data from each sensor to one or more performance criteria to determine whether the parameters (or sensor data) match the one or more performance criteria. The comparison may be based on parameters derived from the sensor data or other input data, for example, from a master grower or other computing device or system connected to the controller 150. Thus, the controller 150 may generate or derive one or more parameters as a preliminary step before determining whether the parameters match the one or more performance criteria. The generation or derivation may comprise performing calculations based on the sensed data and/or generating (or encoding) a visual representation based on dense data and/or derived data. For one example, the derived parameters may be a growth rate, growth parameter, plant state, or plant condition may be derived, for example, based on current and historical sensor data and considered as a parameter. For another example, information about amount of any one of cannabinoids measured in harvested plant material, cannabis terpenes measured in harvested plant material, cannabis flavonoids measured in harvested plant material, or a combination of thereof may be input and considered as a parameter. The information about amount of any one of cannabinoids measured in harvested plant material, cannabis terpenes measured in harvested plant material, cannabis flavonoids measured in harvested plant material may be defined by a cannabinoid profile, terpene profile, flavonoid profile, or combination thereof. For example, a comparison of cannabinoid profiles, terpene profiles, flavonoid profile or a combination thereof may be performed based on visual representations generated (or encoded) based on the sensed data and/or derived data.

[00393] The performance criteria may comprise one or more threshold values or ranges. The sensor data may be pre-processed before the comparison and determination operations, for example, to determine derivative information from the sensor data such as, but not limited to averages, means or other statistical values. The performance criteria may vary at least in part in dependence on the particular sensors being used. Exemplary, non-limiting performance criteria are described below.

[00394] The performance criteria may be defined by a grower, customer, regulator or other entity. The performance criteria may vary based on objectives of the grower, customer, regulator or other entity (e.g., yield quality, yield quantity, cost control, revenue etc.), the plant type (e.g., species, variety, strain, etc.) mother/family of the plant 10. The performance criteria and associated optimization problem is a multivariable problem in which plant parameters, environmental parameters, and operational parameters interact and cannot be easily deconvolved.

Performance criteria

[00395] The performance criteria may comprise a gas profile of the air in the environment surrounding the plant 10, such as a volatile compound profile or an aromatic profile, as described above.

[00396] The performance criteria may comprise a light profile in which the intensity, timing/frequency and wavelength of light is defined, for example, over a 24 hour duration in some embodiments. Ambient light in the environment of the plant 10 may be measured by one or more photo sensors. The ambient light may be adjusted by one or more LED modules 152 to provide supplemental light at an intensity, time/frequency and wavelength so that the ambient light measured by the one or more photo sensors matches the light profile. [00397] The performance criteria when the plant 10 is cannabis may comprise an amount, range or ratio of specific cannabinoids in some embodiments. For example, the performance criteria may define the amount, range or ratio of specific cannabinoids in harvested plant material, such as in the floral buds, including, but not limited to one or more of a weight % tetrahydrocannabinol (THC), a weight % cannabidiol (CBD) or a ratio of THC to CBD (THC: CBD).

[00398] The performance criteria may comprise an amount of harvested plant materials in some embodiments, which may be based on, for example, a plant height, plant weight, weight of harvested plant material, a number of harvested floral buds, or weight of harvested floral buds.

[00399] The performance criteria may comprise an audio profile. Ambient audio in the environment surrounding the plant 10 may be measured by one or more microphones or audio sensors. The ambient audio may be adjusted via speakers by reproducing sounds (e.g., white noise), tones or music so that the ambient audio measured by the one or more microphones or audio sensors matches the audio profile. The , which may be measured by microphones or audio sensors in some embodiments. The audio profile may be set or adjusted via speakers in the growing apparatus 300 which may be used to reproduce sounds (e.g., white noise), tones or music to match the audio profile.

