System and method for treatment or growing of cuttings

Abstract

Systems and methods are disclosed for determining environmental conditions, in particular lighting conditions, for treatment or growing of a cutting (21) from a mother plant (11). The system comprises a data processing system (1002) comprising a memory storing computer-readable instructions, at least one communication interface, and at least one processor. The at least one processor is configured to, in response to executing the computer-readable instructions, receive, via the at least one communication interface, information associated with a cutting (21), and to determine one or more second environmental conditions for treatment or growing of the cutting (21) or of a clone (291,2) obtained from the cutting (21), based on at least the information associated with the cutting (21). The information associated with the cutting (21) comprises at least one of: one or more first environmental conditions of a mother plant (11) of the cutting (21) prior to obtaining the cutting (21) from the mother plant (11); one or more characteristics of the mother plant (11); and one or more characteristics of a clipping process (20) used to obtain the cutting (21) from the mother plant (11) and / or used to handle the cutting (21) until the cutting (21) is planted.

Description

[0001] 2023PF80480

[0002] 1

[0003] SYSTEM AND METHOD FOR TREATMENT OR GROWING OF CUTTINGS

[0004] FIELD OF THE INVENTION

[0005] This disclosure relates to a system and method for determining an environmental condition for treatment or growing of a cutting from a mother plant. This disclosure further relates to a computer-implemented method for determining an environmental condition for treatment or growing of a cutting from a mother plant and to a computer program for performing such method and a computer-readable storage medium stored therein such computer program or a computer-readable signal medium embodying such computer program.

[0006] BACKGROUND OF THE INVENTION

[0007] Horticultural systems that adjust growing parameters of a crop to be grown based on the current status of the crop are known in the art.

[0008] For example, WO 2019 / 237200 Al describes a growing system comprising sensors for sensing parameters of a plant and / or of a plant’s environment, and a control system to control the plant’s environment based on sensor data received from the sensors, and, optionally, on plant information (such as species, variety, et cetera).

[0009] In many growing facilities, environmental conditions such as lighting intensity, temperature, humidity, et cetera, are shared between multiple plants. For a system as described above to function optimally, the plants that share the same environmental conditions should be maximally similar, so that the optimal environmental conditions are the same for all plants.

[0010] In light of the above, there is a need in the art for a system and method for irradiating a plurality of plants that increases the light use efficiency for treatment or growth of the plurality of plants.

[0011] SUMMARY OF THE INVENTION

[0012] To that end, a data processing system, an irradiation system and a computer program product for determining environmental conditions, in particular lighting conditions,2023PF80480

[0013] 2

[0014] for treatment or growing of a cutting from a mother plant is disclosed. The invention is defined by the claims.

[0015] In an aspect, the data processing system for determining an environmental condition for treatment or growing of a cutting from a mother plant comprises a memory storing computer-readable instructions, at least one communication interface, and at least one processor. The at least one processor is configured to, in response to executing the computer-readable instructions, receive, via the at least one communication interface, information associated with a cutting, and to determine one or more environmental conditions for treatment or growing of the cutting or of a clone obtained from the cutting, hereinafter referred to as the one or more second environmental conditions, based on at least the information associated with the cutting. The information associated with the cutting comprises at least one of: one or more first environmental conditions of a mother plant of the cutting prior to obtaining the cutting from the mother plant; one or more characteristics of the mother plant; and one or more characteristics of a clipping process used to obtain the cutting from the mother plant and / or used to handle the cutting until the cutting is planted.

[0016] For various plant genera, including Cannabis, the preferred propagation method is via cloning. One drawback of cloning is that the resulting clones are relatively heterogeneous, as the properties of the clone depend not only on the mother plant, but also on the environmental conditions of the mother plant (prior to obtaining the cutting) as a whole as well as the specific location the cutting was taken from, on the clipping process used to obtain the cutting from the mother plant, on the handling or processing of the cutting before the cutting is planted, and so forth. By taking at least some of this information into account, the environmental conditions for growing or treatment of the clones may be optimized to obtain clones with desired properties for further cultivation.

[0017] The information associated with the cuttings may also be used to create groupings of cuttings that, when exposed to similar environmental conditions, will result in plants with similar characteristics.

[0018] The information associated with the cutting may be received, as sensor data, from one or more sensors. This is in particular the case for the first environmental conditions of the mother plant of the cutting prior to the clipping and may also be the case for one or more characteristics of the mother plant, such as leave color and (estimates of) absolute or relative levels of certain chemicals in the mother plant. Other information associated with the cutting may be received as user input data, e.g., clipping process, cutting angle, wounding, location of the cutting on the mother plant, et cetera. One or more of the one or more2023PF80480

[0019] 3

[0020] characteristics of the mother plant may also be received via user input, such as, e.g., stem thickness, et cetera.

[0021] As used herein, a cutting refers to the plant part that has been obtained from the mother plant by a clipping process, and a clone refers to a cutting that has been planted and is in the process of developing a root system, new stems and new leaves. After clones have developed a root system, a new stem and new leaves and hence have become a new plant, they are referred to as plants.

[0022] In an embodiment, the at least one processor is further configured to determine and transmit, via the at least one communication interface, one or more control commands to an environmental installation, the one or more control commands configuring the environmental installation to apply the determined one or more second environmental conditions to the cutting. This way, the determined one or more second environmental conditions may be effectuated, in order to cause the clone to develop as planned.

[0023] In an embodiment, the at least one processor is further configured to output the determined one or more second environmental conditions and / or a recommendation based on the determined one or more second environmental conditions to a user, e.g., to a grower or an operator of a horticulture facility where the cuttings are grown or treated, using the communication interface. To that end, the communication interface may comprise a user interface or be operationally connectable to a user interface accessible by the user. This way, the user may implement or arrange to have implemented the one or more second environmental conditions. Additionally or alternatively, the user can, based on the recommendation, create groupings of clones having the same or similar recommendations.

[0024] In an embodiment, the cutting is of the genus Cannabis. Cannabis plants are typically grown in well-controlled environments as the flower buds they produce have strict requirements in levels of certain metabolites, such as terpenes, THC, DDC, et cetera. Hence, a high degree of uniformity is desired for these plants. In other embodiments, the cutting may be of a different genus, typically a genus that is grown in horticulture, e.g., roses, hydrangeas, chrysanthemums, geraniums, mint.

[0025] In an embodiment, the first and / or second environmental conditions comprise one or more of: substrate temperature, substrate humidity, substrate pH, substrate texture, substrate water retention capability, air temperature, air humidity, CO2level, nutrient flow, irrigation properties, radiation recipe. These are all conditions that may affect growth and development of both the mother plant and the cutting or clone. Hence knowing the first2023PF80480

[0026] 4

[0027] environmental condition(s) and subsequently controlling a second environmental condition(s) allows to form highly homogeneous groups of plants.

[0028] In an embodiment, a radiation recipe defines one or more of:

[0029] - a photon flux of radiation as emitted by an irradiation system, - a photon flux density of the radiation as received from the irradiation system by the mother plant prior to obtaining the cutting,

[0030] - a photon flux density of the radiation as received from the irradiation system by the clone obtained from the cutting,

[0031] - a spectral power distribution of the radiation generated by the irradiation system, and

[0032] - a timing of the irradiation from the irradiation system.

[0033] It is to be noted that the irradiation system, e.g., the radiation source(s), for providing radiation to the mother plant is not necessarily the same as the irradiation system, e.g., the radiation source(s), for providing radiation to the cutting / clone. Therefore, in one embodiment, the radiation source(s) for providing radiation to the mother plant and the radiation source(s) for providing radiation to the cutting / clone are included in the same irradiation system and, in another embodiment, the radiation source(s) for providing radiation to the mother plant and the radiation source(s) for providing radiation to the cutting / clone are part of different irradiation systems. In the latter case, the data processing system may be configured to communicate with both irradiation systems and send control signals to both irradiation system to implement and execute radiation recipes.

[0034] The timing of the irradiation may refer to a photoperiod (expressed as, e.g., a number of hours per day) and / or to a schedule of the irradiation (i.e., at which hours of the day). In such an embodiment, the data processing system may be configured to cause the irradiation system to generate radiation such that the radiation has the photon flux and / or photon flux density and / or the spectral power distribution and / or the timing of the irradiation as defined by the first and second radiation recipes and applied to the mother plant and the clone, respectively.

[0035] The timing of the irradiation may include temporal variation of the photon flux (density) and / or spectral power distribution, and / or the duration of the irradiation. The photon flux density may be defined, e.g., in μmol / (m2s), or in any other useful quantity.

[0036] In an embodiment, the radiation recipe defines a spatial distribution of the radiation emitted by the irradiation system. A radiation recipe with a non-homogeneous spatial radiation distribution applied to the mother plant(s) may be used to provide specific2023PF80480

[0037] 5

[0038] treatment of parts of the mother plant before the clipping, or provide different treatments to different mother plants. Conversely, cuttings or clones obtained from different parts of a mother plant or from different mother plants exposed to radiation with a different spectral power distribution, may be exposed to different second environmental conditions. A radiation recipe with a non-homogeneous spatial radiation distribution applied to a plurality of cuttings or clones may be used to separately optimize growth or development of certain cuttings or clones from the plurality of clones.

