Method for improving plant treatment

Abstract

The present disclosure relates to systems and methods for improving crop treatment efficiency and efficacy and testing crop treatment using genetically engineered sensor plants.

Description

Cross-references to related applications

[0001] This application claims priority to U.S. Provisional Application No. 63 / 530,186, filed August 1, 2023, pursuant to 35 USC § 119(e). The contents of that application are incorporated herein by reference in their entirety. introduction

[0002] Plant stressors include both biotic and abiotic stressors. Biotic stressors can include, but are not limited to, insects, bacteria, viruses, fungi, and other plants, while abiotic stressors include, but are not limited to, environmental factors such as water, temperature, wind, nutrient deficiency, and salinity. (Mosa K et al.) Plant Stress Tolerance , (2017) doi:10.1007 / 978-3-319-59379-1_1. These stressors can also include chemical stressors, which arise from the application of various treatments associated with the stressor. While plants may be able to adapt to certain stressors, stressors can limit plant growth and also lead to plant death. Therefore, if plants are grown as crops, properly addressing stressors in plants is key to ensuring optimal plant health and yield.

[0003] Genetically engineered plants (i.e., plants with edited genes) possess improved resistance to pathogens, stressors, and diseases, while allowing farmers to increase overall crop yields and efficiency. However, genetically engineered plants still require the application of various treatments (e.g., herbicides, insecticides, fungicides, etc.) to adequately protect them from stressors. The widespread, indiscriminate application of treatments against a wide range of plant diseases and pathogens, promoting plant health, has adverse environmental effects and leads to increased resistance and / or tolerance to these treatments. Therefore, there is a need for more selective screening of plants requiring treatment and / or more selective application of treatments to plants in agricultural settings. Furthermore, the efficacy of new and old treatments applied to address specific plant diseases, pathogens, or stressors needs to be tested and analyzed. Overview

[0004] In some embodiments, this disclosure provides a method for reducing excessive exposure of agricultural environments to chemical plant treatments, comprising: (a) capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to produce signals in response to stressors; (b) detecting stress-responsive signals in the spectral images of the sensor plants; and (c) selectively applying stress-targeting chemical treatments to a subgroup of plants in the agricultural environment based on the detected signals.

[0005] In some embodiments, this disclosure provides a method for improving plant treatment efficiency, comprising: (a) capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to produce signals in response to a stressor; (b) detecting the stressor-responsive signals in the spectral images of the sensor plants; and (c) selectively applying stressor-targeting treatments to a subgroup of plants in the agricultural environment based on the detected signals.

[0006] In some embodiments, this disclosure provides a method for screening plants to be treated, comprising: (a) capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to produce signals in response to a stressor; (b) detecting the stressor-responsive signals in the spectral images of the sensor plants; and (c) selecting a subgroup of plants in the agricultural environment for treatment based on the detected signals, wherein the treatment is achieved by targeting the stressor with chemicals.

[0007] In some embodiments, this disclosure provides a method for testing the efficacy of a treatment on plants, comprising: (a) applying a stressor to one or more sensor plants in an agricultural environment, wherein the sensor plants have been genetically engineered to produce a signal in response to the stressor; (b) capturing a spectral image of the sensor plants in the agricultural environment; (c) detecting the stressor-responsive signal in the spectral image of the sensor plants; (d) selectively applying the treatment to the plants in the agricultural environment based on the detected signal; and (e) recording changes in the signal after the treatment has been applied.

[0008] In some embodiments, this disclosure provides a method for testing the efficacy of a treatment on plants, comprising: (a) capturing a spectral image of a sensor plant in an agricultural environment, wherein the sensor plant has been genetically engineered to produce a signal in response to a stressor; (b) detecting the stressor-responsive signal in the spectral image of the sensor plant; (c) selectively applying the treatment to the plant in the agricultural environment based on the detected signal; and (d) recording changes in the signal after the treatment has been applied.

[0009] In some embodiments, the sensor plant described herein is a dicotyledonous plant. In some embodiments, the sensor plant described herein is a monocotyledonous plant. Brief description of the attached diagram

[0010] Figure 1 The illustration shows a graphical representation of the sensor plant and the system method for detecting the sensor plant.

[0011] Figure 2 The illustration shows a graphical representation of the sensor plant and the system method for detecting the sensor plant.

[0012] Figures 3A-3C The use of drought stress sensors in tomato plants is described. Figure 3A The fluorescence signals from a drought-sensor plant that was fully watered (left) and a control plant that was fully watered and always constitutively expressed red fluorescent protein (right) are depicted. Figure 3B Fluorescence signals from drought sensor plants (left) and drought control plants (right) that always express red fluorescent protein during drought are depicted. Figure 3C The changes in fluorescence signals from exemplary unmodified tomato plants (M82), drought sensor plants (V298-27-8), and plants that always constitutively express fluorescent protein (DsRed) are shown during drought experiments.

[0013] Figure 4A and Figure 4B The application of fungal stress sensors in soybean plants is shown. Figure 4A Exposure to Cercospora ( Cercospora Visible disease symptoms occur in soybean plants containing spores, and Figure 4B The induction of fluorescent signals in fungal sensor plants after exposure to Cercospora spores is shown. Detailed description

[0014] As used herein, "sensor plant" refers to a plant configured to detect the presence of a specific stressor or set of stressors inside and / or at the site of a plant. Sensor plants can be genetically engineered to include a set of promoter-reporter pairs (e.g., one promoter-reporter pair, three promoter-reporter pairs) configured to trigger the sensor plant to generate one or more detectable signals in the presence of a specific stressor or set of stressors. For example, a sensor plant can be genetically engineered to include a first promoter-reporter pair configured to trigger the sensor plant to generate a red fluorescent signal in the presence of fungi. Thus, the sensor plant can generate a detectable signal that, when detected, alerts a user associated with the sensor plant (e.g., a farmer, agronomist, botanist) to the presence of one or more stressors. Furthermore, sensor plants of a first plant type can be configured to detect the presence of stressors in a first type and / or different types of plants. For example, a sensor maize plant can be configured to detect the presence of stressors in maize plants. In another example, a sensor tomato plant can be configured to display the presence of stressors in potato plants.

[0015] As used herein, “stressor” refers to an abiotic and / or biotic stress that may negatively impact plant health, such as pests, diseases, chemicals, water, heat, and / or nutrient stress or deficiency. For example, plants may experience insect stress corresponding to the presence of insects or insect colonies at the plant's location, which may hinder plant growth and / or health.

[0016] As used herein, “stress” refers to the measurable and / or detectable presence of a specific stressor and / or a group of stressors in a plant (e.g., stressors present in sensor plants, sensor plant clusters, sensor plant crops (e.g., fields planted with sensor plants), agricultural environments containing sensor plants, etc.). For example, a computer system can detect insect stressors at a sensor plant cluster and estimate the insect stress at that cluster (e.g., measurable presence, distribution, amplitude) based on features extracted from an image of the sensor plant cluster. Thus, stress represents the measurable presence of a specific stressor.

[0017] As used herein, "pressure gradient" refers to the distribution of stress (or multiple stressors) across multiple sensor plants and / or groups (or clusters) of sensor plants in an agricultural environment. For example, a user may initially distribute three groups of sensor plants within an agricultural environment. Later, a computer system may acquire images of the agricultural environment depicting the three groups of sensor plants, recorded by aerial sensors (e.g., satellites). Based on features extracted from regions depicting each group of sensor plants, the computer system can interpret the stress gradient of the stressors in the agricultural environment. More specifically, the computer system may: interpret a first stress of the stressors in the first group of sensor plants based on features extracted from a first region of an image depicting the first group of sensor plants; interpret a second stress of the stressors in the second group of sensor plants based on features extracted from a second region of an image depicting the second group of sensor plants; interpret a third stress of the stressors in the third group of sensor plants based on features extracted from a third region of an image depicting the third group of sensor plants; and interpret a stress gradient of the stressors in the agricultural environment based on the first, second, and third stresses. Based on this stress gradient, the computer system may (e.g., via interpolation) interpret the stress of the stressors at various locations within the agricultural environment.

[0018] As used herein, “user” refers to a person associated with an agricultural environment containing sensor plants. The term “agricultural environment” includes, but is not limited to, farmland, plant crops, greenhouses, botanical gardens, laboratories, and / or other areas where plants can grow. For example, a user may refer to a farmer associated with a particular agricultural environment. In another instance, a user may refer to an agronomist associated with a particular plant crop. In yet another instance, a user may refer to a scientist who studies or develops treatments for stress in sensor plants and / or both sensor and non-sensor plants.

[0019] The following description of embodiments of the present invention is not intended to limit the invention to these embodiments, but rather to enable those skilled in the art to make and use the invention. The variations, configurations, implementations, exemplary embodiments, and instances described herein are optional and not limited to them. The invention described herein can include any and all permutations of these variations, configurations, implementations, exemplary embodiments, and instances.

[0020] Sensor plants This disclosure includes genetically engineered sensor plants that generate detectable signals in response to stressors. In some embodiments, to generate sensor plants, plant cells can be genetically engineered to couple a known reporter gene to certain biological processes. Molecular genetic techniques (e.g., gene or genome editing) can be implemented to associate the expression of the reporter gene with certain abiotic and / or biotic stresses and traits. Thus, the reporter gene can act as a signal for abiotic and / or biotic stresses or traits in plant cells. For example, sensor plants can be modified to fluoresce (i.e., absorb photons of one frequency and emit photons of a different frequency) in the presence of disease or stress (and in proportion to the disease or stress), exhibit changes in pigmentation (i.e., produce pigment proteins that cause phenotypic changes in plant cells), or generate another detectable signal (e.g., heat). In this example, the sensor plant can be modified to fluoresce in the presence of one or more diseases or stressors (such as fungi, bacteria, nematodes, parasites, viruses, insects, chemicals, heat, competing plant species, water stress, nutrient stress, phytoplasmic diseases, etc.). In another example, the sensor plant can be modified to indicate the presence of a stressor via bioluminescence. In yet another example, the sensor plant can be modified to indicate the presence of a stressor via changes in pigmentation. In yet another example, the plant can be modified to indicate the presence of a stressor via the release of heat.

[0021] The sensor plant described herein can be any plant capable of being genetically engineered, including but not limited to soybean (soybean) (soybean) Glycine max )), cotton (species of the genus Gossypium ( Gossypium species), corn (corn) (corn ( Zea mays ()), Canola (European rapeseed ()) Brassica napusIn some embodiments, the sensor plant is a dicotyledonous plant. In some embodiments, the sensor plant is a monocotyledonous plant. Methods for genetically engineering plant cells are known to those skilled in the art, and sensor plants can be produced using any acceptable genetic engineering method compatible with a given plant species (e.g., gene or genome editing).

[0022] Plant cells can be genetically engineered (e.g., through gene or genome editing) to contain promoter and reporter pairs that indicate the presence of certain stressors in a plant or plant crop. A promoter contains a genetic regulatory element that drives the expression of mRNA at a specific time and place, which is then translated into a functional protein. Promoter activity represents a natural biological process that occurs when a specific stress is present in the plant. To detect the presence of these stressors, a known reporter gene expressing a certain signal can be coupled to a selected promoter. Thus, when a plant cell expresses a promoter associated with a certain stressor, the reporter gene tagged on the promoter is also expressed and is therefore detectable. Some reporter signals (e.g., fluorescent signals, pigments, etc.) are naturally present in plants without genetic modification. These signals can be enhanced through selective breeding, gene or genome editing, novel breeding techniques, and / or other plant selection techniques. Each of these reporter genes can produce an optical signal distinguishable from the plant itself. Combinations of reporter genes can also be used to indicate a variety of plant stressors present in a plant or crop. In some implementations, the generation of promoter-reporter pairs and stress-responsive signals does not interfere with the function of other genes in the plant.

[0023] In some implementations, the sensor plants described herein are plants that have already grown and can be transplanted into agricultural environments for continued growth and monitoring.

[0024] As described herein, the sensor plant includes a first promoter-reporter pair, the first promoter-reporter pair including: a first promoter activated in the presence of a first stressor at the sensor plant; and a first reporter coupled to the first promoter and configured to exhibit a detectable first signal (e.g., a signal in the electromagnetic spectrum) in response to activation of the first promoter by the first stressor.

[0025] In the implementation, the sensor plant described herein also includes a second promoter-reporter pair comprising: a second promoter activated in the presence of a second stressor at the sensor plant; and a second reporter coupled to the second promoter and configured to exhibit a detectable second signal (e.g., a signal in the electromagnetic spectrum) in response to activation of the first promoter by the second stressor, the second signal being different from the first signal.