[00400] The performance criteria may comprise a maturity or growth stage of the plant 10 in some embodiments, for example, as the plant 10 moves from germination, to seedling, to vegetative growth, to flowering, to fruit production, to senescence. The sensors 132, 134 may detect the current growth stage of the plant 10 and the control system 200 may instruct the effectors 205 to adjust the growing conditions accordingly to optimize the growing conditions for the current maturity or growth stage of the plant 10. In some applications, it may be desirable to encourage or discourage maturation of the plant 10 to shorten or prolong a particular stage of growth. For example, if seeds are desired, the effectors 205 may adopt a particular set of growing conditions to encourage rapid maturation of the plant 10 through to the vegetative stage, after which the growing conditions may be sequentially modified to encourage flowering, pollination, and seed-setting, respectively. For example, when the plant 10 is cannabis, floral budding or fruiting may be desired and encouraged. Likewise, the sensors 132, 134 may detect the onset of fruiting, and the effectors 205 may adjust the growing conditions

accordingly to encourage fruit development and ripening.

[00401] The performance criteria may comprise a height of the plant 10 in some embodiments. Heights below a threshold value may indicate stunting and/or stress whereas heights at or above the threshold value may indicate excessive vegetative growth. In such embodiments, it may be advantageous to encourage or discourage further growth by adjusting the growing conditions accordingly. For example, when the height of a plant 10 exceeds the threshold value, the effector 150 may reduce the level of fertilizers or other nutrients dispensed into the growth medium 20. Likewise, if the plant height is below the threshold value, fertilizer levels (or other growing conditions) may be increased to encourage further growth of the plant 10.

[00402] The performance criteria may comprise a condition of the plant 10 in some embodiments, such as the color of the leaves, leaf surface area, leaf temperature, stem thickness, root depth, root coloration, the presence of a fungal or insect infestation, or a combination thereof. In such embodiments, it may be advantageous for the effectors 205 to modify the growing conditions to respond to the condition of the plant 10. For example, yellowing of leaves and high leaf temperatures may indicate a need for further watering, whereas a fungal infestation may indicate a need for lower humidity. Likewise, reduced root depth or darkened root coloration may indicate a need for reduced watering.

[00403] The performance criteria may comprise a condition of the growth medium 20 in some embodiments, such as the nutrient content, pH, moisture level, or temperature of the soil. In such embodiments, it may be advantageous for the effectors 205 to modify the growing conditions to respond to the condition of the growth medium 20. For example, a pH sensor may detect acidic or basic soil conditions, which may be modified by the effector by dosing the soil with basic or acidic agents to return to a threshold pH value.

[00404] The example performance criteria described above may be considered alone or in combination. For example, measurements of plant height and leaf surface area may be combined with flowering or other visual cues to estimate the growth stage or maturity of the plant 10.

[00405] The performance criteria may comprise operational criteria in some embodiments. The operational criteria may be based costs, revenues or profits, for example, to minimize costs, optimize revenue or optimize profit. For example, the performance criteria may comprise a cost per unit measure (e.g., gram of solid product, millilitre of liquid product, etc.), revenue per unit measure or profit per unit measure. For example, the cost of electricity or other variable costs may be taken into account to balance quantity and/or quality with the cost of production.

[00406] At operation 506, in response to a determination that the sensor data does not match the one or more performance criteria, a notification may be generated by the controller 150. The notification provides a message or other indication that the controller 150 has determined that the sensor data does not match the one or more performance criteria. The message may specify the device ID (or plant ID), the performance criteria that was not met, the sensor data, date/time at which the sensor data was acquired, potential risks, and a

recommendation corrective action, if any. The generation of the notification may comprise displaying the notification on the display 336 of the controller 150, for example, in a high visibility GUI window, menu or box. For example, the notification may be provided in a top layer overlay that overlays other content on the display 336. The generation of the notification may be selective based on a particular performance criteria or type of performance criteria which the sensor data did not match. For example, performance criteria may be associated with an importance rating (e.g., low, medium or high), and a notification may only be generated when the particular performance criteria or type of performance criteria which the sensor data did not match has importance rating that meets or exceeds a notification threshold (e.g., high, possibly medium). The importance rating may be based on one or more factors such as a risk of plant failure/death. The notification may be send to one or more designated messaging addresses (such as a master grower, managers, officers, directors, etc. of the operating entity) in addition to, or instead of, being displayed on the display 336. For example, an email message or text message comprising the notification may be sent to the designated addresses. In other embodiments, the notification may be generated in batch when a threshold number of failures to meet performance criteria have been determined, with the notification including the notification information for all features as described above.