[0039] In an embodiment, the one or more first environmental conditions of the mother plant prior to obtaining the cutting from the mother plant comprise a time-series of first environmental conditions. The properties of the cutting may be affected by the first environmental conditions over a period of time prior to the clipping. Using a time-series of first environmental conditions, more precise second environmental conditions may be determined. In other embodiments, a statistically representative value may be used, e.g., a mean or median value of the first environmental conditions to determine second environmental conditions. A time-series comprises a plurality of values obtained at different moments in time. The time-series may comprise at least two, at least four, at least ten, or at least twenty values. The time-series may cover a time interval of at least one day, at least two days, at least a week, at least two weeks, at least a month, or at least two months prior to obtaining the cutting. The time-series may cover a time interval of at most two months, at most six weeks, at most one month, or at most two weeks. In general, a longer time-series comprises more potentially relevant information, while a shorter time-series may be more easily processed.

[0040] When the environmental conditions in the growing environment are not uniform, the environmental conditions experienced by the mother plant may depend on the location of the mother plant in the growing environment. Hence, the first environmental condition may be a localized or location specific environmental condition. The localized or location specific environmental condition may be obtained from local sensors or may be obtained from information comprising a density map of the environmental condition for the growing environment, wherein such density map is a representation of the distribution and intensity of the environmental condition across the growing environment, or may be obtained from an estimate based on environmental conditions available for other, e.g., nearby, locations in the growing environment.

[0041] In an embodiment, the one or more characteristics of the mother plant comprise at least one of: a location of the mother plant in a growing environment, a location2023PF80480

[0042] 6

[0043] of the cutting on the mother plant, a position and / or an orientation of the cutting relative to the mother plant, an age of the mother plant, a species of the mother plant, a morphology of the mother plant, a health status of the mother plant, a number of days since a previous cutting from the mother plant. These characteristics of the mother plant, and / or of the cutting-to-be (i.e., when the cutting-to-be is still part of the mother plant), can all affect the growth and development of the cutting once clipped or the clone.

[0044] For example, the environmental conditions experienced by a part of the mother plant prior to clipping may depend on the position of the cutting-to-be on the mother plant. For example, a branch high up in the canopy may receive more light than one closer to the ground. A branch pointing ‘outward’ of a group of plants, e.g. into a walkway, may experience different conditions than a branch pointing ‘inward’ into a group of plants.

[0045] Similarly, temperatures, humidity levels, et cetera, may all be different.

[0046] Furthermore, the properties of the cutting may depend on the location on the mother plant the cutting was cut from, e.g., closer to the stem or further out, closer to the roots or to the top, et cetera.

[0047] In an embodiment, the one or more characteristics of the clipping process used to obtain the cutting from the mother plant comprise at least one of: wounding of the cutting, wound properties of a wound applied during the clipping process, leaf trimming, application of rooting hormones to the cutting, angle of cutting, type of cutting implement, sharpness of cutting implement, cleanliness of cutting implement.

[0048] These characteristics of the clipping process can all affect the growth and development of the cutting or the clone. One or more of these parameters may be provided for all cuttings, e.g., based on a cutting protocol; alternatively, one or more of these parameters may be determined separately for each cutting, e.g., based on actual practice.

[0049] In an embodiment, determining one or more second environmental conditions comprises providing the information associated with the cutting to an input of a machinelearning model and receiving from the machine-learning model an inference on the one or more second environmental conditions. The machine-learning model is trained to determine the one or more second environmental conditions in response to receiving the information associated with the cutting.

[0050] In an embodiment, the machine-learning model comprises a first algorithm trained to predict, in response to receiving the information associated with the cutting, a growth trajectory for the clone obtained from the cutting in dependence on a set of parameters representing the one or more second environmental conditions, and a second2023PF80480

[0051] 7

[0052] algorithm to select, based on the growth trajectory for the clone from the first algorithm and a growth target, optimized parameters representing the one or more second environmental conditions for achieving the growth target.

[0053] By functionally separating the growth model algorithm and the optimization algorithm, an efficient and easy to generalize machine-learning model can be created.

[0054] In a further aspect, embodiments in this disclosure relate to an irradiation system comprising one or more controllable radiation sources and a data processing system as described above. In embodiments, the irradiation system may further comprise a control system or one or more controllers configured to control the controllable radiation sources. The control system or the one or more controllers may be separate from or integrated in the one or more controllable radiation sources.

[0055] The irradiation system may comprise one or more irradiation subsystems, each irradiation subsystem comprising one or more controllable radiation sources. The one or more irradiation subsystems may be controlled independently from each other. For example, a first irradiation subsystem may comprise one or more first controllable radiation sources for providing radiation to the mother plant(s), and a second irradiation subsystem may comprise one or more second controllable radiation sources for providing radiation to the cutting(s) / clone(s).

[0056] In an embodiment, the second environmental conditions comprise a radiation recipe, and the data processing system is configured to send control commands to the one or more controllable radiation sources, or the control system or the one or more controllers controlling the one or more controllable radiation sources, according to the radiation recipe. The controllable radiation sources may be configured to irradiate the cutting or the clone obtained from the cutting in accordance with the received control commands. This way, the cutting or the clone may be irradiated with the determined radiation recipe.

[0057] In an aspect, this disclosure relates to a horticulture arrangement comprising such a system. The term “horticulture arrangement” especially refers to an arrangement including a plant support wherein or whereon plants may grow, an irradiation system that is configured to direct (horticulture) radiation to the plant support wherein or whereon the plants may grow (or grow), and a control system that controls the (horticulture) radiation. The control system may comprise or be communicatively connected to the data processing system. In use, the horticulture arrangement may include a plant support with a cutting or a clone.2023PF80480

[0058] 8

[0059] The term “horticulture arrangement” may also refer to a plant farm or climate cell, also known as a vertical farm or city farm, wherein the plants are grown under controlled conditions, and wherein the plants substantially do not receive natural radiation (daylight). Further, such plant farm may be climatized, such as in the case of a climate cell. Hence, in embodiments, the horticulture arrangement includes such plant farm or climate cell. In other embodiments, the plant farm or climate cell includes at least part of the horticulture arrangement. For instance, a climate cell may comprise the plant support and the irradiation system, and the control system may be configured inside or external from the climate cell. Especially, a plant farm may comprise a climate cell.

[0060] The control system of a horticulture arrangement may control one or more of temperature, humidity, CO2level, irrigation, nutrient supply, radiant intensity or irradiance and / or a spectral intensity or spectral irradiance of the horticulture radiation, air conditions including one or more of air temperature, air composition, air flow, etc. The control system may be configured to control one or more of these conditions at different locations in the horticulture arrangement. The radiant intensity as received by the plurality of plants may refer to, e.g., the physical quantity “irradiance” (typically expressed in W / m2) or “photon flux density” (typically expressed in μmol / (m2s)). The irradiation with the horticulture radiation may in embodiments be done in response to, e.g., one or more of time of the day, season of the year, (local) (natural or environmental) irradiation conditions, age of plant, condition of the plant, planting period, etc. Hence, the irradiation with the horticulture radiation may in embodiments be done in response to plant related data, time related parameters, conditions to which the plant is subjected (such as natural radiation, temperature, relative humidity, CO2level, irrigation, nutrient supply, etc.).

[0061] The irradiation system can be especially configured to provide horticulture radiation to plants. This may especially imply that the irradiation system is configured to provide horticulture radiation in a direction of a plant support wherein or whereon plants may grow. Such plant support may be a tray. Especially, the term “plant support” may also refer to a plurality of plant supports, as the plants may be grown in layers one over the other (“multi-layer system”). Hence, a rack, with two or more plant supports, each with a corresponding irradiation systems, or alternatively, each with a corresponding radiation sources of the irradiation system, is also included. Hence, the term “irradiation system” may also refer to a plurality of (individually controlled) irradiation systems.2023PF80480

[0062] 9

[0063] Further, the control system is configured to control one or more of a radiant intensity or irradiance and / or a spectral intensity or spectral irradiance of the horticulture radiation.

[0064] The phrase “radiant intensity or irradiance and / or a spectral intensity or spectral irradiance of the horticulture radiation” refers to quantities defined in the SI radiometry standard. An overview of SI radiometric quantities, units and dimensions is available on https: / / en.wikipedia.org / wiki / Radiometry.

[0065] In an aspect, embodiments in this disclosure relate to a computer-implemented method comprising receiving information associated with a cutting of a mother plant, and determining one or more environmental conditions for the cutting or for a clone obtained from the cutting based on at least the information associated with the cutting. The information associated with the cutting may comprise at least one of one or more environmental conditions of the mother plant of the cutting prior to obtaining the cutting from the mother plant; one or more characteristics of the mother plant, or one or more characteristics of a process used to obtain the cutting from the mother plant.

[0066] Thus, an irradiation system as described above may be controlled using this method. The method may be executed, for example, by the data processing system described above.

[0067] One aspect of this disclosure relates to a computer program or suite of computer programs comprising at least one software code portion or a computer program product storing at least one software code portion, the software code portion, when run on a computer system, being configured for executing any of the methods disclosed herein.

[0068] One aspect of this disclosure relates to a non-transitory computer-readable storage medium storing at least one software code portion, the software code portion, when executed or processed by a computer, is configured to perform any of the methods disclosed herein.

[0069] As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, a method or a computer program product.

[0070] Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Functions described in this disclosure may be implemented as an algorithm executed by a processor / microprocessor of a computer. Furthermore, aspects of the present invention may take the form of a computer2023PF80480

[0071] 10

[0072] program product embodied in one or more computer readable medium(s) having computer readable program code embodied, e.g., stored, thereon.

[0073] Any combination of one or more computer readable medium(s) may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer readable storage medium may include, but are not limited to, the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of the present invention, a computer readable storage medium may be any tangible medium that can contain, or store, a program for use by or in connection with an instruction execution system, apparatus, or device.

