Systems and methods for simulating crop yield based on detection of plant stressors in crops

Abstract

One variant of the method comprises: obtaining an image of a sensitive plant in a crop of a crop type sowed in a geographical area, and the sensitive plant is configured to signal the presence of a stressor; interpreting a first pressure of the stressor in a first sub-area based on a first subset of features extracted from the image; interpreting a second pressure of the stressor in a second sub-area based on a second subset of features extracted from the image; deriving, based on the first pressure and the second pressure, a pressure map representing the pressure of the stressor in the geographical area; obtaining a yield model that links the pressure of the stressor to a crop yield of the crop of the crop type in the geographical area; and predicting, based on the pressure map and the yield model, the crop yield of the crop of the crop type in the geographical area.

Description

[0001] Cross-reference to related applications This application claims the benefits of U.S. Provisional Application No. 63 / 417,247, filed October 18, 2022, and U.S. Provisional Application No. 63 / 338,618, filed May 5, 2022, each of which is incorporated herein by reference in its entirety.

[0002] This application relates to U.S. Patent Application No. 17 / 592,275, filed February 3, 2022, which is a continuation of U.S. Patent Application No. 17 / 217,840, filed March 30, 2021, which is a continuation of U.S. Patent Application No. 16 / 908,526, filed June 22, 2020, which claims the benefit of U.S. Provisional Application No. 62 / 864,401, filed June 20, 2019. Each of the above patent applications is incorporated herein by reference in its entirety. Technical Field

[0003] This invention relates generally to the agricultural field, and more specifically to new and useful methods for detecting stressors in crops and simulating crop yields in the agricultural field. Brief description of the attached diagram Figure 1 It is a flowchart representation of the method; Figure 2A and Figure 2B It is a flowchart representation of a variation of the method; Figure 3 It is a flowchart representation of a variation of the method; Figure 4A and Figure 4B It is a flowchart representation of a variant of the method; and Figure 5 It is a flowchart representation of a variation of the method.

[0005] Implementation Example Description 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 implementations, and examples described herein are optional and are not limited to them. The invention described herein can include any and all combinations of these variations, configurations, implementations, exemplary implementations, and examples.

[0006] 1. Method like Figure 1 , Figure 2A , Figure 2B , Figure 3 , Figure 4A , Figure 4B and Figure 5 As shown, method S100 includes: in block S110, acquiring an image feed of a sensitive plant of a sensitive plant type sown in a set of farmlands within a geographic region, the image feed being recorded during a first time period, the sensitive plant of the sensitive plant type being configured to signal the presence of a set of stressors at the sensitive plant location; in block S112, interpreting a first stressor of a first stressor in the first sub-region of the set of stressors based on features extracted from a first subset of images depicting sensitive plants in a first sub-region within the geographic region from the image feed; in block S112, interpreting a first stressor of a first stressor in the first sub-region of the set of stressors based on features extracted from a first subset of images depicting sensitive plants in a second sub-region within the geographic region from the image feed. Features extracted from a second subset of images of sensitive plants are used to interpret the second stress of the first stressor in the second sub-region; in box S120, a first stress map of the geographic region is derived based on the first and second stresses, the first stress map indicating the presence of the set of stressors in the geographic region during a first time period; in box S122, a yield model is obtained, which associates the stress of the set of stressors in the geographic region with the crop yield of a set of crop types in the target region; and in box S130, based on the first stress map and the yield model, the first crop yield of the first crop type in the set of crop types in the geographic region is predicted.

[0007] A variation of method S100 includes: in block S110, acquiring an image feed of a sensitive plant population of a crop type sown in a farmland, the image feed being recorded by an aerial sensor during a first time period, the sensitive plant population being configured to signal the presence of a set of conditions and including a first group of sensitive plants arranged in a first region of the farmland; in block S112, interpreting a first set of conditions at the plants in the first region based on features extracted from a first subset of images depicting the sensitive plants in the first region from the image feed; and in block S116, acquiring images of the sensitive plants in the first region of the farmland... A set of target conditions defined for the plant; in box S140, a first health score for the plant in the first region is predicted based on a first difference between the first set of conditions and the target conditions; in box S150, based on the first health score, a first treatment pathway is selected for the plant in the first region from a set of treatment pathways, the first treatment pathway being configured to drive the conditions of the plant in the farmland toward the target conditions; in box S160, a prompt is generated to implement the first treatment pathway during a second time period following the first time period; and in box S162, the prompt is sent to a user associated with the farmland.