[00407] At operation 508, the controller 150 may determine one or more environmental changes to be implemented based on the difference between the sensor data and the one or more performance criteria, and one or more commands or instructions for one or more of the subsystems of the environmental control system 210.

[00408] For example, the sensor 132, 134 may detect entry of a plant 10 into a vegetative growth stage and in response the controller 150 determine to instruct the effectors 205, e.g. LED modules 152, to alter a lighting scheduling (timing frequency) from always-on (e.g., 24 hours of light) to periods of a partial light and dark (e.g., 10-16 of light with 14-8 hours without illumination). When the plant 10 is not in isolation from ambient light, the supplemental light produced by the LED modules 152 may be modified based on ambient light levels, which may vary throughout the year based on sunrise and sunset, cloud cover, etc. Similarly, the sensor 132, 134 may detect entry of a cannabis plant into a flowering stage and in response the controller 150 may instruct the effectors 205, in this case a UV light source, to increase the UV light output to increase the production of cannabinoids in the plant.

[00409] When the cost of electricity is low or a rebate is provided to consumer power, the controller 150 may determine whether the plants 10 may accept more light based on the condition of the plants 10 and the stage of development of the plans 10 to take advantage of the lower cost environment. Similar considerations may be made for other variable cost inputs such as water and nutrients. [00410] At operation 510, the controller 150 sends the one or more commands or instructions to the one or more respective subsystems of the environmental control system 210 (or possibly effectors 205) to modify the growing conditions of the plant 10. Operations then return to operation 502 until the method 500 is discounted (decision block 512), for example, because the growing apparatus 300 is taken out of service. The method 500 may be stopped for a particular growing apparatus 300, by removing the device ID (or a corresponding plant ID associated with/mapped to the device ID) from the list of device IDs (or plant IDs) being monitored by the controller 150.

[00411] Over time, the plant 10 will respond to the modified growing conditions which, while the method 500 is being performed, will be detected by the sensors 132, 134. Thus, the method 500 provides an integrated growth solution to improve yield quality and/or quantity through a continuous feedback loop of monitoring and adjustment.

Artificial intelligence and machine learning

[00412] The AI controller 150 may be pre-programmed or trained using machine learning, depending on the embodiment. In example embodiments, the AI module 208 may be, or comprise, for example, a genetic algorithm (GA) controller 460 and/or generative adversarial network (GAN) 462 (FIG. 4).

[00413] Reference is next made to FIG. 6 which shows the genetic algorithm controller 460 in accordance with the one example embodiment of the present disclosure. The genetic algorithm controller 460 is a machine learning/artificial intelligence based controller, and comprises a number of functional modules. The genetic algorithm controller 460 comprises a population generator 552, a fitness evaluator 554, a selector 556 and one or more sequence modifiers 558 which, in the some embodiments, comprises a crossover generator 560 and a mutation generator 562.

[00414] Referring now to FIG. 11, a method 1100 of multivariable optimization of plant growth in accordance with an example embodiment of the present disclosure will be described. The method 1100 is carried out by the genetic algorithm controller 460 of the controller 150.

[00415] At operation 1102, the population generator 512 generates a set of growing states is defined as an initial population. Each growing state defines a set of plant parameters that are measurable by one or a combination of plant growth sensors 132 and environmental parameters that are measurable by one or a combination of environmental sensors 134. The growing states may further define operational parameters that are determinable by the controller 150 from data obtained from the databases 205, supplemental data sources 255 and/or measured by the operational sensors 136.