[0074] A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0075] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber, cable, RF, etc., or any suitable combination of the foregoing. Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java™, Python, Smalltalk, C++ or the like and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The program code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through2023PF80480

[0076] 11

[0077] any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0078] Aspects of the present invention are described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products as claimed in embodiments of the present invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor, in particular a microprocessor or a central processing unit (CPU), of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer, other programmable data processing apparatus, or other devices create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0079] These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0080] The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0081] The flowcharts and diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products as claimed in various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the2023PF80480

[0082] 12

[0083] blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0084] Moreover, a computer program for carrying out the methods described herein, as well as a non-transitory computer readable storage-medium storing the computer program are provided. A computer program may, for example, be downloaded (updated) to the existing systems (e.g., to the existing control systems) or be stored upon manufacturing of these systems.

[0085] Elements and aspects discussed for or in relation with a particular embodiment may be suitably combined with elements and aspects of other embodiments, unless explicitly stated otherwise. Embodiments of the present invention will be further illustrated with reference to the attached drawings, which schematically will show embodiments as claimed in the invention. It will be understood that the present invention is not in any way restricted to these specific embodiments.

[0086] BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Aspects of the invention will be explained in greater detail by reference to exemplary embodiments shown in the drawings, in which:

[0088] FIG. 1 schematically illustrates a plant cloning facility according to an embodiment;

[0089] FIG. 2 schematically illustrates a system according to an embodiment;

[0090] FIG. 3 is a flowchart of a method according to a first embodiment;

[0091] FIG. 4 is a flowchart of a method according to a second embodiment;

[0092] FIG. 5 depicts an example of grow trajectory for several clone groups; and FIG. 6 illustrates a data processing system according to an embodiment.

[0093] DETAILED DESCRIPTION OF THE DRAWINGS

[0094] In the figures, identical reference numbers indicate identical or similar elements.

[0095] In the cultivation of various plant genera, (including may horticulturally grown genera such as, cannabis, roses, hydrangeas, chrysanthemums, geraniums, and mint), “cloning” is a plant propagation technique which grows new plants from a piece, called a2023PF80480

[0096] 13

[0097] cutting or a clipping, of an adult plant, called the mother plant. In dioecious plants, the mother plant is typically the female plant. For example, for cannabis, propagation via cloning is preferred over propagation from seeds as the latter method is not deterministic in terms of profile (vigor, cannabinoids) and gender of the resulting new plants (after propagation from seeds, male plants need to be identified and removed from the area to avoid unwanted pollination). By cloning from well-maintained and well-observed mother plants, farmers can expect less variability among different clones as well as less variability between the mother and each of the clones. This increases predictability of output and facilitates environment optimization: as the plants are highly similar, they will react in very similar ways to environmental conditions such as light, temperature, and humidity. Moreover, new plants propagated from clones always have the same gender as the mother plant (and hence, for cannabis, are always females).

[0098] Typically, at the start of the cloning process, farmers create a required number of cuttings from the mother stock. The subsequent growth and development behavior of a cutting depends, inter alia, on the clipping angle, the sharpness of the clipping implement, and the application of wounding. After clipping, each cutting is trimmed for uniform structure and to reduce the leaf area (so that clone spends its energy predominantly on rooting), and rooting hormones (e.g., Auxin IBA) may be applied at the end of each cutting. The cutting is then planted in a small cube of grow medium (e.g., rockwool), after which it may be referred to as a clone. Subsequently, the clones are packed tightly in a tray and are covered with transparent domes to control the micro-environment of the cuttings and retain high humidity and water. At times, the trays with the clones may be heated from the bottom using a heat mat.

[0099] For cannabis, for instance, the duration of the cloning stage of the propagation process varies between 3 to 14 days depending on the cultivar, growth recipe and farmer’s objectives. At the end of this stage, clones have developed a root system, a new stem and new leaves and hence have become a new plant that’s genetically identical to but independent of the original mother plant.

[0100] The success rate of such cloning processes is however less than optimal. Hence, farmers currently have to compensate for the poor success rate of (Cannabis) propagation by starting the clone stage with more cuttings than their actual needs; for example, a farmer may start with 1500 clones while the capacity of the flowering room is only 1000 plants. This practice results in a suboptimal use of the cloning area in the greenhouse, a significant waste of energy and material which are spent on the many clones2023PF80480

[0101] 14

[0102] that do not continue to the flowering area, and unnecessary stress on the mother stock as it needs to provide more cuttings than necessary. The unnecessary stress leads to a reduced lifetime of the mother plant.

[0103] At the end of cloning stage, farmers would like to have an as high as possible uniformity among clones so that, when they transplant them to larger vegetative growth rooms, they can apply the same growth recipe to all clones / plants, or at least all clones / plants within a single vegetative growth room. A growth recipe comprises target values, which may vary over time, for controllable environmental conditions. The growth recipe may comprise a radiation recipe, an irrigation (and nutrition) recipe, a target temperature, a target humidity, a target CO2level, et cetera. Different growing facilities may have different constraints with respects to controllable environmental conditions, or different ranges of controllability of environmental conditions. Hence, the growth recipe may depend on the environmental installation in which the growth recipe is applied. Further, in practice, cannabis clones obtained from cuttings of different mother plants may exhibit high variance owing to differences in the mother plants, differences in environmental conditions experienced by the mother plants, the location on the mother plants where the cuttings were taken from, differences in clipping processes (for instance, differences in wounding, clipping, applying rooting hormones etc.) and differences in growth recipe (light, water, humidity, temperature etc.) during growth of the mother plant. For example, the root and stem development of the clones correlate with the age and health of mother plants as well as which the part of the mother plants the cuttings were taken from. Across the industry, farmers suffer from an up to 10-25% of cultivation cost increase associated with the lack of uniformity among the cuttings / clones / plants of a single cultivation batch. The actual loss varies depending on cultivars and the farmer’s experience.

[0104] Farmers currently address this uniformity issue by scoring and grouping clones at the very end of the cloning stage. Subsequently, each of the identified groups is then cultivated separately in the greenhouse during the vegetative and flowering stages using group-specific growth recipes. At times, farmers intentionally create different clone groups (of the same cultivar) with slightly different properties depending on their forecasted enduser demand (e.g., in the case of cannabis, the farmer may aim to create 1000 plants for medicinal end use and 500 plants for recreational end use; or for perishable produce, a certain amount of produce in one week and a different amount of produce in a different week, based on, e.g., a different expected demand from the market due to the holiday season). However, it is an operational nightmare for the farmer to produce an exact number of clones for every2023PF80480

[0105] 15

[0106] group with precisely its desired properties. As a result, farmers often struggle at the end of each cultivation cycle to meet their customer' s demands while at the same time struggling to run an efficient production process in terms of cost, space usage and labor.

[0107] Although cloning is one of the most important stages in the cultivation of certain plants, there is lack of cloning-stage-specific light recipes available in the industry today, in particular for cannabis. Reasons for the lack of cloning-stage specific light recipes are that the role of lighting during propagation stage is largely unexplored from a scientific perspective; the length of the cloning and propagation stage is relatively short (e.g., up to 14 days for cannabis), compared to the length of the vegetative and flowering stages (e.g., 56 days for cannabis); and the floor area in the growing facility occupied by plants (clones) in the cloning and propagation stage is substantially smaller than the floor area in the growing facility occupied by plants in the vegetative and flowering stage.

[0108] Fig. 1 schematically illustrates a horticulture arrangement, e.g., a plant cloning facility, according to an embodiment. The cloning facility comprises a first plant growing facility 10i, in this example housing the mother plants 11 that are to be cloned. The first plant growing facility 10i includes a monitoring system 1 for monitoring first environmental conditions of the mother plants 11. The first environmental conditions may comprise one or more of: substrate temperature, substrate humidity, substrate pH, substrate texture, substrate water retention capability, air temperature, air humidity, CO2level, nutrient flow, irrigation properties, irradiance, et cetera. The irradiance may refer to, e.g., radiation intensity (typically expressed in W / m2) or photon flux density (typically expressed in μmol / (m2s)), and may or may not be spectrally resolved. The first environmental conditions may be stored by the monitoring system as one or more time-series. It is noted that both the temporal and the spatial resolution of monitoring may be different for different environmental conditions.

[0109] The monitoring system 1 comprises one or more sensors 131,2 for monitoring the first environmental conditions; in this example a light sensor 131 and a temperature sensor 132. Other embodiments may have more or different sensors. The monitoring system may also comprise a sensor controller 9 which collects sensor data, optionally pre-processes and stores the sensor data, and transmits the sensor data to the first data processing system 100i of the first plant growing facility 10i. The sensor controller 9 may be configured to control one or more of the sensors 1312,2. In other embodiments, at least part of the functionality of the sensor controller 9 is embedded in the first data processing system 100i.

[0110] In the depicted embodiment, the first plant growing facility 10i also comprises an environmental installation 3. The environmental installation 3 is configured to control one2023PF80480

[0111] 16

[0112] or more of the first environmental conditions. The first environmental conditions that are controlled by the environmental installation 3 may completely or partially overlap with the first environmental conditions that are monitored by the monitoring system 1.

[0113] In this example, the environmental installation 3 comprises a multi-channel irradiation system, wherein each channel is configured to emit radiation at a respective (controllable) intensity in a respective spectral band. In this context, a channel refers to one or more radiation sources that are controlled together. In the depicted example, the irradiation system comprises a plurality of controllable radiation sources 5. The controllable radiation sources may comprise, e.g., a plurality of individually or group-wise controllable LEDs. In this example, the radiation sources 5 are controlled by controller 7. The radiation sources may be configured to provide radiation according to a radiation recipe, e.g., as part of a so-called growth recipe. The controller can control the intensity of each of the channels, thus controlling a spectral power distribution of the emitted radiation. The radiation may comprise visible light, such as red, blue, green, and / or white light, and / or radiation outside the visible spectrum, e.g., (near) infrared and / or (near) ultraviolet light.