[0026] In some embodiments, the sensor plant described herein also includes a third promoter activated in the presence of a third stressor at the sensor plant, and a third reporter coupled to the third promoter and configured to exhibit a detectable third signal (e.g., a signal in the electromagnetic spectrum) in response to activation of the third promoter by the third stressor, the third signal being distinct from the first and second signals.

[0027] In some embodiments, the sensor plant described herein also includes a fourth promoter activated in the presence of a fourth stressor at the sensor plant, and a fourth reporter coupled to the fourth promoter and configured to exhibit a detectable fourth signal (e.g., a signal in the electromagnetic spectrum) in response to activation of the fourth promoter by the fourth stressor, the fourth signal being distinct from the first, second, and third signals.

[0028] In some embodiments, the sensor plant described herein also includes a fifth promoter activated in the presence of a fifth stressor at the sensor plant, and a fifth reporter coupled to the fifth promoter and configured to exhibit a detectable fifth signal (e.g., a signal in the electromagnetic spectrum) in response to activation of the fifth promoter by the fifth stressor, the fifth signal being distinct from the first, second, third, and fourth signals.

[0029] In some embodiments, the sensor plant described herein also includes a sixth promoter activated in the presence of a sixth stressor at the sensor plant, and a sixth reporter coupled to the sixth promoter and configured to exhibit a detectable sixth signal (e.g., a signal in the electromagnetic spectrum) in response to activation of the sixth promoter by the sixth stressor, the sixth signal being distinct from the first, second, third, fourth, and fifth signals.

[0030] Figure 1 A graphical representation of a sensor plant, as described herein, is provided, wherein the sensor plant comprises one or more promoter-reporter pairs. An optical sensor monitors the sensor plant and captures images of the plant and any signals generated by the sensor plant via the promoter-reporter pairs. The collected images can be compared to a stored model in a computer system to identify the presence of a specific stressor, and the identification of the stressor can automatically trigger the generation of a specific cue for the user (e.g., a cue to apply an insecticide in response to the detection of a signal responsive to an insect stressor).

[0031] In some embodiments, the sensor plant described herein includes a first promoter-reporter pair, the first promoter-reporter pair comprising: a first promoter configured to activate in the presence of a first stressor within a first amplitude range at the sensor plant; and a first reporter coupled to the first promoter and configured to exhibit a first signal in the electromagnetic spectrum in response to activation of the first promoter by the first stressor. In this variant, the sensor plant further includes a second promoter-reporter pair, the second promoter-reporter pair comprising: a second promoter configured to activate in the presence of a second stressor within a second amplitude range greater than the first amplitude range at the sensor plant; and a second reporter coupled to the second promoter and configured to exhibit a second signal in the electromagnetic spectrum in response to activation of the second promoter by the second stressor.

[0032] In some embodiments, the sensor plant described herein includes: a first promoter that is activated at a first time and lasts for a first duration in response to the presence of a first stressor in the sensor plant; a second promoter that is activated at a second time and lasts for a second duration in response to the presence of the first stressor in the sensor plant, the second time being after the first time and before the termination of the first duration; and a reporter coupled to the first and second promoters that, in response to activation of the first promoter, exhibits a first signal for detecting the first stressor during the first duration; and, in response to activation of the second promoter, exhibits a second signal for detecting the first stressor during the second duration.

[0033] In this implementation, multiple promoters can be labeled onto a reporter, causing the sensor plant to output a signal for a specific stressor over an extended period. For example, a set of three promoters linked to fungal stress can be labeled with a red fluorescent protein reporter. Initially, the presence of the first promoter triggers red fluorescent protein expression in response to fungal stress. At a second time, as the signal generated by the first promoter decreases, the presence of the second promoter triggers sustained red fluorescence expression. And again, at a third time, the third promoter triggers red fluorescence expression in the plant. Therefore, genetic engineering techniques can be implemented to string together multiple promoter sequences and label this string with a reporter gene to identify which promoter sequences are expressed in the plant, thereby expanding the detection window.

[0034] In some embodiments, plant cells can be genetically engineered to include combined reporter-promoter pairs that present different signals in response to different stressors and / or pressures (e.g., promoter-promoter pairs indicating the presence of more than one type of stressor). In some embodiments, combined reporter-promoter pairs include, but are not limited to, promoter-promoter pairs that detect fungi, bacteria, nematodes, parasites, viruses, insects, chemicals, heat, water stress, nutrient stress, phytoplasmic diseases, and combinations thereof. The computer system can distinguish the different signals generated by the combined promoter-promoter pairs and detect when such signals are generated by the sensor plant. The computer system can further utilize models to interpret these signals, including deriving more information than the sum of the reporter pairs, such as: the type of fungus and the presence of fungal stress; or the ratio of water stress to heat stress.

[0035] In some embodiments, the sensor plant can be configured to include a first number of promoters and a second number of reporters less than the first number of promoters. For example, expression of red fluorescent protein can indicate the presence of water stress, and expression of yellow fluorescent protein can indicate the presence of thermal stress. However, expression of both red and yellow fluorescent proteins can indicate the presence of both water stress and thermal stress, or a third stress, such as insect stress. Therefore, the fluorescence of the sensor plant can be combined with knowledge of disease frequency, common disease location, and common disease timing to isolate specific plant stressors present in the agricultural environment. In some embodiments, the first, second, and third fluorescent compounds are each coupled to the first, second, and third biological processes, respectively. In some embodiments, a fourth biological process is coupled to the first and second fluorescent compounds; a fifth biological process is coupled to the second and third fluorescent compounds; a sixth biological process is coupled to the first and third fluorescent compounds; and a seventh biological process is coupled to the first, second, and third fluorescent compounds. In this implementation, the detection of all three fluorescent compounds in the plant can reveal each of the following: activation of a sixth biological process; activation of the first, second, and third biological processes; activation of the first and fifth biological processes; activation of the fourth and third biological processes; and activation of the sixth and second biological processes. These biological processes can be distinguished to enable the detection of different processes occurring in these plant cells, and thus to detect different stressors present in the plant. For example, a computer system can prompt crop managers to treat all possible diseases or specific diseases that could be catastrophic if not treated promptly. In another instance, a farmer or agronomist can retrieve samples from the plant and test for each possible disease to initiate appropriate action procedures. Furthermore, by selectively identifying the presence of one or more specific stressors, treatment applications (including chemical treatments) can be selectively applied to limit overexposure to treatments that may have negative environmental impacts (e.g., chemical runoff, unwanted greenhouse gas releases, tolerance to treatments, etc.) that could ultimately affect plant health, including crop yield.

[0036] In some implementations, the promoter and reporter pair can be implemented by tagging a reporter to a promoter. For example, if a red fluorescent protein is tagged to a promoter sequence indicating fungal stress in a sensor plant, then the promoter sequence, and therefore the red fluorescent protein, can be expressed in the plant cell when fungal infection in the plant cell rises above a minimum fungal stress threshold. Similarly, if an anthocyanin protein is tagged to a promoter sequence indicating insect stress in a sensor plant, then the promoter sequence, and therefore the anthocyanin, can be expressed in the plant cell when insect stress rises above a minimum insect stress threshold.

[0037] In some implementations, each sensor plant type for a particular crop is configured to generate a signal in response to a plant stressor; that is, a sensor plant type includes a promoter-reporter pair configured to generate a signal for a type of stressor. For example, a first sensor plant type for a particular crop (e.g., maize) includes a promoter-reporter pair configured to output a signal in response to fungal stress; and a second sensor plant type for the same particular crop includes a different promoter-reporter pair configured to output a signal in response to insect stress.

[0038] In some implementations, promoter-reporter pairs configured to output signals in response to multiple different stressors are integrated into a sensor plant type for a specific crop. For example, a sensor plant type for a specific crop includes promoter-reporter pairs configured to produce: a luminescent signal in response to fungal stress; a pigmentary change in response to insect stress; and a red fluorescent signal in response to phosphorus deficiency. Therefore, a plant or cluster of plants of this sensor plant type can be sensed to detect multiple discrete stresses.

[0039] Detection system In the detection system described herein, a computer system (e.g., a local computing device, a remote server, a computer network) identifies stressors present at the sensor plant based on signals (e.g., fluorescence signals emitted in the electromagnetic spectrum) generated by the sensor plant and captured in spectral images taken by an optical sensor, wherein the sensor plant has been genetically engineered to display environmental conditions unfavorable to plant health or growth (i.e., abiotic and / or biotic stressors). In some embodiments, the computer system extracts features (e.g., intensities corresponding to specific wavelengths of specific components, such as proteins) from the spectral images and interprets the presence and / or magnitude of specific stressors exposed to the sensor plant based on these features. In some embodiments, the computer system interprets the detected signals based on a stored model that associates plant stressors with wavelengths of interest based on known features of promoters and reporter genes in the sensor plant—and before such stressors are visually distinguishable in the visible spectrum (i.e., with the human eye). In some embodiments, the computer system interprets the presence and / or magnitude of stressors at the sensor plant and / or other nearby plants based on signals generated by the sensor plant. Then, based on the signals detected in the spectral images captured by the optical sensors, the computer system selectively generates and distributes cues to the user to alleviate stress at the sensor plant and / or nearby plants.

[0040] In the detection system described herein, optical sensors (e.g., multispectral or hyperspectral cameras, spectrometers, etc.) capture spectral images of the agricultural environment. In some embodiments, the optical sensors are fixed. In some embodiments, one or more fixed optical sensors are attached to poles within the agricultural environment, allowing the optical sensors to collect images of sensor plants within the agricultural environment, such as hourly or daily, and upload these images (e.g., via a computer network) to a computer system. In some embodiments, the optical sensors are mobile. In some embodiments, one or more mobile optical sensors are attached to trucks, tractors, or other agricultural implements, which can intermittently capture images of these sensor plant clusters as they travel along a path through the agricultural environment, such as multiple times a day, or during spraying or other value-added operations. In some embodiments, mobile optical sensors are attached to aircraft, helicopters, drones, satellites, or other aerial equipment. In some embodiments, the optical sensors used in the detection system described herein include fixed optical sensors, mobile optical sensors, and combinations thereof, allowing more than one optical sensor to be used to capture spectral images of sensor plants within the agricultural environment.

[0041] In some embodiments, one or more optical sensors capture spectral images of sensor plants at different frequencies and locations within an agricultural environment to achieve greater spatial resolution. In some embodiments, as the optical sensors capture spectral images of sensor plants within the agricultural environment, additional data is recorded and correlated with the images. In some embodiments, GPS data associated with the optical sensors and / or the imaged sensor plants, date and time, weather, and other conditions is recorded and correlated with the corresponding images. Therefore, if a particular sensor plant generates a signal in response to a stressor, the computer system can provide the environmental conditions and precise location (e.g., coordinates) of that particular sensor plant.

[0042] In some embodiments, the computer system extracts the amplitude (e.g., intensity) of the wavelengths of sensor plant reporting signals from spectral images collected by one or more optical sensors. In some embodiments, the computer system implements a stored model to interpret the stress (e.g., presence and / or amplitude) of a particular stressor over time in an agricultural environment based on the amplitude of the extracted wavelengths associated with that particular stressor.

[0043] In some embodiments, spectral images are collected intermittently and inconsistently (e.g., at lower temporal resolution) by one or more optical sensors. In some embodiments, spectral images are collected consistently (e.g., at greater temporal resolution) by one or more optical sensors. In some embodiments, images are collected hourly, daily, every other day, every half week, weekly, every two weeks, and / or monthly. In some embodiments, the computer system combines data extracted from intermittent and inconsistent images recorded by optical sensors with consistent data extracted from images recorded by optical sensors in agricultural settings to extend stress prediction across crops. Furthermore, the computer system can converge to more accurate models for predicting stress across crops over time based on data extracted from these images, such as by incorporating machine learning algorithms.

[0044] Detection methods In the method using the detection system described herein, a computer system can detect and interpret signals generated by sensor plants by extracting features related to the presence of specific stressors at the sensor plants from images of sensor plants in an agricultural environment.

[0045] In some embodiments, the computer system acquires digital images (e.g., spectral images) of the sensor plant, the agricultural environment, and / or the plant canopy (e.g., the sensor plant and surrounding plants) captured by optical sensors deployed at the sensor plant and / or the plant canopy. In some embodiments, the optical sensor may include: an optomechanical fore optic capable of measuring fluorescence and non-fluorescent targets; and a digital spectrometer or digital camera that records images through the optomechanical fore optic. Thus, the computer system can acquire images recorded by the optical sensor and process these images according to the methods described herein to detect reporting signals and interpret stressors present in the plants. More specifically, the computer system may: acquire images (e.g., spectra) of the sensor plant recorded by the optical sensor (e.g., a digital spectrometer); extract wavelengths of compounds of interest from these images; and identify stressors present at the sensor plant based on these wavelengths.