[0008] A variation of method S100 includes: in block S110, acquiring an image feed of a sensitive plant population of a crop type sown in a target area, wherein the sensitive plant population is configured to signal the presence of a set of stressors at the sensitive plants, the image feed being captured by an optical sensor during a first time period; in block S112, interpreting a first time series of stress data of plants in a first sub-region of a set of sub-regions in the target area based on features extracted from a first subset of images captured in the image feed during the first time period, the first time series of stress data representing changes in the stress of a set of stressors at the plants in the first sub-region during the first time period; in block S114, based on features extracted from the first subset of images captured during the first time period... Features extracted from a second subset of images in the image feed are used to interpret a second time series of stress data of plants in a second sub-region of a set of sub-regions in the target region. This second time series of stress data represents the change in stress of a set of stressors at the plants in the second sub-region during the first time period. In box S122, a yield model is obtained that correlates the stress of the set of stressors in the target region with the crop yield of a set of crop types in the target region. In box S130, based on the first time series of stress data, the second time series of stress data, and the yield model, the first crop yield of the first crop type in the set of crop types in the target region is predicted during a target harvest period after the first time period.

[0009] A variation of method S100 includes: in block S110, acquiring an image feed of a sensitive plant population of a crop of a certain crop type sown in a target area, wherein the sensitive plant population is configured to signal the presence of a set of stressors at the sensitive plants, the image feed being captured by an optical sensor during a first time period; in block S112, interpreting a first stressor in a first sub-region of the set of stressors in the target area based on features extracted from a first subset of images depicting a first set of sensitive plants in the sensitive plant population in the image feed; in block S114, based on features extracted from the images depicting... Features extracted from a second subset of images of a second group of sensitive plants in a sensitive plant population are used to interpret the second stress of the first stressor in a second sub-region within the target area; in box S120, a first stress map of the target area is derived based on the first and second stresses during a first time period; in box S122, a yield model is obtained that correlates the stress of the first stressor in the target area with the crop yield of the crop of that crop type; and in box S130, based on the first stress map and the yield model, the first crop yield of the crop of that crop type in the target area is predicted during a target harvest period after the first time period.

[0010] A variation of method S100 includes: in block S110, acquiring an image feed of a sensitive plant population of a crop type (e.g., cotton, soybean, corn) sown in a field, recorded by an aerial sensor during a first time period, the sensitive plant population being configured to signal the presence of a set of conditions, the sensitive plant population including a first group of sensitive plants arranged in a first sub-region of the field and a second group of sensitive plants arranged in a second sub-region of the field; in block S112, interpreting a first set of conditions at the plants in the first sub-region based on a first set of plant signals (e.g., fluorescence signals) detected in a first image subset depicting the sensitive plants in the first sub-region in the image feed; and in block S114, interpreting a second set of conditions at the plants in the second sub-region based on a second set of signals (e.g., fluorescence signals) detected in a second image subset depicting the sensitive plants in the second sub-region in the image feed. Method S100 further includes: in box S116, obtaining a first set of target conditions defined for plants in a first sub-region; in box S140, predicting a first health score for plants in the first sub-region of farmland based on a first difference between the first set of conditions and the first set of target conditions; and in box S150, selecting a first treatment pathway for plants in the first sub-region based on the first health score.

[0011] In a previous variation, method S100 further includes: in box S116, obtaining a second set of target conditions defined for plants in the second sub-region; in box S140, predicting a second health score for plants in the second sub-region of the farmland based on a second difference between the second set of conditions and the second set of target conditions; and in box S150, selecting a second treatment pathway for plants in the second sub-region based on the second health score. In a variation, method S100 further includes: in box S170, assembling a treatment map based on a first treatment pathway selected for a first sub-region and a second treatment pathway selected for a second sub-region, specifying the location and amount (e.g., frequency and / or quantity) of application for each treatment pathway selected for the crop.