[0114] The first plant growing facility 10i may also comprise a plant monitoring system (not explicitly shown). The plant monitoring system may be (partially) integrated with the monitoring system 1; for example, the monitoring system may comprise one or more camera which may be used both to monitor the plants 11 and to monitor the lighting conditions. The plant monitoring system may monitor, for example, the health of the mother plants 11 and / or morphological properties of the mother plants 11, such as leaf color, stem thickness, leaf coverage, et cetera.

[0115] The first data processing system 100i comprises a processor, a memory, and a communication interface. The memory and the communication interface are communicatively connected to the processor. The memory may store executable instructions that, when executed by the processor, configure the processor to perform method steps as described herein, e.g., the method steps described with reference to Fig. 3 and 4. The communication interface may comprise an input interface and an output interface, which may be separated or combined. In particular, the first data processing system 100i may be configured to receive, via the communication interface, sensor data from the monitoring system 1 (via sensor controller 9). Similarly, the first data processing system 100i may be configured to generate and transmit control signals, via the communication interface, to the environmental installation 3 (via controller 7). For example, the first data processing system may transmit control signals to the controller 7, which controller may be configured to2023PF80480

[0116] 17

[0117] receive said control signals and control the radiation sources 5 accordingly. An example of a data processing system is described in more detail below with reference to Fig. 6.

[0118] At some point, cuttings 21 may be obtained from the mother plants 11, using a clipping process 20. The clipping process may comprise various steps (not shown here), including so-called wounding of the cuttings, trimming of the cuttings, application of rooting hormones to the cuttings, et cetera.

[0119] In the depicted embodiment, the cuttings are sorted 221,2 into a plurality of groupings. The sorting process may be aimed to create groupings of cuttings that are similar to each other, and that may lead to similar clones. The sorting process may take into account properties of the cuttings, such as size, stem thickness, internode distance, et cetera.

[0120] Additionally or alternatively, the cuttings may be sorted based on, inter alia, properties of the clipping process, based on properties of the mother plant, environmental conditions of the mother plant, and so forth.

[0121] In the depicted embodiment, the plant cloning facility comprises a second data processing system IOO2, which second data processing system IOO2 is configured for determining an environmental condition for treatment or growing of the cuttings 21 from the mother plants 11. The second data processing system IOO2 may be the same data processing system as the first data processing system 100i.

[0122] The second data processing system IOO2 comprises a memory storing computer-readable instructions, at least one communication interface, and at least one processor. The at least one processor is configured to, in response to executing the computer-readable instructions, receive, via the at least one communication interface, information associated with the cuttings 21. To that end, the communication interface may be communicatively connected to the first data processing system 100i for receiving mother plant related data and / or may be communicatively connected to a user interface for receiving characteristics of the cuttings 21, the clipping process 20 and / or the mother plants 11.

[0123] The information associated with the cuttings 21 comprises at least one of: one or more first environmental conditions of the mother plants 11 of the cuttings 21 prior to obtaining the cuttings 21 from the mother plants 11; one or more characteristics of the mother plants 11; and one or more characteristics of the clipping process 20 used to obtain the cuttings from the mother plants 11 and / or used to handle the cuttings 21 until the cuttings are planted. Optionally, the at least one processor may receive external information 24 related to a target growth and development trajectory of the clones resulting from the cuttings 21.2023PF80480

[0124] 18

[0125] The one or more characteristics of a mother plants of a cutting may comprise at least one of: a location of the mother plant in the growing environment, a location of the cutting on the mother plant, a position and / or an orientation of the cutting relative to the mother plant, an age of the mother plant, a species of the mother plant, a morphology of the mother plant, a health status of the mother plant, or a number of days since a previous cutting from the mother plant. The one or more first environmental conditions of the mother plants prior to obtaining the cutting from the mother plant may comprise a time-series of the first environmental conditions.

[0126] The one or more characteristics of the clipping process used to obtain the cutting from the mother plant may comprise at least one of: information regarding wounding of the cutting, wound properties of a wound applied during the clipping process, information regarding leaf trimming, information regarding application of rooting hormones to the cutting, an angle of cutting, a type of a cutting implement used for the cutting, a sharpness of the cutting implement, a cleanliness of cutting implement.

[0127] The at least one processor is configured to determine one or more second environmental conditions for treatment or growing of the cuttings 21 or of clones 291,2 obtained from the cuttings, based on at least the information associated with the cutting. The information associated with the cutting comprises at least one of: one or more first environmental conditions of a mother plant of the cutting prior to obtaining the cutting from the mother plant; one or more characteristics of the mother plant; and one or more characteristics of a process used to obtain the cutting from the mother plant and / or used to handle the cutting until the cutting is planted.

[0128] The determined second environmental conditions may comprise one or more of the following parameters: a substrate temperature, a substrate humidity, a substrate pH, a substrate texture, a substrate water retention capability, an air temperature, an air humidity, a CO2level, a nutrient flow, irrigation properties, or a radiation recipe. These parameters may be provided as a time-series with a suitable temporal resolution. The radiation recipe may define one or more of: an intensity of radiation as emitted by an irradiation system (e.g., in terms of photon flux), an irradiance of the radiation as received from the irradiation system by the clone obtained from the cutting (e.g., in terms of photon flux density), a spectral intensity of the radiation generated by the irradiation system, a spatial distribution of the radiation emitted by the irradiation system, and a timing of the radiation from the irradiation system.2023PF80480

[0129] 19

[0130] The at least one processor may determine the one or more second environmental conditions, at least in part, by providing the information associated with the cutting to an input of a trained machine-learning model and receiving from the machinelearning model an inference on the one or more second environmental conditions. The machine-learning model may have been trained to determine the one or more second environmental conditions in response to receiving the information associated with the cutting.

[0131] The machine-learning model may comprise a first algorithm trained to predict a growth trajectory for the clone obtained from the cutting in dependence on a set of parameters representing the one or more second environmental conditions, and a second algorithm to select optimized parameters representing the one or more second environmental conditions based on the first algorithm and a target growth. A more detailed example of such a machine-learning model is described in more detail below with reference to Fig. 4 and 4.

[0132] In the depicted embodiment, the plant cloning facility comprises a plurality of climate cells 231,2, each of which houses clones obtained from a grouping of the cuttings 21. Other embodiments may use different growing environments for the clones. Each climate cell 231,2 comprises a climate cell environmental installation for controlling the (micro)-climate in the climate cell. In the depicted example, the climate cell environmental installation comprises a controllable radiation source 251,2 and a heater 271,2. Thus, for example, the second data processing system may determine a first radiation recipe and a first temperature profile for the first climate cell 231 containing the first grouping of clones 29i, and a second radiation recipe and a second temperature profile for the second climate cell 232 containing the second grouping of clones 292.

[0133] In other embodiments, the second data processing system IOO2 may output the determined one or more second environmental conditions using the communication interface, e.g., in the form of a recommendation to a user via a user interface. This can be especially useful if the cuttings are grown in a growing facility with a climate installation that is not controlled, directly or indirectly, by the second data processing system IOO2.

[0134] After the clones have been exposed to the second environmental conditions for a sufficient amount of time and have developed a root system, new stems and new leaves, the resulting plants may be grown further, e.g., through a vegetative growth stage and flowering growth stage (in the case of cannabis plants) until they can be harvested. In the depicted examples, the first grouping of clones 29i is moved to a second plant growing facility IO2, which may, in terms of environmental control options, be similar or identical to the first plant growing facility 10i.2023PF80480

[0135] 20

[0136] In an embodiment, the second environmental conditions comprise a radiation recipe. In such an embodiment, the environmental installation may comprise an irradiation system with controllable radiation properties, e.g., radiant intensity, spectral intensity, photoperiod, et cetera, configured to irradiate the clones. The environmental installation may further comprise, e.g., a heating system, a ventilation system, an irrigation system, and so on.

[0137] The clone growing facility (e.g., the climate cells 231,2 in Fig. 1) may further comprise a sensing system configured for measuring one or more aspects of growth and development of the clones being grown in the clone growing facility. Such a sensing system may comprise one or more of an imaging system (e.g., an RGB, RGB+IR, hyperspectral, or RF imaging system), a stem sensor, a sap flow sensor, a root sensor, et cetera.

[0138] Fig. 2 schematically illustrates a system according to an embodiment. The system may be a data processing system e.g., as described in more detail with reference to Fig. 6. In the depicted embodiment, the system comprises a memory storing a machinelearning model 32, at least one processor, e.g., a microprocessor, communicatively connected to the memory, and at least one communication interface, communicatively connected to the processor.

[0139] The at least one processor is configured to receive, via the at least one communication interface, information 30 associated with a cutting 21. The information 30 associated with the cutting 21 may comprise at least one of one or more first environmental conditions of a mother plant 11 of the cutting, obtained via sensor(s) 13, prior to obtaining the cutting from the mother plant 11, one or more characteristics of the mother plant 11, one or more characteristics of a clipping process 20 used to obtain the cutting 21 from the mother plant 11 and / or used to handle the cutting 21 until the cutting 21 is planted. The information 30 associated with the cutting 21 may also comprise information on the cutting 21 itself.

[0140] The machine-learning model 32 may be used to determine the second environmental conditions 37 as described above. The second environmental conditions are determined based on at least information 30 associated with the cutting. The second environmental conditions may furthermore be determined based on input 38 received from the sensing system, which may be used to adjust or finetune initially determined second environmental conditions. For example, input 38 may relate to a time-series of the second environmental conditions, and / or (a time-series of) a growth property of the clone (e.g., root formation, length, leaf formation, leaf area), et cetera.