[00416] Each growing state is encoded as a generic representation which may be stored as a bit string in some embodiments. Each plant parameter,

environmental parameters and operational parameter may be represented by a set of one or more octets. The bit string may have a fixed or variable length. When the bit string is a variable length, in each octet of the generic representation, a most significant bit (MSB) is used to indicate whether that octet is the last octet in the set of one or more octets for a given parameter. That is, the MSB is set to indicate whether another octet of the parameter follows. Different data structures may be used to store genetic information in other embodiments. For example, each generic representation may be stored as a vector of values, such as a vector of real numbers, in other embodiments.

[00417] At operation 1104, the fitness evaluator 514 determines a fitness of each of the growing states via a fitness function. The fitness function determines a fitness (performance) of each of the individual growing states in the set of growing states. The fitness function outputs, for each of the individual growing states, a fitness score that defines the fitness of each of the individual growing states. The probability that an individual growing state will be selected for reproduction is based on its fitness score.

[00418] At operation 1106, the selector 516 selects a plurality of individual growing states are selected for a subsequent generation. During the selection operation, individual growing states determined to be the fittest (highest performing) are selected from the set of all growing states. In some embodiments, for example, a pair of individual growing states is selected via a selection function based on the fitness scores. The selection function is adapted to select individual growing states having a high fitness. In some embodiments, the selection function may select the individual growing states having the highest fitness scores. In other embodiments, the selection function may select individual growing states having a fitness score above a threshold fitness score in accordance with one or more particular selection criteria, which may be based on one or more performance criteria, plant parameters, environmental parameters or operational parameters. In other embodiments, the selection function may select individual growing states having a fitness score above a threshold fitness score at random in accordance with a randomized selection algorithm.

[00419] At operation 1108, the crossover generator 560 generates a plurality of new growing states by performing a crossover of the selected individual growing states via a crossover (genetic) algorithm. The crossover algorithm stochastically generates each new growing state from the pair of selected growing states. The genetic representations of the pair of selected individual growing states are recombined with one or more different crossover operators. The new growing states represent offspring of the previous generation of growing states.

[00420] The crossover algorithm may be a single-point crossover, a two-point crossover, a k-point crossover, a uniform crossover or special crossover. In a single-point crossover, a single point is selected at random from the parent chromosomes and designated a crossover point. Bits to the right of the crossover point are exchanged with between the two parent chromosomes whereas bits to the left of the crossover point are not changed. The result of the single-point crossover is two offspring, each carrying some genetic information from both parents. In a two-point crossover, two crossover points are selected at random from the parent chromosomes. The bits in between the two crossover points are exchanged between the parent chromosomes. In a k-point crossover for any positive integer k, k crossover points are selected at random from the parent chromosomes. The bits in between the crossover points are exchanged between the parent chromosomes. In a uniform crossover, the bits of each offspring's genome is independently chosen at random from the two parents according to a given distribution. In contrast to k- point crossover, uniform crossover exchanges individual bits and not segments of the bit array, thereby avoiding any no bias for two bits that are close together in the array to be inherited together. In some embodiments, each bit may be chosen from either parent's chromosome with equal probability. Other probability ratios may be used in other embodiments such that offspring inherit more genetic information from one parent than the other parent.

[00421] Depending on the genetic representation, not all possible

chromosomes represent valid solutions and specialized crossover and mutation operators to avoid violating any constraints are employed. Crossover genetic algorithms that optimize the ordering of a given list of constraints but avoid generating invalid solutions include, but are not limited to, partially matched crossover (PMX), cycle crossover (CX), order crossover operator (0X1), order- based crossover operator (0X2), position-based crossover operator (POS), voting recombination crossover operator (VR), alternating-position crossover operator (AP), sequential constructive crossover operator (SCX), and edge recombination operator (ERO).