[0046] In some implementations, the computer system acquires images of the sensor plant captured by an optical sensor, such as from a handheld camera, a handheld spectrometer, a mobile phone, a satellite, or any other device including a high-resolution spectrometer, including a specific band filter, or otherwise configured to detect electromagnetic radiation fluorescence, the wavelength of emission, or changes in the wavelength of visible light produced by the sensor plant in the presence of a specific stressor.

[0047] In some embodiments, the computer system employs different instruments depending on the compound of interest, because different compounds are best observed at different wavelengths under different conditions and may require different detection modes. In some embodiments, the computer system acquires images of sensor plants captured by a handheld spectrometer, the sensor plants being configured to emit fluorescence signals (e.g., red fluorescence) in the presence of a stressor; and acquires images of sensor plants captured by a handheld camera, the sensor plants being configured to exhibit changes in pigmentation (production of anthocyanin pigment proteins) in the presence of a stressor.

[0048] In some implementations, the computer system acquires images of the sensor plant collected at specific times and / or time intervals throughout the day to maximize the detectability of signals generated by the sensor plant. For example, for a sensor plant configured to generate a bioluminescent signal in the presence of one or more specific stressors, the computer system may acquire images of the sensor plant collected at night, when other signals generated by the sensor plant and its surroundings are minimized.

[0049] The computer system described herein can detect and interpret stress in sensor plants via active and / or passive detection modes. In some embodiments, the computer system implements passive detection to detect signals generated by the sensor plant in the presence of one or more stressors without stimulating the sensor plant. In some embodiments, the computer system implements active detection to detect signals generated by the sensor plant in response to stimulation (e.g., via external illumination) in the presence of one or more stressors. In some embodiments, the computer system implements a detection method in which the sensor plant is irradiated with oscillating light for stimulation, such that the response to the irradiation can be isolated.

[0050] In some implementations, the computer system detects solar-induced fluorescence signals generated by sensor plants via measurements of narrow wavelengths near dark spectral features in incident solar radiation. Narrow-band techniques associated with Fraunhofer lines (absorption from the solar atmosphere) and atmospheric lines (absorption from molecules in the Earth's atmosphere) enable the measurement of light signals in sunlight without the need for external illumination. Implementing this measurement technique allows for both the specificity and accuracy of measuring small, fuzzy signals, and the ability to collect measurements from both the ground and the air. Therefore, images of the sensor plants can be collected from a wide range of distances. The computer system detects these solar-induced fluorescence signals and extracts insights into stressor stress at the sensor plants that generate these signals. In some implementations, the computer system may: acquire a first feed of spectral images captured by a first spectrometer; interpret a first stressor stress in a first set of sensor plants based on solar-induced fluorescence measurements extracted from the first image feed; acquire a reporter model relating the solar-induced fluorescence measurements extracted from the spectral images to stressor stress in the sensor plants; and interpret the first stressor stress in the first set of sensor plants based on the first solar-induced fluorescence measurements extracted from the first image.

[0051] In some embodiments, the computer system acquires data from a single sensor plant in an agricultural environment. In some embodiments, the computer system acquires images collected by optical sensors configured to be mounted (e.g., clipped) to the leaves or stems of the sensor plant and to capture close-up images of fluorescent surfaces on the sensor plant at a high frequency (e.g., once per minute, once per hour). In some embodiments, the computer system acquires images collected by optical sensors not mounted to the sensor plant. In some embodiments, one or more optical sensors are used to capture images of the sensor plant. In these examples, the computer system may upload images captured by one or more optical sensors to a remote database via a cellular network, or, when a mobile device or vehicle is nearby, download images to the mobile device or vehicle via a local self-organizing wireless network, and then upload the images from the mobile device or vehicle to a remote database for further analysis as described herein.

[0052] In some implementations, the computer system acquires images of a collection (e.g., a cluster) of sensor plants collected by one or more optical sensors. For example, the computer system may acquire images of sensor plants in an agricultural environment recorded by optical sensors fixed to a pole or post located at the center of the sensor plants, capturing close-up images of fluorescent surfaces on the sensor plants at a high frequency (e.g., once per hour, once per day). The computer system can extract insights from these close-up images of the sensor plants to interpret stress from specific stressors within the sensor plants. Furthermore, by interpreting stress within the sensor plants from images recorded by optical sensors located at the sensor plants, the computer system can extract insights into stress in sub-regions of an agricultural environment including a particular sensor plant, as well as in adjacent sub-regions.

[0053] In some implementations, the computer system acquires images of the agricultural environment including the sensor plants (e.g., a field entirely comprising the sensor plants). For example, the computer system may acquire images of the sensor plants in the agricultural environment recorded by one or more optical sensors (e.g., fixed optical sensors, movable optical sensors, aerial optical sensors, etc.) at a high frequency (e.g., once per hour, once per day). In some implementations, images are captured at a lower frequency (e.g., once per week, twice per month, once per month). The computer system can extract insights from these images of the sensor plants to interpret stress from specific stressors in the sensor plants. Furthermore, by interpreting stress in individual sensor plants from images recorded by optical sensors, the computer system can also extract insights into stress in the entire agricultural environment.

[0054] In some implementations, a user manually collects data on sensor plants on a handheld device. For example, a computer system may acquire images (e.g., spectral images) of sensor plants in an agricultural environment collected by a user-operated mobile device (e.g., a smartphone), capturing close-up images of the sensor plants at a low frequency (e.g., weekly, bi-weekly). In some implementations, the computer system additionally acquires images of sensor plants captured by other optical sensors in the agricultural environment. In this implementation, the computer system may upload the images to a remote database via a cellular network or automatically via a local or web-based agricultural application running on the handheld device. The computer system can directly interpret the stress in the sensor plants from the features extracted from the spectral images to generate a high-resolution, short-interval time-series representation of the health of the sensor plants and / or the agricultural environment.

[0055] In some implementations, the computer system implements ground-based mobile imaging to extract insights into the health of sensor plants and the agricultural environment by collecting images from optical sensors mounted in manned or unmanned vehicles. For example, the computer system can acquire images (e.g., spectral images) of sensor plants collected by optical sensors configured to be mounted (e.g., fixed) to the floorboards of a user-operated truck. In this example, the user can drive the truck along the edge of or across the agricultural environment to capture images of the sensor plants as the truck moves through it. The computer system can then upload these images to a remote database, timestamp and georeference them, and retrieve them at the time of upload or at a later time.

[0056] In some implementations, the computer system acquires images of sensor plants and / or the agricultural environment recorded by aerial sensors configured to capture images (e.g., spectral images) of the agricultural environment and sensor plants. For example, the computer system may acquire images of sensor plants and / or the agricultural environment collected by optical sensors configured to be mounted (e.g., fixed) to a drone or other aerial equipment. Optionally, in an agricultural environment containing both non-sensor plants and clusters of sensor plants, a drone or other aerial equipment may be used to scan areas of the agricultural environment where the sensor plant clusters are located to collect images of these sensor plants.

[0057] In some implementations, the computer system acquires images of sensor plant clusters, multiple sensor plant clusters, and / or sensor plant crops in an agricultural environment, recorded by aerial sensors (e.g., long-duration, high-altitude UAVs or satellites such as OCO-2 or GOSAT) configured to capture remote imagery of sensor plants. For example, the computer system may acquire images collected by satellite sensors configured to collect remote imagery of sensor plants at a low frequency (e.g., weekly, bi-weekly, monthly). In some implementations, the computer system may acquire images collected by commercial satellite sensors configured to collect remote imagery of sensor plants at a relatively high frequency (e.g., daily, multiple times weekly).

[0058] Computer systems can acquire images of sensor plants captured at set intervals or at specific times of day to increase the likelihood of signal detection, allowing for rapid testing of treatments and / or screening of plants to be treated, and detecting stressor stress in sensor plants and crops containing sensor plants at an early stage before these stresses amplify in magnitude or negatively impact crop yields. For example, a computer system can acquire images of sensor plants in an agricultural environment recorded by one or more optical sensors to monitor stressors indicative of plant health and, upon detection of these stresses (e.g., stresses above a threshold), prompt users associated with the agricultural environment (e.g., farmers) to selectively mitigate these stresses. Alternatively, users manually monitoring agricultural environments may not visibly see or detect stressor stress in crops until stress has significantly damaged plants within the crop. Therefore, computer systems can reduce the risk or probability of stress spreading throughout the agricultural environment and across crops to other agricultural environments, increasing overall crop yield. Computer systems also enable users to selectively and specifically apply given treatments specific to the stresses that the sensor plants are experiencing. Selective application of treatments reduces overexposure or unnecessary exposure to a given treatment, which can mitigate the development of tolerance and / or environmental effects that may result from exposure to the treatment. Furthermore, sensor plants can be configured to output signals of relatively large amplitude (e.g., greater intensity) in response to relatively low levels of stress. Sensor plants may include promoters configured to be activated and / or inactivated at the sensor plant during initial infection, absence, or for a short period (e.g., minutes or hours) based on the current level of stress at the sensor plant. A computer system can then detect the signals generated by the activation or inactivation of promoters in the sensor plant. Based on the detection of the signals, the computer system can recommend minimal treatments to alleviate stress in the sensor plant.

[0059] A computer system can periodically monitor sensor plants at a set frequency, enabling early detection of stress in the sensor plants while limiting costs and effort for users associated with the agricultural environment (e.g., farmers, agronomists). For example, the computer system can: acquire feeds of images of sensor plants in the agricultural environment recorded at a set frequency (e.g., twice daily, daily, weekly); interpret stress in the sensor plants based on features extracted from a first image in a first image feed; and generate prompts to the user associated with the agricultural environment in response to stress exceeding a threshold stress to address stress in the sensor plants and / or neighboring plants in the agricultural environment. In this example, if the stress drops below the threshold stress, the computer system can continue acquiring images from the first image feed at a set frequency to continue monitoring stress in the sensor plants. In some embodiments, the computer system can generate prompts to alert the user to stress. Therefore, the computer system enables users to periodically monitor the health of sensor plants and / or plants in the agricultural environment associated with the user, while minimizing actual user travel to the agricultural environment, sensor plant handling, and / or sensor plant health testing.

[0060] In some implementations, the computer system performs both high-frequency and low-frequency measurements to more accurately interpret and predict stressors in both the sensor plants and the agricultural environment. In this implementation, the computer system can combine a high-resolution, short-interval time-series representation of sensor plant health with features extracted from low-frequency, wider-field-of-view images of the sensor plants to predict the health of both the sensor plants and the agricultural environment. For example, the computer system can acquire a first feed of images recorded by fixed sensors of sensor plants in an agricultural environment at a first frequency (e.g., twice daily, once daily, or every two weeks). Additionally, the computer system can acquire a second feed of images of the agricultural environment containing the sensor plants, recorded by mobile sensors (e.g., deployed by users associated with the agricultural environment) at a second frequency (e.g., once weekly or every two weeks) less than the first frequency. From the images in these feeds, the computer system can derive a model relating features extracted from the images in the first feed to stressors in both the sensor plants and the agricultural environment. Therefore, the computer system can predict stress across a region of the agricultural environment at the first frequency based on features extracted from the images in the first feed. The computer system can periodically verify and / or correct the model based on features extracted from the image in the second feed at a second frequency.

[0061] In some implementations, a computer system can extract features from these images of sensor plants to interpret stress in the sensor plants. For example, the computer system can: acquire a first feed of images of sensor plants in an agricultural environment; and interpret a first stress of a stressor in the sensor plants based on a first set of features extracted from the first image in the first feed of images. More specifically, the computer system can: extract a first feature from a first set of features from the first image, the first feature corresponding to a first pixel of the first image; extract a second feature from the feature set of the first image, the second feature corresponding to a second pixel of the first image; and estimate a representative feature based on a combination of the first and second features; acquire a reporter model that associates the features extracted from the images in the first feed with the stress of a first stressor at the sensor plant; and interpret the first stress of a first stressor in the sensor plants based on the representative feature and the reporter model. Thus, based on features extracted from images collected by one or more optical sensors, the computer system can interpret the stress of a stressor at one or more sensor plants based on a reporter model that associates properties (e.g., wavelength intensity) with the stress of a specific stressor (e.g., insects, heat, fungi) and / or the stress of a specific stressor.

[0062] Computer systems can extract features (e.g., intensity at specific wavelengths) from images of sensor plants, clusters of sensor plants, and / or agricultural environments containing sensor plants to interpret stress from these sensor plants. To extract these features, the computer system can distinguish sensor plants from non-sensor plants (if present in the agricultural environment) within these images.