[0141] The machine-learning model 32 may be configured to determine second environmental conditions 37 for a predetermined period of time, which second environmental2023PF80480

[0142] 21

[0143] conditions maximize a probability that the clones that have been exposed to the determined second environmental conditions meet one or more target criteria at an end of the predetermined period of time. To that end, the machine-learning model may be configured to receive the one or more target criteria as input. The machine-learning model may furthermore be configured to receive constraints associated with the environmental installation used to control the environmental conditions of the clones being grown.

[0144] In the depicted embodiment, the machine-learning model comprises a first algorithm 34 trained to predict a growth trajectory for a clone in dependence on a set of parameters representing one or more second environmental conditions. The growth trajectory is further determined based on the received information 30 associated with the cutting from which the clone was obtained. The first algorithm 34 may also be referred to as a clonegrowth algorithm.

[0145] As an example, the clone-growth algorithm may estimate a growth trajectory using knowledge of previous clone-growth trials, knowledge of the mother plant and / or the cutting, observations from the sensing system and the clone’s reaction to the administered environmental conditions (e.g., a radiation recipe).

[0146] The clone-growth algorithm may use a discretized time, in which case the changes relative to a previous time step may be determined. A time step typically has a duration in a range from a few hours to about a day, e.g., 2, 3, 4, 6, 8, 12, or 24 hours.

[0147] Reinforcement learning may be used which quantifies differences between a modelled current state and an observed current state of the clone 38 to reward or penalize prior actions. The reinforcement learning hence heuristically identifies the underlying growth model of a clone without a need to explicitly model all physiological growth and development processes going on in the clone.

[0148] The clone-growth algorithm can be generalized across different cultivars by translating cultivar-specific features using token embeddings. Because the development of a root system is difficult to visually assess, the described clone-growth algorithm leverages the fact that development of root propagation can be modelled by correlating secondary growth features (such as stem and leaf development) with farmer-given root scores. For example, plants with good rooting may respire better and hence have lower leaf temperature which can be observed using a leaf temperature sensor or IR camera. Similarly, plants with good rooting may produce new leaves faster.

[0149] In the depicted embodiment, the machine-learning model 32 further comprises a second algorithm 36 to select optimized parameters representing the one or more second2023PF80480

[0150] 22

[0151] environmental conditions 37 (for a next time step) based on the first algorithm 34 and one or more target criteria, such as a target growth or target metabolite profile. The optimized parameters representing the (optimized) one or more second environmental conditions may be referred to as a clone recipe, which may include, e.g., a radiation recipe, an irrigation recipe, and so on. Hence, the second algorithm 36 may be referred to as the clone-recipe algorithm. The clone-recipe algorithm 36 may use a known optimization model to optimize one or more parameters representing the second environmental conditions (of a next time step), e.g., using a cost function based on a difference between the one or more target criteria and a predicted clone state modelled using the clone-growth algorithm 34.

[0152] For example, the clone-growth algorithm 34 may receive, as input, information 30 associated with the cutting 21 comprising at least one of:

[0153] - one or more first environmental conditions of a mother plant 11 of the cutting 21 prior to obtaining the cutting 21 from the mother plant 11, e.g., for a period of a number of days or weeks prior to the clipping process 20, such as daily light integral, daily temperature profile, and / or irrigation recipe;

[0154] - one or more characteristics of the mother plant 11, e.g. on the day of the clipping process, such as health score, vigor score, age, amount of time since last cutting, and / or cutting location; and

[0155] - one or more characteristics of a clipping process 20 used to obtain the cutting 21 from the mother plant 11 and / or used to handle the cutting 21 until the cutting 21 is planted, such as (absolute or relative) amount of rooting hormone applied, presence of a cutting wound, location and angle of a cutting wound, and / or number of leaves trimmed.

[0156] Additionally, the clone-growth algorithm 34 may receive, as input, one or more of:

[0157] - cutting properties (i.e., before planting), such as stem width, internode length, and / or number of leaves present; and

[0158] - clone properties (i.e., after planting), e.g. as input 38, such as water stress level, stem width, presence and type of pests, and / or relative water content.

[0159] The clone-growth algorithm 34 may also receive, as input, one or more past or current second environmental conditions. For example, the clone-growth algorithm 34 may receive the current second environmental conditions, or a current clone recipe, and use this to predict the development of the clones during a next time step, assuming that the second environmental conditions, or the clone recipe, remains the same. Alternatively, the clone-2023PF80480

[0160] 23

[0161] growth algorithm 34 may extrapolate the second environmental conditions for the next time step based on one or more respective trajectories of the one or more second environmental conditions over the past time steps. Additionally or alternatively, the clone-growth algorithm 34 may assume one or more second environmental conditions for the next time step based on previous growth cycles.

[0162] The clone-growth algorithm 34 may provide, as output, one or more predicted clone properties after a next time step, or at or after each of a plurality of next time steps (e.g., a growth trajectory until a start of the vegetative and flowering stage). The predicted clone properties may comprise one or more of: stem width, stem score, internode length, root score, meristem score, leaf score, et cetera.

[0163] The clone-recipe algorithm 36 may receive, as input, the one or more predicted clone properties after a next time step (or for one or more future time steps) that have been output by the clone-growth algorithm 34.

[0164] Additionally, the clone-recipe algorithm 36 may receive, as input, one or more clone properties from one or more previous time steps (possibly all time steps of the current growth cycle, or a limited number of time steps corresponding to, e.g., a few days or about a week). The clone-recipe algorithm 36 may also one or more clone recipes, and / or the (corresponding) one or more second environmental conditions, from one or more previous time steps; typically the same time steps for which the clone properties are received. This allows the clone-recipe algorithm 36 to use the reactions of the clones, as represented by the one or more clone properties, to the clone recipes and / or second environmental conditions to which they were exposed, to improve the prediction for the next time step (or for one or more future time steps).

[0165] The clone-recipe algorithm 36 may provide, as output, a clone recipe for the next time step, the clone recipe defining one or more second environmental conditions 37 to expose the clones in climate cell 23 to during the next time step. The one or more second environmental conditions may comprise, e.g., one or more of: a radiant intensity, a photoperiod, a relative humidity, a soli temperature, an air temperature, a rate of water flow, a rate of nutrients flow, a pest management treatment, a trimming action, et cetera.

[0166] If a climate cell 23 comprises multiple clones, the clone-recipe algorithm 36 may receive targets (e.g., current and future clone properties) for all clones in the climate cell 23, and perform a multi -objective optimization for all clones. Alternatively, clone recipes may be determined for each clone, and a subsequent algorithm may receive the multiple2023PF80480

[0167] 24

[0168] clone recipes and define a single climate cell recipe, e.g., by determining a statistical representative (e.g., a mean or a median) for each controlled second environmental condition.

[0169] Thus, in brief, the clone-growth algorithm 34 may receive, as input, information 30 associated with the cutting 21, and growing information 38 from the climate cell 23. The growing information 38 may comprise clone properties, and past and / or current second environmental conditions (as measured and / or as defined in the clone recipe(s) for the past and / or current time steps). The clone-growth algorithm 34 may output target clone properties for the next time step, which are received as input by the clone-recipe algorithm 36. The clone-recipe algorithm 36 may additionally receive past and / or current clone properties, and past and / or current second environmental conditions. The clone-recipe algorithm 36 then outputs a clone recipe for the next time step.

[0170] More detailed examples of the clone-growth algorithm and clone-recipe algorithm are discussed below with reference to Fig. 4.

[0171] The machine-learning model 32 may provide recommendations to regroup the clones in several groupings of clones, based on their current status and / or the determined environmental conditions, such that clones that are to be exposed to the same or similar environmental conditions are grouped together, and / or such that clones that are to meet the same target criteria are grouped together. For example, the clone-recipe algorithm may determine a clone recipe for each clone, and suggest a grouping of the clones based on a clustering of the determined clone recipes. The clustering may be weighted to favor clusters that are similar to the current cluster, and only suggest regrouping when deviations between clone recipes in a group become too large. The (re)grouping may be updated every time step, or with a lower frequency, e.g., once a day or every wthday, where n is, e.g., 2, 3,4, 5, 6, or 7.

[0172] In an embodiment, the machine-learning model 32 may be communicatively connected to a user interface which may show, e.g., each clone’s or group of clones’ properties at a given time step t, its prior and future (estimated) growth trajectories, an associated group name, and confidence in meeting the one or more target criteria.

[0173] Thus, for instance, the machine-learning model 32 may work as follows: at each time step, the clone-growth algorithm 34 may assess (based on input information 38) the growth of each clone compared to the previous time step, estimate its growth until the next time step, score the clone (based on clone properties related to the one or more target criteria), determine an optimum number of clone groups (based on the one or more target criteria, constraints of the environmental installation, as well as the plant properties of the current growth cycle), estimate a cost function and use the clone-recipe algorithm 36 to2023PF80480

[0174] 25

[0175] generate second environmental conditions 37 (e.g., a radiation recipe) for the next time step so that clone groups are optimized towards the one or more target criteria.

[0176] Fig. 3 is a flowchart of a method according to a first embodiment. The method may be executed by a data processing system.

[0177] A first step 40 comprises receiving information associated with a cutting. The information associated with the cutting comprises at least one of:

[0178] - one or more first environmental conditions of a mother plant of the cutting prior to obtaining the cutting from the mother plant,

[0179] - one or more characteristics of the mother plant, and

[0180] - one or more characteristics of a clipping process used to obtain the cutting from the mother plant and / or used to handle the cutting until the cutting is planted.