[00422] At operation 1110, the mutation generator 562 may generate one or more variations (e.g., mutations) in the plurality of new growing states (offspring) with a low random probability. This involves switching bits in the bit string of the affected growing states. Mutation occurs to maintain diversity within the population and prevent premature convergence.

[00423] At operation 1112, the genetic algorithm controller 460 determines whether the population has converged, whether the current generation has produced offspring which are significantly different from the previous generation. This may comprise comparing the fitness or chromosomes (genetic representation) of the new growing states (offspring) to the fitness or chromosomes (genetic representation) of the previous generation. When the difference is less than a threshold, the population has converged. When the difference exceeds or is equal to the threshold, the population has not converged. At operation 1114, an

optimized growing state is output in response to a determination that the

population has converged. Processes return to operation 1104 in response to a determination that the population has not converged.

Generative adversarial network fGAINH

[00424] Referring now to FIG. 16, a generative adversarial network (GAN)

1600 for the growing system of FIG. 1A and IB in accordance with one embodiment of the present disclosure will be described. The AI controller 150 or processing system may be used to implement the GAN 1600, either in whole or in part.

[00425] The GAN 1600 comprises a neural network based image generator ("generator") 1606, a neural network based discriminator ("discriminator") 1610, an image database 1608, and a loss calculator 1612. In some example

embodiments, the generator 1606 can be implemented by a convolutional neural network while the discriminator 1612 can be implemented by a de-convolutional neural network. Other types of neural networks or multilayer perceptrons (MLPs) can also be used in other example embodiments.

[00426] The generator 1606 operates a generator model receives as input a noise variable input 1604 and generates a random noisy image from an implicit probability distribution as output. The discriminator 1610 receives as input a generated image or a real image from the image database 1608. The discriminator 1610 operates a discriminator model, a classifier that, given the input of a generated image or a real image from the image database 1608, performs a determination as to whether the input corresponds to a generated image or real image, and outputs produces a scalar (a label) representing the determination.

[00427] The input and output of the discriminator 1610 are received as input to the loss (cost) calculator 1612 which terms a loss for one or both of the generator 1606 and discriminator 1610 which are backpropagated to the generator 1606 and discriminator 1610 respectively, thereby updating the generator model and/or discriminator model. The loss (cost) functions for training the generator model and discriminator model may vary and may be selected by the AI designer.

[00428] The generator model and discriminator model of the GAN 1600 are trained simultaneously using the generator and discriminator loss functions. The two models are represented generally by functions denoted G and D respectively. The function D is optimized (trained) to assign the correct labels to both training data and data produced by G whereas the function G is optimized (trained) to minimize correct assignments of D regarding data produced by G. The generator 1606 may be trained by backpropagating the error so as to maximize an error calculated by the loss calculator 1612 whereas the discriminator 1610 may be trained by backpropagating the error so as to minimize an error calculated by the loss calculator 1612.

[00429] After completion of a first machine learning/training in which the GAN 1600 is trained to generate a synthetic image from the image database 1608, the AI module 208 may undergo a second machine learning/training in which a variational autoencoder (not shown) is trained to generate (or encode) a synthetic image from sensor data using a training set comprising a set of sensor data paired with representative images or visual representation. After completion of the second machine learning/training, the AI module 208 is trained to: generate (or encode) at least some of the sensor data as a visual representation such as a synthetic image or graph. The visual representation may be used as a parameter for determining whether parameters based at least in part on the sensor data match the one or more performance criteria.

[00430] GANs are described, for example, by Ian J. Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio in Generative Adversarial Networks, University of Montreal, 10 Jun 2014. Variational autoencoder are described, for example, by Yunchen Pum Zhe Gan, Ricardo Henao, Xin Yuan, Chunyuan Li, Andrew Stevens and Lawrence Carin in Variational Autoencoder for Deep Learning of Images, Labels and Captions, Advances in Neural Information Processing Systems 29 (NIPS 2016). The content of both of these documents being incorporated herein by reference.