[0063] In some implementations, the computer system identifies the locations of sensor plants within an agricultural environment and extracts features from images or image regions corresponding to those locations. For example, the computer system can acquire georeferenced images of sensor plants in an agricultural environment recorded by ground-based mobile sensors. The computer system can: acquire the location and orientation of the ground-based mobile sensors while capturing images; acquire a set of GPS coordinates corresponding to the locations of the sensor plants in the agricultural environment; and identify the sensor plants in the images based on the location and orientation of the ground-based mobile sensors and the GPS coordinates of the sensor plants.

[0064] In some implementations, a computer system can identify sensor plants in images of sensor plants and non-sensor plants based solely on a baseline signal generated by the sensor plant. For example, the sensor plant can be configured to generate a baseline signal within a first wavelength band in which no signal is generated by the non-sensor plant. Furthermore, these sensor plants can be configured to generate a signal in a second wavelength band, distinct from the first, in response to stress from a stressor at the sensor plant. Thus, the computer system can examine the baseline signal within the first wavelength band for clusters of sensor plants or sub-regions of an image containing the sensor plant to identify regions of the image containing the sensor plant and / or clusters of sensor plants.

[0065] In some implementations, a computer system can identify sensor plants in aerial images of a crop (e.g., sensor plants and non-sensor plants) by covering an image with a mask configured to hide non-sensor plants and highlight sensor plants. For example, the computer system can generate a mask for a specific agricultural environment comprising five clusters of sensor plants distributed throughout the environment, the mask defining an opaque layer comprising five transparent regions corresponding to the five clusters. The computer system can then: overlay the mask onto an image of the crop captured by an aerial sensor; apply null pixel values ​​to the areas of the crop covered by the opaque layer; and extract features (e.g., intensity measurements) from the five transparent regions corresponding to the five sensor plant clusters in the crop.

[0066] It should be understood that the computer system described herein can implement any combination of these data collection methods (e.g., instrumentation, frequency, range) to collect high-quality data that enables a rapid, targeted response to certain plant stressors and thus increases the yield of sensor plants and / or nearby non-sensor plants in the same agricultural environment. In some embodiments, the computer system acquires high-resolution images recorded by high-resolution optical sensors (e.g., RGB cameras, multispectral cameras or spectrometers, thermal or IR cameras), which are fixed to poles located in the agricultural environment and configured to capture high-resolution images of sensor plants at a high frequency (e.g., three times a day) daily and upload these images to a remote database. The computer system can extract features (e.g., intensity at specific wavelengths) from these high-resolution images to interpret stress at the first sensor plant cluster. Alternatively, the computer system can acquire low-resolution images recorded by satellite sensors configured to capture low-resolution images of the entire agricultural environment at a low frequency (e.g., every two weeks). The computer system can extract features (e.g., intensity at specific wavelengths) from these low-resolution images to interpret stress in sensor plants within the agricultural environment. The computer system can derive models that link stress at one or more sensor plants to stress at other sensor and / or non-sensor plants in the agricultural environment, based on the daily behavior of sensor plants and their bi-weekly behavior in the agricultural environment; and interpolate the behavior of the entire agricultural environment.

[0067] Sensor plant distribution In some embodiments, sensor plant traits are incorporated into the genome of a genetically modified organism (GMO) plant as part of a GMO stack already present in the GMO seed, which can then be planted to produce an entire sensor plant crop. The sensor plants can be configured to generate several different signals representing a range of stresses and can be planted in clusters in a field—as described above—where all plants in one cluster contain the same promoter-reporter pair configured to generate signals against a specific biotic or abiotic stressor (or a specific group of biotic and / or abiotic stressors). In some embodiments, the sensor plants are specifically grown in an agricultural environment. In some embodiments, sensor plants containing the same promoter-reporter pair are planted along the entire length of a crop row in a field, where sensor plants in two adjacent crop rows contain different promoter-reporter pairs configured to generate signals against different biotic or abiotic stressors; in this example, a row pattern containing sensor plants with different promoter-reporter pairs is repeated along the entire length of the field. In another example, sensor plants containing the same promoter-reporter pairs are planted in linear clusters, such as in adjacent five-meter sections of five consecutive crop rows, where the sensor plants in adjacent clusters contain different promoter-reporter pairs configured to generate signals against different biotic or abiotic stressors; in this example, the grid of sensor plant clusters containing the same promoter-reporter pairs is repeated along the entire length and width of the field.

[0068] In implementations, sensor plants can be specifically cultivated in agricultural environments. In some implementations, sensor plants are planted in clusters—along with non-sensor plants that have the same fruit or similar crop types, and / or with different types of sensor plants (e.g., sensor plants that detect different stressors)—in order to maintain a high signal-to-noise ratio and sensing capability of the crops.

[0069] By clustering sensor plants in a one-dimensional or two-dimensional group of plants configured to generate signals against the same stressor, the crop as a whole can generate high-amplitude signals against multiple different biotic and / or abiotic stressors in discrete rows or regions of the field, characterized by a high signal-to-noise ratio. As described above, the stressors indicated by these plant rows or clusters configured to generate signals against the same stressor can then be interpolated or extrapolated across the entire field to predict stress across the entire crop.

[0070] Therefore, in the aforementioned implementation, since each plant in the field exhibits sensing capabilities, the entire crop can be directly monitored. The computer system can generate a stress map of biotic and / or abiotic stresses for the entire crop based on signals generated by these plants over a period of time (e.g., a day) and detected by fixed or mobile local or remote sensors. By repeating this process to develop new stress maps for the field over time, the computer system can monitor stresses across the field over time and provide data and / or recommendations for proactively mitigating these stresses. The computer system can also implement this process to update the field's stress map after stress treatment, enabling field operators to directly assess the effectiveness of the stress treatment and make more informed treatment decisions for the field in the future. Users can screen plants for treatment, allowing treatment to be applied selectively as needed, rather than across the entire agricultural environment. Furthermore, after a specific treatment has been applied to the field based on these interpreted stresses, the computer system can continue to measure and detect signals generated by the sensor plants and thus assess the effectiveness of the specific treatment based on the new stresses interpreted from these signals.

[0071] In some implementations, instead of planting sensor plants as seeds (such as row crops), seedlings, and / or saplings, they can be grafted onto existing plants. Grafting can be used for perennial crops and other high-value crops, such as apricot trees or grapevines. A scion or leafy portion of the sensor plant can be grafted onto a part of the desired plant, such as in the middle of the trunk. For example, a scion of a sensor grapevine can be grafted onto the trunk of a mature grapevine, allowing the scion portion of the mature vine to implement sensing technology, providing a healthy indication of the vine's condition. Because grafting sensor plants onto existing plants is initially a more time-consuming process, grafting can be useful for perennial crops that do not require annual replanting. These plants are pruned at the end of each season, but the sensing ability remains when the leaves flower in the next season. Therefore, grafting requires only a single application and can sustain the plant for its entire lifespan.

[0072] In some implementations, when planting in a field, sensor plants can be planted in clusters or exclusively, rather than mixed with non-sensor plants. Therefore, in implementations where the agricultural environment is entirely comprised of sensor plants, individual plants can be monitored, and the user can also be informed of the overall health of the agricultural environment. In some implementations, sensor plants are planted alongside non-sensor plants or different types of sensor plants (e.g., detecting different stressors), rather than mixing sensor plants targeting a specific stressor with non-sensor plants of the same or similar plant types. These sensor plants can be planted in clusters or specifically in designated sensor plant areas within the field, such as in specific crop rows (e.g., every 50 crop rows) or in target sections of crop rows (e.g., clusters three rows wide and three meters long, with a minimum of 20 crop rows or 20 meters between adjacent clusters of sensor plants). Therefore, by clustering these sensor plants in the same field adjacent to or surrounded by non-sensor plants or different types of sensor plants (e.g., detecting different stressors), the stress-related signals generated by these sensor plants can exhibit high contrast with adjacent non-sensor plants or different types of sensor plants, and thus produce a high signal-to-noise ratio for the presence of a specific stressor in the field. For example, by planting multiple instances of sensor plants in a small area of ​​the field, it is easier to distinguish the red fluorescent reporter outputs of these sensor plants from the non-fluorescent background of adjacent non-sensor plants or the different reporter outputs produced by different types of sensor plants. Similarly, if multiple sensor plants are planted in a row in the field, the cluster of sensor plants can generate a cumulative signal—indicating the presence of insect stress when it migrates across the crop—characterized by a larger signal-to-noise ratio than a single sensor plant in the row, and the cluster of sensor plants can also generate more spatial information about the direction and extent of insect stress movement across the field than a single sensor plant in the row.

[0073] Sensor plant clusters can be planted in a field alongside non-sensor plant crops, wherein the sensor plant clusters contain at least one sensor plant for each stressor, or wherein each sensor plant contains a promoter for each plant stressor. For example, batches of sensor plants—containing at least one promoter for at least one stressor—can be planted in clusters in a field along with other non-sensor plants. In another embodiment, clusters of sensor plants are grouped by promoters. In this embodiment, a first cluster of water pressure-sensing plants, a second cluster of fungal pressure-sensing plants, and a third cluster of insect pressure-sensing plants are planted in a discrete group in the field. In this embodiment, where sensor plants containing the same reporter are planted in clusters together, these clusters can output stronger, higher amplitude, and lower noise signals that are more easily identified by fixed, locally mobile, or remote sensors when the corresponding stress is present in the field.

[0074] The location of sensor plant clusters can also be chosen to enable the detection of certain plant stressors with higher accuracy and / or reduced noise. In one instance where a user is physically present to collect stressor data from an agricultural environment—such as via sensors mounted on a vehicle or via a handheld device—the clusters of sensor plants can be planted near the edge of the crop to allow farmers quick access. In this example, because the sensor plant clusters are located near the edge of the crop, the user can collect samples from these sensor plants and directly test the plant stressors in these samples to verify the stress indicated by the reporters in these sensor plant clusters. In another instance, sensor plants are planted in the center of the crop to increase proximity to each plant in the crop and thus potentially increase sensing capabilities or the likelihood of detecting disease migration across the crop.

[0075] In yet another instance, if a user's crop shares an edge with another user's crop, it might be desirable to plant a row of insect pressure sensor plants along the shared edge to quickly detect migrating insect colonies as they enter the crop. In another instance, if there is a lower elevation portion of the crop, a cluster of water pressure sensor plants could be planted in that area to detect when that area is collecting excessive water. A cluster could also be planted at the highest elevation portion of the crop, where plant dehydration may be prevalent. In some implementations, sensor plants are grown throughout the agricultural environment.

[0076] In the above-described embodiment where sensor plants are distributed in clusters throughout the field, the sensor plants can be identified and distinguished from non-sensor plants to improve the efficiency of data collection. For example, if a user collects images of the clusters weekly using a handheld device, markers can be placed in the field to facilitate cluster location. In another instance, where satellite imagery is used to collect crop images, the coordinates of the clusters can be obtained to collect wavelength measurements of the sensor plants.

[0077] In another implementation, sensor plants are mixed with non-sensor plants and also planted together in clusters. Clusters of sensor plants alone can be evenly distributed throughout the crop or in optimized locations. Sensor plant clusters can be analyzed more frequently, such as by drones scanning them daily to collect aerial imagery. Satellites can collect images of the entire crop less frequently, gathering data from both the sensor plant clusters and the individual sensor plants mixed with the rest of the crop. The health of the entire crop or agricultural environment can be predicted by a computer system based on timestamps of the sensor plants and georeferenced imagery.

[0078] In one embodiment, the sensor plant can be transplanted into a crop as a seedling. For example, a sensor strawberry plant can be initially transplanted into a strawberry field as a seedling. In another embodiment, the sensor plant can be sown into a crop as a seed. For example, a sensor soybean plant can be initially sown into a soybean crop as a seed. In yet another embodiment, the sensor plant can be grafted onto an existing perennial crop. For example, a sensor grape scion can be grafted onto a grapevine.

[0079] In some implementations, the agricultural environment is a controlled environment, such as a greenhouse (e.g., a glass roof or factory farm), a growth chamber, or another enclosed growth structure. Sensor plants growing in the controlled environment can be monitored periodically to detect stress at the sensor plant location. In one implementation, the sensor plants can be grown in an enclosed growth structure via vertical cultivation.

[0080] Sensor plants grown in these controlled environments can be transplanted to other locations (e.g., commercial agricultural environments) for use as sensor plants. Optionally, sensor plants grown in controlled environments can be monitored to detect stress from one or more stressors under specific controlled environmental conditions (e.g., climate, region, presence of other plants). Computer systems can interpret the stress in these sensor plants in greenhouse environments and extract insights into plants under similar environmental conditions (e.g., agricultural environments) based on the stress in the sensor plants.