[0012] A variation of method S100 includes: in block S110, acquiring an image feed of a sensitive plant population sown in a crop of a crop type (e.g., cotton, soybean, corn) within a target area (e.g., a target geographic area), the image feed being recorded by an aerial sensor during a first time period, the sensitive plant population being configured to signal the presence of a set of stressors (e.g., abiotic stressors and / or biotic stressors) at the sensitive plants; in block S112, interpreting a first stressor in the first sub-region of the set of stressors based on a first signal (e.g., a fluorescence signal) detected in a first subset of images depicting sensitive plants in a first sub-region within the target area in the image feed; In box S114, a second stressor stress in the second sub-region of the target region is interpreted based on a second signal (e.g., fluorescence signal) detected in a second subset of images depicting sensitive plants in a second sub-region of the target region in the image feed; in box S120, a first stress map of the target region during a first time period is derived based on the first stressor stress and the second stressor stress; in box S122, a yield model is obtained that correlates the stressor stress of the first stressor ...

[0013] In one variant, method S100 further includes: acquiring a stress model configured to predict future stress of a first stressor in the target area based on the stress of a first stressor detected in the target area; and in box S180, predicting a second stress map of the target area during a second time period following a first time period based on the first stress map and the stress model. In response to a second stress map predicting that the third stress of a first stressor in a third sub-region within a target area exceeds a threshold stress, method S100 further includes: in blocks S160 and S162, sending a first prompt to a first group of users associated with the maintenance of crops located in the third sub-region to implement a first mitigation technique from a set of mitigation techniques, the first mitigation technique being configured to alleviate the stress of the first stressor; in blocks S160 and S162, sending a second prompt to a second group of users associated with the manufacture of crop treatments to generate a supply of a first crop treatment corresponding to the first mitigation technique and configured to treat the stress of the first stressor; and in blocks S160 and S162, notifying a third group of users associated with the maintenance of crops near the third sub-region of the prediction of the third stressor stress in the third sub-region during a second time period.

[0014] 2. Application Typically, the framework of method S100 can be executed collaboratively by a computer system (e.g., a remote server, a local computing device, a computer network) and a sensitive plant platform (e.g., a local application or a web-based application) to: detect signals generated by sensitive plants; interpret (e.g., estimate) stressors in crops, on multiple crops, and / or at sensitive plants planted in specific geographic areas based on these sensitive plant signals; derive a set of crop models for specific crops and / or specific crop regions, which are configured to predict various indicators of crop health and / or crop performance, such as the presence of stressors in crops, (e.g., regarding a specific growing season) crop yield, and / or crop resistance (e.g., the rate and / or magnitude of stressor mitigation); and selectively distribute insights, instructions, and / or recommendations related to the detection of stressors in crops to various users associated with the crop supply chain via the sensitive plant platform.

[0015] For example, computer systems working with sensitive plant platforms can selectively distribute alerts to local users (e.g., farmers, agronomists, researchers) associated with crops that are near or contain these sensitive plants and / or users in various sectors or industries associated with the supply chains of these crops, such as users associated with the food, clothing or textiles, distribution (e.g., trucking, shipping, storage), health, government, insurance, and / or chemical industries.

[0016] In one implementation, the system may: acquire images of farmland (e.g., satellite or aerial color or infrared images); scan these images to obtain signals indicating sensitive plants (e.g., fluorescence in specific spectral characteristics of sensitive plants or characteristics of specific stressors present at the sensitive plants); identify populations of sensitive plants sown in specific geographic areas depicted in these images based on these characteristic signals (or “baseline signals”) detected in these images; interpret stressor stress within the sensitive plant population based on the presence and / or amplitude of optical signals present at the sensitive plants; and integrate a stress map for a specific geographic area, which depicts the stress of a set of stressors in the sensitive plant population during a specific time period.

[0017] The system can continuously acquire images of sensitive plants within sensitive plant populations over time to integrate time series of stress data for that specific geographic area. The system can then utilize these time series stress data, combined with time series of stress data collected across numerous sensitive plant populations spanning many crops and / or many regions, to predict future stress from stressors in that specific geographic area based on the current stress map. The system can also fuse this time series stress data with other data collected for that specific geographic area, such as time series weather data and / or time series crop treatment data, to predict future stress from stressors in that specific geographic area based on (currently) detected stress, applied crop treatments, average temperature, average humidity, average rainfall, etc., corresponding to that specific geographic area.