[00431] Although example embodiments are described herein in respect of plants, the devices, systems and methods described herein may also be applied to growing organisms that are not plants including phototrophic organisms such as algae.

General

[00432] The steps and/or operations in the flowcharts and drawings described herein are for purposes of example only. There may be many variations to these steps and/or operations without departing from the teachings of the present disclosure. For instance, the steps may be performed in a differing order, or steps may be added, deleted, or modified.

[00433] The coding of software for carrying out the above-described methods described is within the scope of a person of ordinary skill in the art having regard to the present disclosure. Machine-readable code executable by one or more

processors of one or more respective devices to perform the above-described method may be stored in a machine-readable medium such as the memory of the data manager. The terms "software" and "firmware" are interchangeable within the present disclosure and comprise any computer program stored in memory for execution by a processor, comprising Random Access Memory (RAM) memory,

Read Only Memory (ROM) memory, EPROM memory, electrically EPROM (EEPROM) memory, and non-volatile RAM (NVRAM) memory. The above memory types are examples only, and are thus not limiting as to the types of memory usable for storage of a computer program.

[00434] All values and sub-ranges within disclosed ranges are also disclosed. Also, although the systems, devices and processes disclosed and shown herein may comprise a specific plurality of elements, the systems, devices and assemblies may be modified to comprise additional or fewer of such elements. Although several example embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, substitutions, additions, or

modifications may be made to the elements illustrated in the drawings, and the example methods described herein may be modified by substituting, reordering, or adding steps to the disclosed methods.

[00435] Features from one or more of the above-described embodiments may be selected to create alternate embodiments comprised of a subcombination of features which may not be explicitly described above. In addition, features from one or more of the above-described embodiments may be selected and combined to create alternate embodiments comprised of a combination of features which may not be explicitly described above. Features suitable for such combinations and subcombinations would be readily apparent to persons skilled in the art upon review of the present application as a whole.

[00436] In addition, numerous specific details are set forth to provide a thorough understanding of the example embodiments described herein. It will, however, be understood by those of ordinary skill in the art that the example embodiments described herein may be practiced without these specific details.

Furthermore, well-known methods, procedures, and elements have not been described in detail so as not to obscure the example embodiments described herein. The subject matter described herein and in the recited claims intends to cover and embrace all suitable changes in technology.

[00437] Although the present disclosure is described at least in part in terms of methods, a person of ordinary skill in the art will understand that the present disclosure is also directed to the various elements for performing at least some of the aspects and features of the described methods, be it by way of hardware, software or a combination thereof. Accordingly, the technical solution of the present disclosure may be embodied in a non-volatile or non-transitory machine-readable medium (e.g., optical disk, flash memory, etc.) having stored thereon executable instructions tangibly stored thereon that enable a processing device to execute examples of the methods disclosed herein. [00438] The term "processor" may comprise any programmable system comprising systems using microprocessors/controllers or

nanoprocessors/controllers, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) reduced instruction set circuits (RISCs), logic circuits, and any other circuit or processor capable of executing the functions described herein. The term "database" may refer to either a body of data, a relational database management system (RDBMS), or to both. As used herein, a database may comprise any collection of data comprising hierarchical databases, relational databases, flat file databases, object-relational databases, object oriented databases, and any other structured collection of records or data that is stored in a computer system. The above examples are example only, and thus are not intended to limit in any way the definition and/or meaning of the terms "processor" or "database".

[00439] The present disclosure may be embodied in other specific forms without departing from the subject matter of the claims. The described example embodiments are to be considered in all respects as being only illustrative and not restrictive. The present disclosure intends to cover and embrace all suitable changes in technology. The scope of the present disclosure is, therefore, described by the appended claims rather than by the foregoing description. The scope of the claims should not be limited by the embodiments set forth in the examples, but should be given the broadest interpretation consistent with the description as a whole.