[0081] Due to the smaller area of ​​controlled agricultural environments (e.g., indoor growing facilities, greenhouses, etc.), computer systems can monitor sensor plants in controlled agricultural environments more frequently than sensor plants located in agricultural environments. Therefore, computer systems can extract further insights into these sensor plants growing in controlled agricultural environments. For example, by interpreting the daily stress of specific stressors in sensor plants in a greenhouse, computer systems can more precisely converge on models that correlate features extracted from images collected from sensor plants with stress levels of specific stressors. Computer systems can then better model stress levels of specific stressors in controlled agricultural environments containing the same type of sensor plants and / or those transplanted by users associated with the agricultural environment.

[0082] As described herein, sensor plants grown in controlled agricultural environments can also be used as screening tools to evaluate treatments to plant stressors. In some embodiments, sensor plants are grown in controlled agricultural environments and exposed to stressors, wherein the sensor plants contain promoter-reporter pairs specific to the stressors to which the sensor plants are exposed. Various treatments can be applied to the sensor plants after they exhibit detectable signals captured in images captured by one or more optical sensors. Changes in the signals generated by the sensor plants can then be captured in subsequent images collected by one or more optical sensors. Analysis of signal changes can provide insights into the efficacy of different treatments to the stressors and can enhance and accelerate treatment development and testing. Multiple treatments can be tested across controlled environments containing many sensor plants. Treatments applied to sensor plants can be newly developed or already created. Furthermore, treatments can be applied in different forms. In some embodiments, treatments are applied as liquids (e.g., by spraying). In some embodiments, treatments are applied as solids. In some embodiments, the sensor plants and detection systems described herein analyze not only the treatments themselves but also the efficacy of different application methods and treatment protocols to determine the optimal formulation and use of the treatment.

[0083] Analysis performed by the detection system The computer system can: acquire images of sensor plants (e.g., spectral images); extract features indicating stressors in these sensor plants and the pressures corresponding to these stressors; interpolate or extrapolate the pressures of specific stressors in these sensor plants to other plants (e.g., sensor and non-sensor plants) in the same agricultural environment (and nearby fields); and then generate real-time cues or processing decisions for these crops to improve the efficiency of crop handling and maintenance over time and to maintain or increase yields from the agricultural environment.

[0084] In one implementation, the computer system: extracts wavelength measurements of specific compounds in regions depicting images of one or more sensor plants; and converts these wavelength measurements into stress maps (e.g., presence, amplitude) for one or more specific stressors in the one or more sensor plants. For example, if the computer system detects a specific wavelength of a compound associated with fungal disease in that region of the image, the computer system can acquire a model that associates the wavelength of the compound of interest with the fungal stressor, and then pass the intensity of that wavelength in that region of the image into the model to estimate fungal stress in one or more sensor plants (e.g., in the form of "percentage" stress). Based on the fungal stress of a specific sensor plant, the computer system can generate predictions of fungal stress in other plants (e.g., other sensor plants and / or non-sensor plants) around or near the one or more sensor plants.

[0085] Figure 2 A graphical representation of the analysis performed by the computer system is provided. Optical sensors capture images of the sensor plant and extract different wavelengths that can be associated with specific promoter-reporter pairs. The computer system can compare the extracted wavelengths with previously established signals and / or criteria (e.g., threshold levels of the stressor) indicating the presence of a specific stressor. The computer system can then determine which stressors are present in the sensor plant and subsequently generate guidance or instructions for the user to address the identified plant stressors.

[0086] In the aforementioned example, to generate a model linking wavelength intensity to stress, a user can collect samples from leaf or soil sensor plants to detect plant stressors. The samples can be tested to identify the specific type and stress of the stressor present at the leaf location, while the wavelengths of disease-associated compounds in the plant can be measured from the collected images. A model depicting the relationship between the detected wavelengths of the compound of interest and stress amplitude can then be generated based on this empirical data (e.g., via a computer system). Subsequently, the computer system can automatically (and autonomously) predict stress throughout the crop based on features extracted from images of the sensor plants, rather than on physical samples collected by the user. Optionally, this model can be generated based on laboratory data before deploying the sensor plants to an agricultural environment and can be correlated with sensor plants deployed during subsequent growing seasons.

[0087] In crops with multiple sensor plant clusters or where sensor plants are distributed throughout the crop, a computer system can acquire images collected both on the ground and in the air to output a stress map of the crop. The stress map can show the location of specific diseases and stressors and can be updated or combined to show the spread or elimination of a specific stress over time. The map can display interpolated stress data for a region of the crop, including areas without sensor plants. In one implementation, images can be collected multiple times daily from a camera located on a pole at the center of a sensor plant cluster. Additionally, satellite images of the entire crop, including other sensor plant clusters, can be collected every two weeks. Based on the bi-weekly wavelength measurements of disease compounds in the remaining clusters, data collected daily from a single cluster can be used to model the behavior of other clusters. Areas of the crop between clusters, or "non-sensor" areas, can also be modeled through interpolation (e.g., via machine learning algorithms). To confirm the presence of a stressor and interpret the stress caused by that stressor, the user can collect samples from the sensor plants themselves or the surrounding soil.

[0088] For example, a computer system can acquire image feeds from a remote database, the first image feed being timestamped and georeferenced, and uploaded via a wireless network from a device on a pillar at the center of a first sensor plant cluster in an agricultural environment at a frequency of one image per hour; acquire satellite imagery of the agricultural environment, including a group of sensor plant clusters, with satellite imagery collected every two weeks; interpret the stress in the first cluster based on a model that correlates features extracted from the image feeds with stressors and stressor stress; interpolate the stress of the cluster set and all plants in the agricultural environment based on the model and the image feeds from the remote database and satellite imagery; generate a stress map containing: the location of stress in the agricultural environment, the magnitude of stress, the location of the sensor plant clusters, a first timestamp of the time the map was generated, and a second timestamp of the time the map is representative; generate tips or treatment suggestions for the agricultural environment based on the stress map; and deliver the stress map and corresponding tips or treatment suggestions to users associated with the agricultural environment.

[0089] After generating a stress map based on the measurement wavelengths of specific compounds in plants, the computer system can prompt users associated with the agricultural environment to take certain actions to combat plant stressors. In one implementation, farmers can plant a row of insect sensor plant seeds along the edge of a soybean field to monitor the boundary between the farmer's crop and adjacent crops. Each day, optical devices fixed to poles in the sensor plant row can capture images of the sensor plants. From these images, the computer system can measure the wavelengths of compounds associated with insect-related diseases and display a certain insect stress amplitude at the edge of the map where the sensor plant row is located. Based on the insect stress amplitude and the time of image collection, the computer system can display the predicted current insect stress amplitude in the surrounding area of ​​the crop and prompt farmers to make decisions such as: whether to treat insects on the crop with pesticides based on stress amplitude readings; which areas of the crop should be treated for insect diseases; and the degree of treatment in different areas of the crop. After the initial treatment, as more images are collected and more data becomes available, the computer system can update the stress map and prompt farmers to implement updated treatment plans with this new information and make improved treatment decisions for future insect-related diseases. Output stress maps provide farmers with a means to alert them to diseases or stresses in crops when they occur, and to predict the possible responses to certain treatments or the absence of treatment. Over time, as more data is collected and various treatments are applied to crops based on stressors indicated by signals output from sensor plants in the field, computer systems can develop models to predict plant and plant stressor responses to certain treatments, such as the magnitude of changes in the signal output from sensor plants to known stressors in response to a specific treatment applied to the field.

[0090] Computer systems can generate real-time cues or treatment decisions for these crops to increase the efficiency of crop handling and maintenance over time and to maintain or increase yields from the agricultural environment. For example, in response to interpreting that the stress of a specific stressor in a sensor plant exceeds a threshold stress, a computer system can generate cues to address the specific stressor in plants near the sensor plant. More specifically, the computer system can: isolate a first action associated with the specific stressor from a set of actions defined for the sensor plant; and send a notification to the computing devices of users associated with the agricultural environment to take the first action in the agricultural environment to mitigate the specific stressor. Thus, the computer system can update users (e.g., agronomists, farmers, landowners) on plant health and / or recommend treatments to mitigate stress in plants.

[0091] In some implementations, the computer system can derive a stress model that correlates the stress of a specific stressor at a first group of sensor plants (e.g., a single sensor plant, a cluster of sensor plants, or an agricultural environment entirely containing sensor plants) with the stress of a specific stressor at a second group of sensor plants. By developing this stress model, the computer system can minimize data collection from all sensor plants in a specific area (e.g., an agricultural environment) by correlating the stress in a single group of sensor plants with other groups of sensor plants in the agricultural environment.

[0092] In some implementations, the computer system may: acquire a first feed of images recorded at a first frequency by fixed sensors (e.g., cameras fixed to a beam at the center of the agricultural environment) of a first set of sensor plants in an agricultural environment; acquire a second image of a second set of sensor plants in the agricultural environment, the second image being recorded during a first time period by movable sensors (e.g., cameras of a user's movable device associated with the agricultural environment); interpret a first stress of stress in the first set of sensor plants during the first time period based on a first set of features extracted from the first image of the first feed of images captured during the first time period; and interpret a second stress of stress in the second set of sensor plants during the first time period based on a second set of features extracted from the second image. Based on the first stress interpreted at the first set of sensor plants and the second stress interpreted at the second set of sensor plants, the computer system may derive a stress model that correlates the stress of stress at the first set of sensor plants with the stress of stress at the second set of sensor plants.

[0093] After the computer system derives the stress model, it can continue to acquire images from the first feed to interpret the stress at the first and second groups of sensor plants based on the model. For example, during a second time period, the computer system can: interpret a third set of stress in the first group of sensor plants based on a third set of features extracted from a third image in the first feed captured during the second time period; and predict a fourth set of stress in the second group of sensor plants during the second time period based on the third stress and the model. Therefore, the computer system can predict the stress at the second group of sensor plants based on images of the first group of sensor plants from the first feed without acquiring additional images of the second group of sensor plants. Optionally, the computer system can continue to collect images of the second group of sensor plants at a second frequency less than the first frequency to ensure the accuracy of the stress model and update the stress model over time. Furthermore, the computer system can collect images of other groups of sensor plants and develop additional stress models that correlate the stress in these other groups of sensor plants across a specific region with the first group of sensor plants in the agricultural environment, thereby enabling the prediction of the stress of a specific stressor in that group of sensor plants across the agricultural environment based on information extracted from images of the first group of sensor plants.

[0094] Based on this predicted fourth stress at the second set of sensor plants, the computer system can generate prompts or send notifications to users associated with the agricultural environment. For example, in response to the fourth stress at the second set of sensor plants exceeding a threshold stress, the computer system can generate prompts to address stressors in plants near the second set of sensor plants in the agricultural environment.

[0095] In some implementations, the computer system can derive a gradient model that correlates the pressure of a specific stressor at a first set of sensor plants (e.g., a single sensor plant, a cluster of sensor plants) with the pressure at a sub-region of the agricultural environment containing the first set of sensor plants (e.g., a pressure gradient in the agricultural environment). By developing this gradient model, the computer system can minimize data collection from all sensor plants in a specific region (e.g., the agricultural environment) by correlating the pressure gradient in a specific region (e.g., pressure across sensor plants in a specific region) with a single set of sensor plants in the agricultural environment. Furthermore, the computer system can correct for biases in the pressure interpreted at the first set of sensor plants based on the gradient model.

[0096] In some implementations, the computer system may: acquire a first feed of images recorded at a first frequency by fixed sensors (e.g., cameras fixed to poles in the agricultural environment) of a first set of sensor plants in an agricultural environment; acquire a second image of an area of ​​the agricultural environment containing the first set of sensor plants, the second image being recorded by a mobile sensor (e.g., an aerial sensor, a drone, a satellite) during a first time period; interpret a first stress of the stressor in the first set of sensor plants during the first time period based on a first set of features extracted from the first image in the first feed of images captured during the first time period; interpret a first stress gradient of the stressor in the sensor plants in the area of ​​the agricultural environment during the first time period based on a second set of features extracted from the second image; and derive a gradient model that correlates the stressor stress at the first set of sensor plants with the stress gradient of the stressor in the area of ​​the agricultural environment based on the first stressor stress and the first stress gradient.

[0097] When deriving the gradient model, the computer system can correct the first pressure gradient based on the first stress and gradient model of the stressor at the first set of sensor plants. Furthermore, the computer system can predict the pressure gradient of a specific stressor based on features extracted from images in the first feed. For example, the computer system can: interpret the second stress of the stressor in the first set of sensor plants during the second time period based on a third set of features extracted from a third image in the first feed of images captured during the second time period; and predict the second pressure gradient of the stressor in the region of the agricultural environment during the second time period based on the second stress and the model.