[0018] Furthermore, the system can estimate changes in expected crop yields based on the detection and / or prediction of stressors in a specific geographic area, such as based on historical crop data collected for that specific geographic area (including time series of stress data and / or corresponding time series crop yield data). Therefore, based on these predicted changes in stressor stress and / or expected crop yields, the system can selectively generate and distribute tips related to the detection and / or mitigation of crops in that specific geographic area to users.

[0019] 2.1 Regional Simulation In one implementation, the system can utilize fluorescence signals expressed by sensitive plants distributed throughout a geographic area (such as sensitive plants sown in several crops and / or on farmland within the geographic area) to derive insights into crop health status, stressors (e.g., insects, fungi, dehydration, flooding, heat stress, cold stress, soil stressors) and / or crop yields of different crop types within that geographic area.

[0020] For example, the system can: acquire images (e.g., spectral images) of sensitive plants planted throughout a geographic area; extract features indicating the stress of one or more stressors in the sensitive plants in that geographic area, such as the intensity of fluorescence at a specific wavelength; interpolate or extrapolate these stressors in the sensitive plants to other plants (e.g., sensitive and non-sensitive plants) in the same geographic area; and detect and / or predict changes in these stressors over time to predict crop yield for each crop type in that geographic area. Therefore, the system can: derive a yield profile for the geographic area that defines the predicted crop yield for each crop type (e.g., soybean, tomato, corn, cotton) present in the geographic area; and share this predicted yield profile with users associated with the crops in that geographic area (e.g., farmers, food suppliers, food processing facility managers, pesticide and / or fertilizer manufacturers, etc.), enabling these users to better predict outcomes associated with the crops in that specific geographic area.

[0021] 2.2 Local Crop Simulation Additionally or alternatively, in another embodiment, the system may utilize fluorescence signals expressed by sensitive plants sown in a particular crop or field to derive insights into crop health, the diffusion and / or distribution of stressor stress within the crop, and / or the crop yield of that particular crop. Specifically, the system may utilize time series of crop data collected over one or more growth cycles of the crop (including stress data time series, environmental data time series (e.g., weather data, treatment data), yield data time series, etc.) to: derive a high-resolution stress map of the crop (representing stressor stress and / or stress gradients at plants in various regions of the crop); predict future stressor stress in different regions of the crop; characterize the health of individual plants or groups of plants within the crop; predict crop yield over a specific growth cycle based on the health of plants in the crop over time; and / or suggest customized crop treatments for different regions of the crop to mitigate predicted stressor stress, thereby more precisely modulating plant health across the entire crop.

[0022] Furthermore, in this embodiment, the system can utilize time-series crop data collected for the crop to derive a set of target plant conditions (e.g., soil pH, soil nitrogen levels, irrigation levels, fertilizer levels, pest population size, fungal growth) for specific plant groups within the crop and / or located in different regions of the crop. This set of target plant conditions is predicted to maximize the crop yield of that particular crop. The system can then detect deviations from this set of target conditions in different regions of the crop (e.g., throughout the entire growth cycle), and therefore, for implementations in specific regions of the crop, selectively suggest treatments configured to align the plant conditions in those regions towards the set of target plant conditions. Thus, by prompting alignment of plant conditions across the entire crop with a set of target conditions derived for that particular crop, the system can drive crop yield toward the maximum predicted crop yield for that crop.

[0023] 3. Sensitive plants Typically, sensitive plants include a promoter-reporter pair configured to detect stressors present in the sensitive plant and generate a detectable signal (e.g., in the electromagnetic spectrum) to indicate the presence of these stressors in the sensitive plant or in a region of the crop in which the sensitive plant is located. Specifically, sensitive plants can be transgenic to include: a promoter gene sequence (hereinafter referred to as the “promoter”) configured to activate in the presence of a specific stressor (e.g., “associated” with a specific stressor); and a reporter gene sequence (hereinafter referred to as the “reporter”) configured to activate in response to activation of the promoter, encoding a specific molecule (e.g., a fluorescent molecule) configured to express a detectable signal (e.g., a fluorescent signal). This promoter-reporter pair can be incorporated into sensitive plants using genetic engineering techniques that associate the expression of a promoter in response to a specific biological stress with a reporter that generates a measurable signal when the promoter is expressed.