[0181] A step 42 comprises determining one or more second environmental conditions for treatment or growing of the cutting or a clone obtained from the cutting based on at least the information associated with the cutting.

[0182] Fig. 4 is a flowchart of a method according to a second embodiment.

[0183] A first step 40 comprises receiving information associated with a cutting, as described above.

[0184] A step 44 comprises initialising a clone-growth algorithm and a clone-recipe algorithm, based on the received information associated with the cutting. This step may be performed at an initial time step to. This step comprises generating and actuating an initial growth recipe.

[0185] A step 46 comprises receiving sensor data from a sensing system configured to measure one or more aspects of growth and development of the clone being grown from the cutting. This step may be performed at a current time step i > 0.

[0186] A step 47 comprises updating the clone-growth algorithm and / or the clonerecipe algorithm based on a difference between observed and predicted sensor data.

[0187] A step 48 comprises using the clone-growth algorithm to predict a growth and development of the clone for one or more future time steps Zj, j > i.

[0188] If the process is performed for multiple clones, a step 50 may comprise clustering the clones based on the predicted growth and development. The clones may be clustered in real (physical) or virtual clusters. Virtual clusters may be used, e.g., when physically moving clones is either impractical or too expensive. Virtual clusters can help with, e.g., delivering a micro-recipe if the growing environment is equipped with granular2023PF80480

[0189] 26

[0190] controls, such as pixelated lighting, tray-level irrigation controls etc. Virtual clusters can also assist digitally identifying a clone’s score and treat them differently during manual farm operations (e.g., clipping, spraying nutrients, and so on).

[0191] A step 52 comprises using the clone-recipe algorithm to generate a growth recipe for each (real and / or virtual) cluster.

[0192] A step 54 comprises causing the generated growth recipes to be actuated. This step may comprise directly controlling one or more environmental installations, transmitting the growth recipes to one or more climate computers configured to actuate the growth recipes, or outputting the growth recipes to a user interface to be implemented by a farmer, or some other suitable way to directly or indirectly cause the growth recipes to be actuated.

[0193] Steps 46-54 may be repeated until the end of the cloning stage is reached. The clone-growth algorithm may be a cultivar-agnostic clone-growth algorithm. The clone-growth algorithm can estimate growth of a clone given prior knowledge on the cutting, current properties of the clone and (an estimate of) the growth recipe which will be administered.

[0194] In an embodiment, the clone-growth algorithm comprises a neural network (e.g., a recurrent neural network or a transformer neural network). The clone-growth algorithm may generate one or more clone properties for each future time step Zj, j > i (where z represents the current time step), such as, for instance: stem diameter root score, and number of branches.

[0195] Typically, during propagation, the clone height may not vary much between plants with different root scores, as the clippings may be cut in a way to be of same size and plant height growth during this period is generally small.

[0196] In an embodiment, the clone-growth algorithm may use as input data, information associated with the cutting, and sensor data associated with a growth and development of the clone obtained from the cutting.

[0197] The information associated with the cutting may comprise one or more of the following: one or more characteristics of a clipping process used to obtain the cutting from the mother plant and / or used to handle the cutting until the cutting is planted, one or more characteristics of the mother plant from which the cutting is obtained, and one or more first environmental conditions of a mother plant of the cutting prior to obtaining the cutting from the mother plant.

[0198] The one or more characteristics of a clipping process used to obtain the cutting from the mother plant and / or used to handle the cutting until the cutting is planted may2023PF80480

[0199] 27

[0200] comprise one or more of: a use of rooting hormones (Auxin IBA etc.), a presence of a wound (intentional cut) at a bottom end of the cutting (correctly wounded plants are more likely to root and take relatively shorter time to root), a precision of the administered wound (e.g., a 45° angle is known to root well), a trimming of leaves of the cutting, a nature of a blade with which the clipping was performed (e.g., a sharp scalpel cause less tissue damage than pruning shears), a cleanliness of the blade used during clipping.

[0201] The one or more characteristics of the mother plant from which the cutting is obtained may comprise one or more of: a current health of the mother plant, a number of days since a previous clipping process took place on the mother plant, a location on the mother plant where the cutting is taken from.

[0202] The sensor data associated with a growth and development of the clone obtained from the cutting may comprise one or more of: water stress (water stress may occur either due to environmental pressure or due to tissue damage while cutting bottom of stem clippings), stem width (which is generally a good indication of overall health and vigor), plant movement due to air flow (which is indicative of strength of root and stem), a presence of pests (e.g., spider mites and fungus might be prevalent at the clone stage), a presence of diseases (e.g., powdery mildew), and a water content (weight of plug or tray).

[0203] Fig. 5 depicts an example of grow trajectory for five observed clone groups in a one-dimensional latent space. The vertical axis represents, essentially, normalized clone quality, which may take multiple clone properties into account, and the horizontal axis represents time.

[0204] In this example, a farmer would like to steer observed clone groups C1-C3 towards a first target clone group Al, so that they can be grown as adult plants (vegetative and flowering stage) in zone Al after cloning stage under the same (optimized) conditions. Observed clone groups C4, C5 are steered towards a second target clone group A2.

[0205] More in general, an objective of the clone recipe can be to steer clones from a first plurality of observed clone groups (e.g., C1-C5) to a second plurality of target clone groups (e.g., A1-A2) by optimizing the environmental conditions at every time step.

[0206] Optimizing the environmental conditions may comprise observing the clone’s response and error between estimated and actual (observed) clone groups. The first plurality may be larger than the second plurality; in other words, in general, the heterogeneity of the cutting that enter the clone growing stage (the input) is larger than that of the cloned plants leaving the clone growing stage (the output). As noted above, clones may be physically grouped such that clones with similar predicted growth trajectories or determined clone recipes are close2023PF80480

[0207] 28

[0208] together, as they will typically receive similar clone recipes. This initial grouping is typically based on the properties of the cutting, the properties of the mother plant, and / or the properties of the clipping process. If multiple clone recipes are determined for a single climate cell or other growing environment, a statistical representative of the multiple clone recipes may be used. In some cases, physical regrouping of the clones may be desired or even required.

[0209] The one or more target criteria (or farmer’s objective) may comprise a number of plants per target clone group. The target clone groups may be defined by target criteria corresponding to measurable parameters at the end of cloning phase, such as: number of plants per target clone group, average height of clones in a target clone group, average leaf area of clones in a target clone group, average vigor or stem thickness of clones in a target clone group, et cetera. The target clone groups may be based on various predicted outcomes, which may comprise a (projected) revenue per plant, e.g., produce weight, produce quality, et cetera, and / or a (projected) cultivation cost per plant or per generated revenue. These projected values may be based, e.g., on earlier growth cycles. For example, for cannabis, one or more of the following parameters may be included in the one or more target criteria: a number of plants, a fresh flower weight per harvested plant, a distribution of flower sizes (e.g., 50% large, 30 % medium, 20% small), or a total cultivation cost per gram of flower (e.g., US$3 per gram of fresh flower).

[0210] The clone-recipe algorithm may be implemented as a Markov Decision Process (MDP). The Markov Decision Process may be defined by a one or more decision parameters, e.g., a state space S defining a set of possible clones states s, an action space A defining a set of possible actions a, a probability mapping Pa(5, s') defining a probability that an action a applied to a clone in state 5 at time t results in a clone in state s' at time t + 1, and a reward function R«(5, s') defining a reward for an action a applied to a clone in state.s at time t resulting in a clone in state s' at time t + 1.

[0211] For example, the state space S may include one or more of the following (normalized) clone properties, observed at a time Z:

[0212] o a stem width sw E [0,1] (e.g., sw < 0.2 means thin, sw > 0.8 means thick) o a stem score ss E [0,1] (e.g., ss < 0.3 means herbaceous, ss > 0.7 means woody)

[0213] o a (normalized) internode length il E [0,1] (e.g., based on a cultivarspecific maximum internode length)

[0214] o a root score rs E [0,1] (e.g., rs < 0.2 - poor, rs < 0.8 - strong rooting)2023PF80480

[0215] 29

[0216] o a meristem score ms E [0,1] (e.g., 0 - dark green & no growth, 1 - light green & fast growth)

[0217] o a leaf score Is E [0,1] (e.g., 0 - dark green & small size & no growth, 1 - light green, large leaves & fast growth)

[0218] The state space S additionally comprises information associated with the cutting, comprising at least one of:

[0219] - one or more first environmental conditions of a mother plant of the cutting prior to obtaining the cutting from the mother plant, such as:

[0220] o radiant intensities applied to the mother plant in the week before the clipping ml, e.g., as a vector of radiation sources of different spectral intensity

[0221] o a photoperiod applied to the mother plant in the week before the clipping mp

[0222] o a relative humidity applied to the mother plant in the week before the clipping mh

[0223] o a soil temperature applied to the mother plant in the week before the clipping mts

[0224] o an air temperature applied to the mother plant in the week before the clipping mta

[0225] - one or more characteristics of the mother plant, such as:

[0226] o a mother health score mhs E [0,1] (e.g., 0 - very poor, 1 - best) o a mother vigor score mvs E [0,1] (e.g., 0 - very low, 1 - very high) o a (normalized) mother age ma E [0,1] (e.g., based on a cultivarspecific maximum age before removal)

[0227] o a (normalized) recency mcr (i.e., a (normalized) number of days since previous clipping)

[0228] o a cutting location mcl E [0,1] x [0,1] (e.g., vertical and radial distance from ground / main stem, normalized by mother plant dimensions) - one or more characteristics of a clipping process used to obtain the cutting from the mother plant and / or used to handle the cutting until the cutting is planted, such as:

[0229] o a (normalized) cutting length cl E [0,1]

[0230] o a (normalized) cutting leaf area cla E [0,1]

[0231] o a scissor cleanliness score scs E [0,1]2023PF80480

[0232] 30

[0233] o a relative amount of rooting hormone applied rh G [0, 1] o a presence of a cutting wound cw G {0,1}

[0234] o an angle of a cutting wound cwa E [0,1]

[0235] For example, the action space A may include one or more of the following actions and / or environmental conditions, applied between time t and t + 1:

[0236] o radiant intensities 1, e.g., as a vector of radiation sources of different spectral intensity (e.g., red, blue, white, infrared, etc.) o a photoperiod p

[0237] o a relative humidity h

[0238] o a soil temperature ts

[0239] o an air temperature ta

[0240] o a rate of water flow wf

[0241] o a rate of nutrients flow n

[0242] o a pest management treatment (e.g., using light such as UV light and / or chemicals)

[0243] o a (manual) trimming action

[0244] An objective of the Reinforcement Learning (RL) algorithm described above can be to learn an optimal policy 7i to select an action that maximizes an expected sum of discounted rewards from time t defined as

[0245] VK(s) = E ^Ytrt|So=s

[0246]

[0247] -t=0

[0248] where y is the discount rate, rtis the reward at step 1, and E represents an expectation value. The policy may be optimized using a model-free algorithm, such as Q-leaming.