[0098] Based on this pressure gradient, the computer system can monitor the pressure in various sub-regions of the agricultural environment. If the computer system predicts high pressure for a specific stressor in a particular sub-region of the agricultural environment, it can label that sub-region and generate prompts for users associated with the agricultural environment to address the specific stressor in that sub-region. For example, in response to a second pressure gradient predicting a third pressure in a sub-region of the agricultural environment that exceeds a threshold pressure, the computer system can generate prompts to address the stressor in plants occupying a sub-region adjacent to the agricultural environment. Furthermore, based on the pressure gradient, the computer system can generate a pressure map. The computer system can include this pressure map in prompts to the user.

[0099] Furthermore, the computer system can refine the gradient model by interpreting stress from an additional set of sensor plants within the agricultural environment. In one implementation, the entire agricultural environment consists of sensor plants (e.g., no non-sensor plants). In this implementation, the computer system interprets the first stress gradient based on features extracted from a second image recorded by a movable sensor. The computer system can combine this low-resolution stress gradient data of the entire agricultural environment with the high-resolution stress data of the first set of sensor plants to develop a more accurate gradient model for predicting stress gradients across the entire agricultural environment.

[0100] In another embodiment, where clusters of sensor plants are grown within an agricultural environment containing non-sensor plants, a computer system can interpret a first pressure gradient based on features extracted from a region of a second image recorded by a movable sensor, the region including a first group of sensor plants and (at least) a second group of sensor plants. In this embodiment, the computer system can interpret the pressure of a specific stressor at the first group of sensor plants based on the first image, and interpret a second pressure of the specific stressor at the first group of sensor plants based on the second image. The computer system can then: derive a gradient model that correlates the pressure of the specific stressor at the first group of sensor plants with the pressure gradient of the first stressor in the agricultural environment, based on the second pressure and the first pressure gradient both extracted from the second image; and correct the first pressure gradient of the specific stressor in the agricultural environment based on the first pressure and the model.

[0101] Computer systems can utilize data corresponding to specific agricultural environments or crops to develop annual models that simulate the stress of stressors within those environments. For example, during the first season and for a specific crop, the computer system can extract insights such as: water movement across the crop; daylight exposure across the crop (e.g., daily, weekly, monthly, seasonal); and the timing of other stressors such as insects, fungi, and nutrient deficiencies. The computer system can then input each of these insights into an annual model to predict crop conditions at the start of the next season and throughout the following season. At the start of the next season, the computer system can then predict initial crop conditions based on the model. Furthermore, based on these predicted initial conditions, the computer system can recommend cultivation practices to crop-related users, such as the type of seed hybrid to be planted and / or different soil mixtures to be laid. As the season progresses, the system can update the annual model accordingly.

[0102] Furthermore, based on annual models, computer systems can predict and / or recommend the most suitable agricultural products and / or treatments for a given agricultural environment. For example, a computer system can predict the first stressor stress in plants within an agricultural environment at a specific time based on an annual model. Based on the predicted first stress, a user can apply new treatments to these plants at the start of the season to alleviate the predicted first stress. Subsequently, the computer system can interpret the second stressor stress in plants within the agricultural environment at that specific time based on data recorded by sensors in the agricultural environment. If the second stressor stress is less than the predicted first stressor stress, the computer system can update the annual model accordingly and / or recommend new treatments in the future to address the stressor stress.

[0103] In some implementations, the computer system can extract insights from a single sensor plant (e.g., in a crop with a non-sensor plant, in a greenhouse, or in a crop with a sensor plant) to: monitor stressor stress in plants in an agricultural environment; develop models to predict changes in plant behavior over time; develop models to predict plant responses to various stressors present at the sensor plant; develop models to interpret stressor stress at the sensor plant from measurements; test the efficacy of treatments for various stressors present at a single sensor plant; and / or develop models of plant responses to these treatments.

[0104] In some implementations, a single sensor plant or a single cluster of sensor plants may grow within a non-sensor plant crop. In some implementations, a single sensor plant is monitored in an agricultural environment containing sensor plants. The presence of a stressor at the sensor plant location can be monitored for this single sensor plant (or a single cluster of sensor plants). For example, a computer system can acquire data (e.g., images) recorded by a sensor (e.g., a smartphone) and interpret a first stress of a specific stressor at the sensor plant location based on features extracted from that data. Based on the interpreted first stress at the single sensor plant location, the computer system can extract insights into the plants near the single sensor plant and / or the plants within the crop containing non-sensor plants or other sensor plants. Furthermore, the computer system can suggest specific treatments for the plants in the crop based on the interpreted first stress. When a user applies a specific treatment, the computer system can interpret a second stress to confirm the effectiveness of the specific treatment.

[0105] In another example, sensor plants can be grown in a greenhouse. A computer system can acquire data (e.g., hyperspectral images) recorded by optical sensors in the greenhouse to extract a first set of measurements (e.g., wavelength intensity) indicating plant health. A user (e.g., associated with the greenhouse) can collect samples from the sensor plants to confirm their health and / or the presence of any stressors at their location. In this example, if the user interprets the sensor plant as healthy based on the collected samples and interprets the absence of stress from a specific stressor at its location, the computer system can associate the first set of measurements with a healthy plant that does not exhibit stress from the specific stressor and store that information in the model. Later, the user can subject the sensor plant to stress from a specific stressor (e.g., fungal stressor). The computer system can again acquire data recorded by optical sensors in the greenhouse to extract a second set of measurements (e.g., wavelength intensity) corresponding to the sensor plant. The computer system can then associate the second set of measurements from the sensor plant with stress from the specific stressor introduced by the user at the sensor plant and store that information in the model. Therefore, over time, computer systems can develop models that link measurements extracted from data recorded by optical sensors in greenhouses to the stress of specific stressors at the sensor plants.

[0106] In some implementations, the computer system can extract insights related to the efficacy of plant treatments over time. For example, sensor plants can be grown in a greenhouse where plants are arranged in vertical stacks (e.g., via vertical cultivation). The computer system can extract measurements (e.g., images) from data recorded by sensors in the greenhouse to extract insights into plant health. The computer system can interpret a first set of measurements extracted from data recorded by sensors at a first time point to determine the first stress at the sensor plant. The computer system can then notify a user associated with the greenhouse of the first stress. The user can then apply a specific treatment to plants in the greenhouse near the sensor plant to alleviate the first stress. Subsequently, the computer system can interpret a second set of measurements extracted from data recorded by sensors at a second time point (e.g., 24 hours after the application of the specific treatment) to determine the second stress at the sensor plant. Based on the first and second stresses, the computer system can derive a model representing the specific stressor's response to the stress of applying the specific treatment over time. Thus, the computer system can derive models for predicting plant responses to various treatments and / or agricultural techniques. In some implementations, users can actively apply specific stressors to sensor plants in order to assess the effectiveness of treatment on that specific stressor.

[0107] It should be understood that the methods for analyzing and detecting sensor plant signals described herein are applicable to various agricultural environments. For example, in some embodiments, the agricultural environment specifically includes sensor plants. In some embodiments, the agricultural environment includes one or more different sensor plants (i.e., detecting different stressors). In some embodiments, the agricultural environment includes clusters of sensor plants. In some embodiments, the agricultural environment includes sensor plants interspersed with non-sensor plants.

[0108] The computer systems and methods described herein can be presented and / or implemented, at least in part, as machines configured to receive computer-readable media storing computer-readable instructions. The instructions can be executed via computer-executable components integrated with a user computer or mobile device, wristband, smartphone application, app, host, server, network, website, communication service, communication interface, hardware / firmware / software element, or any suitable combination thereof. Other computer systems and methods of the embodiments can be presented and / or implemented, at least in part, as machines configured to receive computer-readable media storing computer-readable instructions. The instructions can be executed via computer-executable components integrated with devices and networks of the types described above. The computer-readable medium can be stored on any suitable computer-readable medium, such as RAM, ROM, flash memory, EEPROM, optical devices (CD or DVD), hard disk drives, floppy disk drives, or any suitable device. The computer-executable component can be a processor, but any suitable dedicated hardware device can (optionally or additionally) execute the instructions.

[0109] Use of sensor plants Networks or crops consisting entirely of sensor plants can be deployed in agricultural environments to (e.g., visually, thermally, chemically) communicate the presence of biotic and abiotic stresses in the sensor plants and the agricultural environment to users. Specifically, when exposed to these plant stresses and phytotoxicants, sensor plants can experience, react, and become biotically degraded in the same or similar manner as comparable non-sensor plants grown in crops, in the presence of certain plant stressors. Sensor plants can also be deployed in agricultural environments, allowing for the monitoring of individual plants to better monitor the health of all plants in the agricultural environment. Therefore, sensor plants can serve as accurate sensors and predictors of diseases and / or stresses in agricultural environments. In some implementations, the agricultural environment comprises only sensor plants, allowing for the rapid and efficient detection and treatment of stresses in the agricultural environment by monitoring each individual sensor plant within it. In some implementations, sensor plants are deployed in agricultural environments and grown alongside other non-sensor plants—such as in clusters of sensor plants surrounded by non-sensor plants or different types of sensor plants (e.g., detecting different stressors)—in order to detect, measure, and communicate certain stressors in the sensor plants, which can then be interpolated or extrapolated to stressors in nearby plants.

[0110] In some embodiments, the agricultural environment comprises only sensor plants. In some embodiments, sensor plants are monitored to identify the presence of stressors in individual sensor plants within the agricultural environment. The presence of stressors in sensor plants can provide valuable information about the health of individual plants, agricultural areas, and the overall agricultural environment. In some embodiments, sensor plants are used to screen for the presence of specific stressors, allowing treatments to be selectively applied only when necessary. Screening plants for selective treatment reduces unnecessary use of treatments, limits untargeted exposure to treatments, can reduce treatment-related environmental impacts, reduces the chance of developing tolerance due to overexposure to treatments, and can improve the overall efficiency of treatments and the health of sensor plants within the agricultural environment. Therefore, this disclosure includes methods for reducing overexposure to treatments (e.g., chemical treatments) in agricultural environments.

[0111] In some embodiments, the agricultural environment includes sensor plants and other plants (e.g., non-sensor plants and sensor plants that detect different stressors). In some embodiments, the presence of stressors (e.g., pests, diseases, dehydration) in the sensor plants within the agricultural environment is monitored. In some embodiments, the presence of stressors (e.g., pests, diseases, dehydration) in the sensor plants and / or other plants is monitored. Typically, a small number of sensor plants can be monitored to extract insights into a larger plant population (e.g., within a crop). For example, a cluster of sensor plants may be planted along the outer edge of a crop, and the presence of pests may be monitored to notify users associated with the crop (e.g., farmers, agronomists, botanists) whether and / or when a pest colony has entered the crop along that outer edge. In some embodiments, individual sensor plants are monitored in an agricultural environment specifically containing sensor plants. In another example, sensor plants of a first plant type (e.g., tomato) may be grown in a greenhouse environment (e.g., a glass roof or factory farm), located in a specific area, and the presence of stressors (e.g., dehydration, diseases, pests) that indicate plant health may be monitored. Users associated with greenhouse environments can extract insights from the stresses present at sensor plants to inform the planting and / or treatment of other plants of the same plant type in specific areas (e.g., in crops). Users can also screen different treatments based on their effectiveness in addressing specific stresses before selecting treatments for broader application.

[0112] In some embodiments, the sensor plants described herein are used to screen the efficacy of various treatments against a specific stressor. Sensor plants in an agricultural environment can be exposed to a specific stressor, resulting in the generation of a detectable signal in the sensor plant. One or more treatments can be applied to sensor plants already exposed to the stressor. The sensor plants can then be monitored to determine changes in the signal as a result of the treatment. In some embodiments, a treatment that effectively addresses a specific stressor can, for example, alter the intensity of the signal generated by the sensor plant in response to the stressor. A computer system can detect and analyze changes in the intensity of the signal generated by the sensor plant to extract insights into the efficacy of the treatment. Thus, new treatments against plant stressors can be evaluated in sensor plants in a rapid and objective manner. The system can also evaluate different forms of treatment application and be used to compare the efficacy of different known treatments, where efficacy may be influenced by other factors that can be simulated by the sensor plant, the agricultural environment, and / or the detection system (e.g., co-application with other treatments, soil composition, environmental conditions, etc.).

[0113] In some embodiments, this disclosure provides a method for reducing excessive exposure of agricultural environments to plant treatments, comprising: (a) capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to produce signals in response to a stressor; (b) detecting the stressor-responsive signals in the spectral images of the sensor plants; and (c) selectively applying a stressor-targeting treatment to a subgroup of plants in the agricultural environment based on the detected signals. In some embodiments, the treatment is a chemical treatment. Plant treatments are generally known to those skilled in the art and may include, but are not limited to, the fungicides, biofungicides, insecticides, herbicides, and fertilizers described herein.