[0249] In the example depicted in Fig. 5, the reward function can include a term that is proportional to a difference between an estimated number (and size) of observed clone groups (C1-C5) and a target number (and size) of target clone groups (e.g., Al, A2).

[0250] Table 1. Examples of defining clone states per observed clone group. In this example, the clones are distributed in five observed clone groups (C1-C5) as depicted in Fig. 6, with the clones in observed clone group Cl having the most desirable properties and the clones in observed clone group C5 having the least desirable properties. The state parameters have the meaning as described above.2023PF80480

[0251] 31

[0252] Clone Phenotypical Characteristics Current State Group and potential reason for phenotype Sz

[0253] Cl Such clones might be originating from cuttings taken from sw > 0.8

[0254] mothers that are at the peak of their growth cycle (vigor) and 0.4 < ss < 0.6 from top region of their canopy (i.e., distal end of plant) il > 0.5

[0255] rs > 0.8 ms >0.5 0.3 < Is < 0.7 C2 Clone may be harvested from mother plants at the peak of their sw > 0.6 growth cycle, producing high quality clones, but at lower 0.5 < ss < 0.7 regions of the canopy in shaded areas at lower light intensities. il > 0.6

[0256] rs > 0.7 ms > 0.4 0.2 < Is < 0.6 C3 Clones that need extra attention may be harvested from older sw > 0.5

[0257] mother plants whose shape was not maintained properly, grown 0.6 < ss < 0.8 too cold or too hot (i.e., suboptimal greenhouse conditions). The il > 0.6 clones may be too thin, woody, and / or not responding quickly in rs > 0.6 rooting environment. ms > 0.3

[0258] 0.2 < Is < 0.5 C4 The clones may be obtained from mother plants that are visually sw > 0.4

[0259] stressed; e.g., grown too cold / hot, irrigation cycles not optimal. 0.3 < ss < 0.8 The plants are not fertilized properly. Plant architecture is not il > 0.4 optimized for clone production, not well maintained. At this rs > 0.5 level, no pests or disease are detected, but the clones are less ms > 0.3 resilient and more sensitive to infection. Uneven clones. 0.2 < Is < 0.4 C5 Such clones may be obtained from old mothers plants that are, sw < 0.2

[0260] e.g., excessively branched out, under high pest pressure, under ss < 0.2 poor root health, grown in hot climates, or with less lighting. il < 0.2 The clones can also be a result of mistakes during the clipping rs < 0.2 process, e.g., using unclean razors, not applying rooting ms < 0.2 hormone properly, or using unclean / reused rooting trays Is < 0.3

[0261]

[0262] 2023PF80480

[0263] 32

[0264] Table 2. Example actions of an optimal policy based on current and previous states

[0265] # Prior observations state at t target state at t + 1 optimal action at t 1 Started in C5, responding C5 move towards C3 ts+, n-, h++, wf+.

[0266] well to previous actions, on

[0267] the verge of leaving C5

[0268] 2 Started at C4, dropped to C5 C5 move towards C3 ts +, n=, h+, wf+.

[0269] 3 Started at c3, dropped to C5 C5 move towards C3 stop treating, eliminate

[0270]

[0271] In the following, some examples of relations between mother plant and clone development are provided.

[0272] Genetic Traits: Each cutting taken from the mother plant is a genetic replicate. Hence, any desirable or undesirable traits (e.g., high yield vs. susceptibility to disease) of the mother plants are passed on to every clone of that mother plant. Such traits include growth patterns, metabolite (e.g., cannabinoid) profiles, and overall plant vigor.

[0273] Phenotypic inconsistency: If a mother plant has undergone environmental or stress-induced variations, the clones of that mother plant may inherit stress markers or epigenetic changes that can affect yield or growth consistency.

[0274] Mother plant health: A robust, pest-free mother plant produces healthier clones with higher success rates in rooting and development. Conversely, clones from stressed or diseased mothers may struggle to thrive.

[0275] Mother age and vigor: If the mother plant is excessively aged (often referred to as “senescent”), clones may root more slowly, have lower vigor, and produce lower yields. Conversely, a mother that is too young may not deliver consistent clone performance.

[0276] Mother vegetative vigor: High-vigor mother plants lead to healthier clones, which typically translates into higher yields once those clones are flowered.

[0277] Mother environmental Conditions: The environment in which the mother plant is kept, including factors like light, temperature, and humidity, impacts its health and the quality of clones taken from it. Optimal conditions promote the development of superior clones with the potential for higher yields.

[0278] From the above examples, it follows that by taking the properties of the mother plant into account, a better growth prediction can be made for the clones (compared to using only observable properties of the cuttings).

[0279] In the following, some examples of relations between the clipping process and clone development are provided.2023PF80480

[0280] 33

[0281] Cutting length: Cutting length decides how close the leaves will be to the clone lights on top of the canopy. If the cuttings are longer than optimal, then the plant is too close to the light source. If the cuttings are shorter, then the plant is too far from the light source. By grouping the cuttings based on their length, a variance in height within a single tray of clones can be reduced. After planting, the light intensity can be adapted based on the average height of the cuttings in a given tray. As cuttings from different (parts of) mother plants may grow at different rates, cuttings may be further grouped based on provenance, to ensure the clones in a tray or climate cell will remain of similar height. Alternatively, fastgrowing shorter cuttings may be combined with slow-growing longer cuttings, to ensure similar height at the end of the growing stage.

[0282] Cutting leaf area: Many growers prefer to cut edges of the leaves in the cutting. If the laborers cut the leaves too short, the resulting lower leaf area affects the clone’s ability to transpire. Moreover, the higher the leaf area, the lower the light intensity of the clone recipe should be. In the event where a clone’s leaves are cut too short, a light recipe may be adapted by increasing the light intensity proportional to the lost leaf area. Moreover, similar to the previous example, clones with a similar leaf area may still exhibit different development patterns due to other differences as described herein. These can be used as grouping criteria, or as compensation measures.

[0283] Cleanliness of the scissors used to clip the cutting: Growers are highly concerned about unclean scissor during the clipping process, as unclean scissors are known to introduce various diseases in the clones, such as Hop Latent Virus (HLV). During the clipping process, the scissors may be frequently cleaned. However, cleaning after each clipping may be too labor-intensive or time-consuming. Hence, a cutting that was clipped shortly before the cleaning process will have been clipped with less clean scissors than a cutting that was clipped soon after the cleaning process, and may hence me more prone to disease. It is noted that the cleanliness of the scissors cannot be observed from the cutting (or clone) itself.

[0284] In the following, some examples of relations between current and future second environmental conditions are provided.

[0285] Overwatering of clones: If a clone on a rockwool substrate is overwatered, water flow may be stopped and a next watering cycle may be delayed (e.g., no more water for 48 hours, instead of a daily or twice daily watering cycle). Additionally or alternatively, the block may be (manually) lifted to shake off excess water. If the clones are still transpiring, relative humidity may be reduced so that the clone’s transpiration rate is reduced, as this2023PF80480

[0286] 34

[0287] helps with drying out the clone. Furthermore, the temperature can be increased which will help with drying out the excess water.

[0288] Underwatering of clones: The water flow may be increased, the irrigation schedule may be adjusted (e.g., by increasing flow rate, flow duration, and / or watering cycle frequency). Additionally, the relative humidity may be increased and the temperature reduced to slow down clone growth until water intake returns to a normal (optimal) state.

[0289] Fig. 6 depicts a block diagram illustrating a data processing system as claimed in an embodiment. For example, data processing systems 100₁₋₃ may be implemented as a data processing system as described herewith.

[0290] As shown in Fig. 6, the data processing system 100 may include at least one processor 102 coupled to memory elements 104 through a system bus 106. As such, the data processing system may store program code within memory elements 104. Further, the processor 102 may execute the program code accessed from the memory elements 104 via a system bus 106. In one aspect, the data processing system may be implemented as a computer that is suitable for storing and / or executing program code. It should be appreciated, however, that the data processing system 100 may be implemented in the form of any system including a processor and a memory that is capable of performing the functions described within this specification.

[0291] The memory elements 104 may include one or more physical memory devices such as, for example, local memory 108 and one or more bulk storage devices 110. The local memory may refer to random access memory or other non-persistent memory device(s) generally used during actual execution of the program code. A bulk storage device may be implemented as a hard drive or other persistent data storage device. The processing system 100 may also include one or more cache memories (not shown) that provide temporary storage of at least some program code in order to reduce the number of times program code must be retrieved from the bulk storage device 110 during execution.

[0292] Input / output (I / O) devices depicted as an input device 112 and an output device 114 optionally can be coupled to the data processing system. Examples of input devices may include, but are not limited to, a keyboard, a pointing device such as a mouse, a touch-sensitive display, an external control system referred to herein, or the like. Examples of output devices may include, but are not limited to, a monitor or a display, speakers, the LED driver, or the like. Input and / or output devices may be coupled to the data processing system either directly or through intervening I / O controllers.2023PF80480

[0293] 35

[0294] In an embodiment, the input and the output devices may be implemented as a combined input / output device (illustrated in Fig. 6 with a dashed line surrounding the input device 112 and the output device 114). An example of such a combined device is a touch sensitive display, also sometimes referred to as a “touch screen display” or simply “touch screen”. In such an embodiment, input to the device may be provided by a movement of a physical object, such as, e.g., a stylus or a finger of a user, on or near the touch screen display.

[0295] A network adapter 116 may also be coupled to the data processing system to enable it to become coupled to other systems, computer systems, remote network devices, and / or remote storage devices through intervening private or public networks. The network adapter may comprise a data receiver for receiving data that is transmitted by said systems, devices and / or networks to the data processing system 100, and a data transmitter for transmitting data from the data processing system 100 to said systems, devices and / or networks. Modems, cable modems, and Ethernet cards are examples of different types of network adapter that may be used with the data processing system 100.

[0296] As pictured in Fig. 6, the memory elements 104 may store an application 118. In various embodiments, the application 118 may be stored in the local memory 108, the one or more bulk storage devices 110, or apart from the local memory and the bulk storage devices. It should be appreciated that the data processing system 100 may further execute an operating system (not shown in Fig. 6) that can facilitate execution of the application 118. The application 118, being implemented in the form of executable program code, can be executed by the data processing system 100, e.g., by the processor 102. Responsive to executing the application, the data processing system 100 may be configured to perform one or more operations or method steps described herein.

[0297] In one aspect of the present invention, the data processing system 100 may represent a control system of an irradiation system, e.g., a LED driver, as described herein.

[0298] In another aspect, the data processing system 100 may represent a client data processing system. In that case, the application 118 may represent a client application that, when executed, configures the data processing system 100 to perform the various functions described herein with reference to a “client”. Examples of a client can include, but are not limited to, a personal computer, a portable computer, a mobile phone, or the like.

[0299] In yet another aspect, the data processing system 100 may represent a server. For example, the data processing system may represent an (HTTP) server, in which case the2023PF80480

[0300] 36

[0301] application 118, when executed, may configure the data processing system to perform (HTTP) server operations.

[0302] Various embodiments of the invention may be implemented as a program product for use with a computer system, where the program(s) of the program product define functions of the embodiments (including the methods described herein). In one embodiment, the program(s) can be contained on a variety of non-transitory computer-readable storage media, where, as used herein, the expression “non-transitory computer readable storage media” comprises all computer-readable media, with the sole exception being a transitory, propagating signal. In another embodiment, the program(s) can be contained on a variety of transitory computer-readable storage media. Illustrative computer-readable storage media include, but are not limited to: (i) non-writable storage media (e.g., read-only memory devices within a computer such as CD-ROM disks readable by a CD-ROM drive, ROM chips or any type of solid-state non-volatile semiconductor memory) on which information is permanently stored; and (ii) writable storage media (e.g., flash memory, floppy disks within a diskette drive or hard-disk drive or any type of solid-state random-access semiconductor memory) on which alterable information is stored. The computer program may be run on the processor 102 described herein.

[0303] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0304] The corresponding structures, materials, acts, and equivalents of all means or step plus function elements in the claims below are intended to include any structure, material, or act for performing the function in combination with other claimed elements as specifically claimed. The description of embodiments of the present invention has been presented for purposes of illustration, but is not intended to be exhaustive or limited to the implementations in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the present invention. The embodiments were chosen and described in order to best explain the principles and some practical applications of the present invention, and to enable others of2023PF80480

[0305] 37

[0306] ordinary skill in the art to understand the present invention for various embodiments with various modifications as are suited to the particular use contemplated.

Claims

2023PF8048038CLAIMS1. A data processing system (100₂) for determining an environmental condition for treatment or growing of a cutting (21) from a mother plant (11), the data processing system (100₂) comprising a memory storing computer-readable instructions, at least one communication interface, and at least one processor, the at least one processor being configured to, in response to executing the computer-readable instructions:receive, via the at least one communication interface, information associated with a cutting (21), the information associated with the cutting (21) comprising at least one of:- one or more first environmental conditions of a mother plant (11) of the cutting (21) prior to obtaining the cutting (21) from the mother plant (11), - one or more characteristics of the mother plant (11),- one or more characteristics of a clipping process (20) used to obtain the cutting (21) from the mother plant (11) and / or used to handle the cutting (21) until the cutting (21) is planted; anddetermine one or more second environmental conditions for treatment or growing of the cutting (21) or a clone (29₁,₂) obtained from the cutting (21) based on at least the information associated with the cutting (21).

2. The data processing system as claimed in claim 1, wherein the at least one processor is further configured to determine and transmit, via the at least one communication interface, one or more control commands to an environmental installation, the one or more control commands configuring the environmental installation to apply the determined one or more second environmental conditions to the cutting (21).

3. The data processing system as claimed in claim 1, wherein the at least one processor is further configured to output the determined one or more second environmental conditions and / or a recommendation based on the determined one or more second environmental conditions to a user using the communication interface.2023PF80480394. The data processing system as claimed in any one of the preceding claims, where the cutting (21) is of the genus Cannabis.

5. The data processing system as claimed in any one of the preceding claims, wherein the first and / or second environmental conditions comprise one or more of: a substrate temperature, a substrate humidity, a substrate pH, a substrate texture, a substrate water retention capability, an air temperature, an air humidity, a CO2level, a nutrient flow, irrigation properties, or a radiation recipe.

6. The data processing system as claimed in claim 5, wherein the first and / or second environmental conditions comprise the radiation recipe, and wherein the radiation recipe defines one or more of:- a radiant intensity or photon flux of radiation as emitted by an irradiation system,- an irradiance or photon flux density of the radiation as received from the irradiation system by, respectively, the mother plant (11) or the clone (29₁,₂) obtained from the cutting (21),- a spectral intensity or spectral power distribution of the radiation generated by the irradiation system,- a spatial distribution of the radiation emitted by the irradiation system, and- a timing of the irradiation from the irradiation system.

7. The data processing system as claimed in any one of the preceding claims, wherein the one or more first environmental conditions of the mother plant (11) prior to obtaining the cutting (21) from the mother plant (11) comprise a time-series of the first environmental conditions.

8. The data processing system as claimed in any one of the preceding claims, wherein the one or more characteristics of the mother plant (11) comprise at least one of: a location of the mother plant (11) in a growing environment, a location of the cutting (21) on the mother plant (11), a position and / or an orientation of the cutting (21) relative to the mother plant (11), an age of the mother plant (11), a species of the mother plant (11), a2023PF8048040morphology of the mother plant (11), a health status of the mother plant (11), or a number of days since a previous cutting from the mother plant (11).

9. The data processing system as claimed in any one of the preceding claims, wherein the one or more characteristics of the clipping process (20) used to obtain the cutting (21) from the mother plant (11) comprise at least one of: information regarding wounding of the cutting (21), wound properties of a wound applied during the clipping process (20), information regarding leaf trimming, information regarding application of rooting hormones to the cutting (21), an angle of clipping (20), a type of a cutting implement used for the clipping, a sharpness of the cutting implement, a cleanliness of cutting implement.

10. The data processing system as claimed in any one of the preceding claims, wherein determining one or more second environmental conditions comprises: providing the information associated with the cutting (21) to an input of a machine-learning model and receiving from the machine-learning model an inference on the one or more second environmental conditions, the machine-learning model being trained to determine the one or more second environmental conditions in response to receiving the information associated with the cutting (21).

11. The data processing system as claimed in claim 10, wherein the machine-learning model comprises a first algorithm trained to predict, in response to receiving the information associated with the cutting (21), a growth trajectory for the clone (291,2) obtained from the cutting (21) in dependence on a set of parameters representing the one or more second environmental conditions, and a second algorithm to select optimized parameters representing the one or more second environmental conditions based on the first algorithm and a target growth or target metabolite profile.

12. An irradiation system comprising one or more controllable radiation sources and a data processing system as claimed in any one of claims 1-11, wherein the second environmental conditions comprise a radiation recipe, and wherein the data processing system is configured to control the one or more controllable radiation sources according to the radiation recipe.

13. A computer-implemented method comprising:2023PF8048041receiving information associated with a cutting (21) of a mother plant (11), the information associated with the cutting (21) comprising at least one of:- one or more first environmental conditions of the mother plant (11) of the cutting (21) prior to obtaining the cutting (21) from the mother plant (11);- one or more characteristics of the mother plant (11),- one or more characteristics of a clipping process (20) used to obtain the cutting (21) from the mother plant (11); anddetermining one or more second environmental conditions for the cutting (21) or for a clone (29₁,₂) obtained from the cutting (21) based on at least the information associated with the cutting (21).

14. A computer program comprising instructions which, when executed by a data processing system (100) of a system as claimed in one of claims 1 to 11, causes the system to perform the method as claimed in claim 13.

15. A computer-readable storage medium having stored thereon a computer program as claimed in claim 14.

Images