[0114] In some embodiments, this disclosure provides a method for improving plant treatment efficiency, comprising: (a) capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to generate signals in response to stressors; (b) detecting stress-responsive signals in the spectral images of the sensor plants; and (c) selectively applying a stress-targeting chemical treatment to a subgroup of plants in the agricultural environment based on the detected signals. In some embodiments, the treatment is a chemical treatment. Plant treatments are generally known to those skilled in the art and may include, but are not limited to, the fungicides, biofungicides, insecticides, herbicides, and fertilizers described herein. In some embodiments, signals generated by one or more sensor plants identify the presence of stressors faster than visible signs of disease that plants might typically exhibit (e.g., discoloration, wilting, etc.). Therefore, the sensor plants and systems described herein allow for early identification of stressors, which may allow for early relief of stressors before visible symptoms begin to appear in plants. Thus, the sensor plants described herein can improve plant health, yield, and provide many benefits and efficiencies associated with early intervention to protect plants from stressors.

[0115] In some embodiments, this disclosure provides a method for screening plants for treatment, comprising: (a) capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to produce signals in response to a stressor; (b) detecting the stressor-responsive signals in the spectral images of the sensor plants; and (c) selectively applying a stressor-targeting chemical treatment to a subgroup of plants in the agricultural environment based on the detected signals. In some embodiments, the treatment is a chemical treatment. Plant treatments are generally known to those skilled in the art and may include, but are not limited to, the fungicides, biofungicides, insecticides, herbicides, and fertilizers described herein.

[0116] In some embodiments, this disclosure provides a method for testing the efficacy of a treatment in plants, comprising: (a) applying a stressor to one or more sensor plants in an agricultural environment, wherein the sensor plants have been genetically engineered to produce a signal in response to the stressor; (b) capturing a spectral image of the sensor plants in the agricultural environment; (c) detecting the stressor-responsive signal in the spectral image of the sensor plants; (d) selectively applying a treatment to the plants in the agricultural environment based on the detected signal; and (e) recording changes in the signal after the treatment has been applied. In some embodiments, the treatment is a chemical treatment. Plant treatments are generally known to those skilled in the art and may include, but are not limited to, the fungicides, biofungicides, insecticides, herbicides, and fertilizers described herein.

[0117] Plant treatment In some embodiments, this disclosure provides sensor plants as described herein to screen plants to be treated in response to stressors. In some embodiments, this disclosure provides sensor plants as described herein to screen agricultural environments to be treated in response to the presence of stressors. In some embodiments, this disclosure provides sensor plants as described herein to screen the efficacy of treatments against specific stressors. In some embodiments, a computer system as described herein provides a prompt to a user to apply minimal treatment to alleviate stress in the sensor plant when stressors are detected in the sensor plant. In some embodiments, the treatment is a chemical treatment. In some embodiments, the treatment is an organic or inorganic treatment. In some embodiments, the treatment is selected from fungicides, insecticides, biofungicides, herbicides, and / or fertilizers.

[0118] In some implementations, the treatment applied to sensor plants and / or agricultural environments, as described herein, is a fungicide. Fungicides include, but are not limited to, triazoles, acanthopanax (quinone inhibitors), and succinate dehydrogenase inhibitors (SDHI).

[0119] Triazoles are fungicides used for the prevention and treatment of fungal diseases in agricultural environments. Triazole fungicides are stable and have long chemical and photochemical half-lives. Due to their stable and persistent nature, triazole fungicides readily accumulate and diffuse into environmental soil and water. Because of their persistence and poor degradation, triazoles are considered organic pollutants. Triazole fungicides that can be used in this disclosure include, but are not limited to, tebuconazole and cyclohexidine.

[0120] For decades, agaricones have been used worldwide to combat fungal diseases. Agaricone fungicides are a type of exoquinone inhibitor that inhibits mitochondrial respiration in fungi by binding to the hydroquinone oxidation site of cytochrome b. Because agaricones inhibit mitochondrial respiration, they exhibit broad-spectrum activity and are non-specific, allowing for widespread use and application. Similar to triazoles, agaricone fungicides have prolonged persistence after application and often contaminate environmental water, soil, and ecosystems. Agaricone fungicides that can be used in this disclosure include, but are not limited to, azoxystrobin, oxadiazon, pyraclostrobin, and azoxystrobin.

[0121] SDHI fungicides are also widely used to control turfgrass diseases and, due to their non-specificity, can serve as effective alternatives to fungicides with other mechanisms of action. SDHI fungicides work by inhibiting mitochondrial respiration in fungi by inhibiting the succinate dehydrogenase complex. SDHI fungicides block electron transport mediated by succinate dehydrogenase, thus preventing fungal growth. SDHI fungicides that can be used in this disclosure include, but are not limited to, bifenthrin and flutoanil.

[0122] It should be understood that those skilled in the art will recognize which fungicides are effective in treating various fungal infections and are suitable for application to a given plant species. While fungal treatments are known and commonly used, overexposure to fungicides and their persistence in the environment increases the risk of pollution, contamination, and the development of tolerance. This disclosure provides sensor plant systems that address these and other risks associated with the use of fungicides in agricultural settings by allowing the testing of new fungicide treatments and screening sensor plants in agricultural settings to selectively apply fungicides to the sensor plants requiring treatment.

[0123] Biofungicides do not rely on chemicals to treat fungi and / or other pathogens, but instead contain live organisms as active ingredients, which possess specific activity against plant pathogens (e.g., fungi). Different biofungicides will have different mechanisms of action, including but not limited to competition (e.g., the live organism in the biofungicide outperforms the plant pathogen), symbiosis (i.e., antibiotics or toxins targeting pathogens), predation or parasitism, and induction of resistance in plants. In some embodiments, biofungicides incorporate multiple mechanisms of action. Because biofungicides do not contain chemicals that may persist in the agricultural environment, they reduce environmental risks. Because biofungicides contain naturally occurring active ingredients, they have limited efficacy against different types of pathogens, and therefore the sensor plant system described herein can rapidly and effectively test biofungicides before application to ensure the efficacy of the treatment. Biofungicides contemplated and usable therein in this disclosure include, but are not limited to, those based on the genus *Trichoderma* (…). Trichoderma Biological fungicides based on Bacillus subtilis (Bacillus subtilis) Bacillus subtilis Biological fungicides and Bacillus amyloliquefaciens-based agents Bacillus amyloliquefaciens ) biological fungicides.

[0124] Plants in agricultural environments can also respond to insect stressors with pesticide treatment. Pesticides pose significant environmental risks through their toxicity and potential impacts on the entire environmental system. Pesticides can be systemic in nature, meaning they are integrated and distributed throughout the plant. Pesticides can also be contact pesticides, making physical contact with the pesticide toxic to insects. Synthetic pesticides contemplated and usable in the sensor plants and sensor plant systems described herein include, but are not limited to, organochlorides, organophosphates, carbamates, pyrethroids, neonicotinoids, phenylpyrazoles, butenolides, and ryanoids / diamids. Pesticides may also include insect growth regulators (e.g., hormone mimics and benzoylphenylurea) and biopesticides, including but not limited to those based on Bacillus thuringiensis (Bt). Bacillus thuringiensis Other bacteria-based pesticides, interfering oligonucleotides (e.g., RNAi-based pesticides), venom-based pesticides, and enzyme-based pesticides.

[0125] Herbicides are common treatments applied to plants in agricultural environments to control unwanted plant growth. Herbicides can be broad-spectrum and more selective, and can be applied before planting, before emergence, and after unwanted plant emergence. Herbicides, as well as other treatments described herein, can be applied to soils in agricultural environments or to plants in agricultural environments. Herbicides contemplated for and usable in sensor plants and sensor plant systems described herein include, but are not limited to, herbicides that inhibit acetyl-CoA carboxylase (ACCase), herbicides that inhibit acetyllactase synthase (ALS), herbicides that inhibit enolpyruvylshikimate 3-phosphate synthase (EPSPS), auxin-like herbicides, herbicides that inhibit photosystem II, herbicides that inhibit photosystem I, and herbicides that inhibit 4-hydroxyphenylpyruvate dioxygenase.

[0126] Fertilizers are also regularly applied to agricultural environments to promote plant growth and health. The sensor plants and sensor plant systems described herein can be used to test and screen fertilizers, and to indicate the need for selective fertilization of sensor plants and / or agricultural environments. Because fertilizers add specific nutrients to agricultural environments, over-fertilization can negatively impact plant growth, water and soil quality, and other consequences. Fertilizers can be organic or inorganic, and can be applied as liquids or solids. Fertilizers envisioned and usable in the sensor plants and sensor plant systems described herein include, but are not limited to, single-nutrient fertilizers (e.g., ammonium nitrate, urea, etc.), multi-nutrient fertilizers (e.g., two-component fertilizers, NPK fertilizers), and micronutrients (e.g., boron, zinc, manganese, etc.).

[0127] In some embodiments, the sensor plants described herein screen for newly developed treatments and / or treatments contemplated for application to plants in an agricultural environment in response to the presence of a stressor. In some embodiments, sensor plants of a specific plant species of interest, which have been genetically engineered as described herein to produce signals in response to a stressor, are exposed to that stressor. In some embodiments, the sensor plants are capable of screening for treatments in a controlled agricultural environment (e.g., a greenhouse or indoor farm). Exposure of the sensor plants to the stressor induces stress-associated signals (e.g., phenotypic changes), and one or more treatments can be applied to the sensor plants to treat the stressor. In some embodiments, the signals change in response to the stressor as a particular treatment becomes effective in treating the stressor and the stress associated with the stressor decreases below a predetermined threshold level. In some embodiments, one or more optical sensors monitoring the sensor plants in an agricultural environment capture images of the sensor plants at predetermined intervals, and a computer system is able to analyze the images to determine the efficacy of the treatment (as a result of changes in detectable signals produced by the sensor plants).

[0128] In some implementations, the sensor plants described herein also provide effective screening of treatment application methods to evaluate the efficacy of different treatment delivery methods. Example

[0129] Example 1: Drought sensing in tomato plants.

[0130] The response of sensor plants to water stress (i.e., drought) was assessed using a drought-sensing promoter-reporter on genetically engineered tomato plants (variety M82). Agrobacterium (…) Agrobacterium )-mediated transformation genetically engineered M82 tomato plants to insert Arabidopsis thaliana containing a gene operatively linked to the TdTomato fluorescent protein (V298-27-8). Arabidopsis The promoter-reporter pair of the RD29a promoter. Control plants used in this experiment included unmodified M82 tomato plants and M82 tomato plants genetically engineered with a ubiquitin promoter operatively linked to the DsRed fluorescent protein (which constitutively expresses the DsRed fluorescent protein).

[0131] Tomato plants (n=5 plants / group) were grown in a growth chamber for three weeks under constant temperature (24°C) and long-day conditions (16 / 8h light / dark cycle). Before the drought experiment began, all plants were weighed and brought to the same water content level. Water was then withheld from all plants to initiate drought stress. Once visible wilting was observed (96 hours after the start of water withholding), the plants were rewatered to deactivate drought stress. Throughout the experiment, fluorescence measurements were collected daily on three leaves of each plant using a handheld spectrometer.

[0132] Figure 3A The image shows the fluorescence signals produced by plants genetically engineered with a drought stress sensor (V298-27-8) and constitutive fluorescence signaling (DsRed) before water retention. Figure 3A As shown, before drought stress was initiated, the constitutive DsRed signal exhibited strong fluorescence in all leaves, while no fluorescence signal was observed in the leaves of the drought sensor plant (V298-27-8).

[0133] Figure 3B The results show that, upon activation of drought stress, leaves in the drought sensor plant (V298-27-8) exhibited strong fluorescent signals, indicating the presence of drought stress in the plant. In contrast, the constitutive DsRed signaling plant maintained its strong fluorescent signals in all leaves both before and after the application of drought stress.

[0134] Figure 3CThe time course of the average fluorescence signal measured for three different plant groups (V298-27-8, DsRed, and unmodified M82) is depicted. Figure 3C As shown in the figure, shortly after water retention began, the drought sensor plant (V298-27-8) responded to drought stress by producing a distinct fluorescence signal relative to the untransformed M82 plant. Throughout the study, the intensity of this fluorescence signal from the drought sensor plant increased over time until symptoms of drought stress were visible at 96 hours after the initial water retention. After the plant was re-watered at the 96-hour timepoint, the intensity of the fluorescence signal from the drought sensor plant decreased as the stress subsided. Notably, the drought stress sensor plant allows for early identification of drought stress, which can allow for early relief of stress before visible symptoms begin to appear in the plant. Therefore, the sensor plants described in this paper can improve plant health, yield, and provide numerous benefits and efficiencies associated with early intervention to protect plants from stressors.

[0135] Example 2: Soybean sensor plant.

[0136] The responsiveness of sensor plants to fungal stress was assessed using genetically engineered soybean plants (Thorne background) with fungal sensing promoter-reporter pairs. The fungal stressor promoter-reporter pairs contained promoter elements from the tomato chitinase gene, operatively linked to the bfloGFP reporter gene. A total of 28 soybean plants were grown to the second-to-three-leaf stage (V2) in a growth chamber under long-day conditions (16 / 8h light / dark cycle) at a constant temperature of 24°C. The plants (n=7 per group) were then divided into four distinct treatment groups (simulated, fungal, fungal + tebuconazole fungicide, and fungal + thiophanate-methyl fungicide). At time point zero, the simulated group was treated with water and surfactant (0.05% Tween-20), while the other three groups were exposed to the fungus by application of *Cercospora* spores prepared in water + surfactant (0.05% Tween-20) at a concentration of approximately 150,000 spores / mL. For the groups receiving the fungicide, the appropriate fungicide was applied via foliar treatment using a Preval sprayer 24 hours after exposure to fungal spores. Fluorescence was measured by the intensity of fluorescence images collected using a camera in a custom imaging box. Disease progression was visually monitored on a scale of 0-10 (0 for asymptomatic cases and 10 for the most severe symptoms).

[0137] Figure 4AThe time course of visible disease scores for sensor plants exposed to *Cercospora* spores is shown. Plants first exhibited visible disease 192 hours after fungal exposure. Plants exposed to the fungus without fungicide treatment showed higher visible disease scores at 192 hours compared to other plant groups treated with a fungicide 24 hours after fungal exposure.

[0138] Figure 4B A rapid increase in fluorescence signal was observed in all plants exposed to the fungus. Notably, a significant increase in fluorescence signal was measured in all fungal sensor plants within 24 hours of fungal exposure. Therefore, Figure 4B It is shown that, with Figure 4A In contrast, fungal sensor plants provide indications of fungal stress approximately 7 days before visible disease symptoms appear. Fluorescent signals from the fungal sensor plants increased after application of either of the tested fungicides (tebuconazole or cyproconazole). Without being bound by any particular theory, it is believed that the fungicides interact with the promoter-reporter pair to keep the signal on and potentially amplify the induced fluorescence signal. Nevertheless, compared to disease-dependent visible symptoms, fungal stress sensor plants allow for significantly earlier identification of fungal infection, which could allow for earlier stress mitigation before visible symptoms are detected in the plant. Therefore, the sensor plants described herein can improve plant health, yield, and provide numerous benefits and efficiencies associated with early intervention to protect against stress.

[0139] As will be appreciated by those skilled in the art from the preceding detailed description and from the embodiments, drawings and claims, modifications and changes can be made to embodiments of the invention without departing from the scope of the invention as defined in the appended claims.

Claims

1. A method for reducing excessive exposure of the agricultural environment to chemical plant treatments, comprising: a. Capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to produce signals in response to stressors; b. Detecting the signal in response to the stressor in the spectral image of the sensor plant; and c. Based on the detected signals, selectively apply chemical treatments targeting the stressors to a subgroup of plants in the agricultural environment.

2. The method according to claim 1, wherein the stressor is a fungal stressor.

3. The method according to claim 2, wherein the treatment is a fungicide.

4. The method according to claim 3, wherein the fungicide is selected from triazoles, agaricone, and succinate dehydrogenase inhibitors.

5. The method according to claim 1, wherein the stressor is an insect stressor.

6. The method according to claim 5, wherein the treatment is an insecticide.

7. The method according to claim 6, wherein the insecticide is selected from organochlorine, organophosphate, organosulfur, carbamate, formamidin, dinitrophenol, organotin, pyrethroid, neonicotinoid, spinosad, pyrazole, pyridazinone, quinazoline, plant preparations, synergists / activators, antibiotics, fumigants, inorganic substances, environmentally friendly insecticides, and benzoylurea.

8. The method according to claim 1, wherein the chemical plant treatment is a fertilizer.

9. The method according to claim 8, wherein the fertilizer is selected from single-nutrient fertilizers, multi-nutrient fertilizers, and micronutrients.

10. The method of claim 1, wherein the chemical treatment is a herbicide.

11. The method according to claim 10, wherein the herbicide is selected from herbicides that inhibit acetyl-CoA carboxylase (ACCase), herbicides that inhibit acetyllactase synthase (ALS), herbicides that inhibit enolpyruvylshikimate 3-phosphate synthase (EPSPS), auxin-like herbicides, herbicides that inhibit photosystem II, herbicides that inhibit photosystem I, and herbicides that inhibit 4-hydroxyphenylpyruvate dioxygenase.

12. The method of claim 1, wherein the stress level is mapped to plants in the agricultural environment based on the detected signal.

13. A method for improving plant treatment efficiency, comprising: a. Capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to produce signals in response to stressors; b. Detecting the signal in response to the stressor in the spectral image of the sensor plant; and c. Based on the detected signals, selectively apply treatments targeting the stressor to a subgroup of plants in the agricultural environment.

14. The method of claim 13, wherein the stressor is a fungal stressor.

15. The method of claim 14, wherein the treatment is a fungicide.

16. The method according to claim 15, wherein the fungicide is selected from triazoles, agaricone, and succinate dehydrogenase inhibitors.

17. The method of claim 13, wherein the stressor is an insect stressor.

18. The method of claim 17, wherein the treatment is an insecticide.

19. The method according to claim 18, wherein the insecticide is selected from organochlorine, organophosphate, organosulfur, carbamate, formamidin, dinitrophenol, organotin, pyrethroid, neonicotinoid, spinosad, pyrazole, pyridazinone, quinazoline, plant preparations, synergists / activators, antibiotics, fumigants, inorganic substances, environmentally friendly insecticides, and benzoylurea.

20. The method of claim 13, wherein the chemical plant treatment is a fertilizer.

21. The method according to claim 20, wherein the fertilizer is selected from single-nutrient fertilizers, multi-nutrient fertilizers, and micronutrients.

22. The method of claim 13, wherein the chemical treatment is a herbicide.

23. The method according to claim 22, wherein the herbicide is selected from herbicides that inhibit acetyl-CoA carboxylase (ACCase), herbicides that inhibit acetyllactase synthase (ALS), herbicides that inhibit enolpyruvylshikimate 3-phosphate synthase (EPSPS), auxin-like herbicides, herbicides that inhibit photosystem II, herbicides that inhibit photosystem I, and herbicides that inhibit 4-hydroxyphenylpyruvate dioxygenase.

24. The method of claim 13, wherein the stress level is mapped to plants in the agricultural environment based on the detected signal.

25. A method for screening plants to be treated, comprising: a. Capturing spectral images of one or more sensor plants in an agricultural environment, wherein the one or more sensor plants have been genetically engineered to produce signals in response to stressors; b. Detecting the signal in response to the stressor in the spectral image of the sensor plant; and c. Selecting a subgroup of plants in the agricultural environment for treatment based on the detected signals, wherein the treatment is achieved by targeting chemicals that target the stressor.

26. The method of claim 25, wherein the stressor is a fungal stressor.

27. The method of claim 26, wherein the treatment is a fungicide.

28. The method of claim 27, wherein the fungicide is selected from triazoles, agaricone, and succinate dehydrogenase inhibitors.

29. The method of claim 25, wherein the stressor is an insect stressor.

30. The method of claim 29, wherein the treatment is an insecticide.

31. The method according to claim 30, wherein the insecticide is selected from organochlorine, organophosphate, organosulfur, carbamate, formamidin, dinitrophenol, organotin, pyrethroid, neonicotinoid, spinosad, pyrazole, pyridazinone, quinazoline, plant preparations, synergists / activators, antibiotics, fumigants, inorganic substances, environmentally friendly insecticides, and benzoylurea.

32. The method of claim 25, wherein the chemical plant treatment is a fertilizer.

33. The method according to claim 32, wherein the fertilizer is selected from single-nutrient fertilizers, multi-nutrient fertilizers, and micronutrients.

34. The method of claim 25, wherein the chemical treatment is a herbicide.

35. The method according to claim 34, wherein the herbicide is selected from herbicides that inhibit acetyl-CoA carboxylase (ACCase), herbicides that inhibit acetyllactase synthase (ALS), herbicides that inhibit enolpyruvylshikimate 3-phosphate synthase (EPSPS), auxin-like herbicides, herbicides that inhibit photosystem II, herbicides that inhibit photosystem I, and herbicides that inhibit 4-hydroxyphenylpyruvate dioxygenase.

36. The method of claim 25, wherein the stress level is mapped to plants in the agricultural environment based on the detected signal.

37. A method for testing the efficacy of a treatment on plants, comprising: a. Applying a stressor to one or more sensor plants in an agricultural environment, wherein the sensor plants have been genetically engineered to generate signals in response to the stressor; b. Capture spectral images of the sensor plants in the agricultural environment; c. Detecting the signal in response to the stress in the spectral image of the sensor plant; d. Based on the detected signals, selectively apply treatment to plants in the agricultural environment; and e. Record the changes in the signal after the aforementioned processing has been applied.

38. The method of claim 37, wherein the stressor is a fungal stressor.

39. The method of claim 38, wherein the treatment is a fungicide.

40. The method according to claim 39, wherein the fungicide is selected from triazoles, agaricone, and succinate dehydrogenase inhibitors.

41. The method of claim 37, wherein the stressor is an insect stressor.

42. The method of claim 41, wherein the treatment is an insecticide.

43. The method according to claim 42, wherein the insecticide is selected from organochlorine, organophosphate, organosulfur, carbamate, formamidin, dinitrophenol, organotin, pyrethroid, neonicotinoid, spinosad, pyrazole, pyridazinone, quinazoline, plant preparations, synergists / activators, antibiotics, fumigants, inorganic substances, environmentally friendly insecticides, and benzoylurea.

44. The method of claim 37, wherein the chemical plant treatment is a fertilizer.

45. The method according to claim 44, wherein the fertilizer is selected from single-nutrient fertilizers, multi-nutrient fertilizers, and micronutrients.

46. ​​The method of claim 37, wherein the chemical treatment is a herbicide.

47. The method according to claim 46, wherein the herbicide is selected from herbicides that inhibit acetyl-CoA carboxylase (ACCase), herbicides that inhibit acetyllactase synthase (ALS), herbicides that inhibit enolpyruvylshikimate 3-phosphate synthase (EPSPS), auxin-like herbicides, herbicides that inhibit photosystem II, herbicides that inhibit photosystem I, and herbicides that inhibit 4-hydroxyphenylpyruvate dioxygenase.

48. The method of claim 37, wherein the stress level is mapped to plants in the agricultural environment based on the detected signal.

49. A method for testing the efficacy of a treatment on a plant, comprising: a. Capturing spectral images of one or more sensor plants in an agricultural environment, wherein the sensor plants have been genetically engineered to produce signals in response to stressors; b. Detect the signal in response to the stress in the spectral image of the sensor plant; c. Based on the detected signals, selectively apply the treatment to the plants in the agricultural environment; and d. Record the changes in the signal after the aforementioned processing has been applied.

50. The method of claim 49, wherein the stressor is a fungal stressor.

51. The method of claim 50, wherein the treatment is a fungicide.

52. The method according to claim 51, wherein the fungicide is selected from triazoles, agaricone, and succinate dehydrogenase inhibitors.

53. The method of claim 49, wherein the stressor is an insect stressor.

54. The method of claim 53, wherein the treatment is an insecticide.

55. The method according to claim 54, wherein the insecticide is selected from organochlorine, organophosphate, organosulfur, carbamate, formamidin, dinitrophenol, organotin, pyrethroid, neonicotinoid, spinosad, pyrazole, pyridazinone, quinazoline, plant preparations, synergists / activators, antibiotics, fumigants, inorganic substances, environmentally friendly insecticides, and benzoylurea.

56. The method of claim 49, wherein the chemical plant treatment is a fertilizer.

57. The method according to claim 56, wherein the fertilizer is selected from single-nutrient fertilizers, multi-nutrient fertilizers, and micronutrients.

58. The method of claim 49, wherein the chemical treatment is a herbicide.

59. The method according to claim 58, wherein the herbicide is selected from herbicides that inhibit acetyl-CoA carboxylase (ACCase), herbicides that inhibit acetyllactase synthase (ALS), herbicides that inhibit enolpyruvylshikimate 3-phosphate synthase (EPSPS), auxin-like herbicides, herbicides that inhibit photosystem II, herbicides that inhibit photosystem I, and herbicides that inhibit 4-hydroxyphenylpyruvate dioxygenase.

60. The method of claim 49, wherein the stress level is mapped to plants in the agricultural environment based on the detected signal.

61. The method according to any one of claims 1-60, wherein the one or more sensor plants are dicotyledonous plants.

Images