[0024] In one embodiment, the sensitive plant can be configured to include a promoter-reporter pair configured to signal the presence of a specific biotic and / or abiotic stress experienced by the sensitive plant, such as pests, diseases, water, heat, soil health conditions, and / or nutrient stress or deficiency. For example, the sensitive plant can be transgenic to include a promoter having activity associated with the presence of a stressor, such as fungi, bacteria, pests, heat, water (e.g., dehydration and / or overhydration), disease or nutrient stress (e.g., nutrient deficiency), phytoplasmic disease, poor soil health conditions (e.g., soil pH), etc. The sensitive plant can also be transgenic to include a reporter paired with the promoter, and the reporter is configured to generate a detectable signal, such as an electromagnetic signal in the visible or infrared spectrum (e.g., a fluorescence signal), when the corresponding promoter is activated. For example, the sensitive plant can be transgenic to fluoresce in the presence of a specific stressor (and proportionally to the stress of the specific stressor) (i.e., absorbing photons at one frequency and emitting photons at different frequencies). Therefore, through the expression of reporters, promoter-reporter pairs can generate measurable signals of specific biological stresses or traits in sensitive plants.

[0025] In another embodiment, the susceptible plant can be transgenic to include multiple promoter-reporter pairs, each promoter-reporter pair indicating a specific biological process occurring in the susceptible plant cell in response to a specific stressor. For example, the susceptible plant may include: a first promoter-reporter pair comprising a first promoter representing a first biological process associated with the presence of a water stressor, the first promoter being labeled with a red fluorescent protein reporter; and a second promoter-reporter pair comprising a second promoter representing a second biological process associated with the presence of a fungal stressor, the second promoter being labeled with a yellow fluorescent protein reporter. Thus, the susceptible plant can signal the presence of multiple stressors by transgenic susceptible plant cells to include a set of promoter-reporter pairs.

[0026] In one variant, the susceptible plant can be transgenic to include a complex gene sensing network representing a set of combined promoter-reporter pairs. In this variant, the susceptible plant can utilize a small number of reporters (e.g., fluorescent compounds) to monitor and detect a larger number of promoters and / or biological processes, and thus simplify the detection process by reducing the number of reporters required, since fluorescent compounds exhibit broad spectral characteristics and it may be difficult to simultaneously measure and distinguish large numbers of these fluorescent compounds.

[0027] 3.1 Variation: Plant Identifier In one variant, a susceptible plant population can be transgenic to express a detectable baseline signal (e.g., fluorescence signal) associated with susceptible plants within that population. Specifically, the genome of each susceptible plant in the susceptible plant population can be transgenic to include an identifier gene (hereinafter referred to as the "identifier") configured to express a baseline signal (e.g., fluorescence signal) containing identifying information about the susceptible plant (e.g., crop location, sensor type, crop type), independent of the presence of stressors at the susceptible plant location within the susceptible plant population.

[0028] In one implementation, a sensitive plant population can be configured to express baseline signal characteristics of sensitive plants growing in a specific region. For example, a first sensitive plant population can be configured to express a first baseline signal associated with a first geographic region, which corresponds to fluorescence within a first wavelength range. A second sensitive plant population can be configured to express a second baseline signal associated with a second geographic region, which corresponds to fluorescence within a second wavelength range different from the first wavelength range. Therefore, the system can: acquire one and / or multiple images of a larger geographic region including the first and second geographic regions; distinguish sensitive plants in the first and second geographic regions based on the detection of the first and second baseline signals in these images; thereby interpreting stressor pressure, generating stress maps, and deriving yield predictions for both the first and second geographic regions, etc.

[0029] Specifically, in one example, a susceptible plant population can be genetically modified to include a fluorescent tag configured to express a first fluorescence signal (e.g., red, yellow, and / or green fluorescence) within a first wavelength range (e.g., in the presence of light). The system can associate the fluorescent tag and the corresponding first fluorescence signal with a first region and / or crop containing the susceptible plant population. Specifically, in this example, the system can store a first fluorescence spectrum depicting the fluorescence signal within the first wavelength range in a first regional crop profile associated with the first region within a set of regional crop profiles. The system can then associate the susceptible plant and / or the susceptible plant population containing the susceptible plant with the first fluorescence signal within the first wavelength range. Subsequently, the system can: acquire an image feed of the geographic area including the susceptible plant and / or the susceptible plant population recorded by an aerial sensor (e.g., a satellite); and identify the susceptible plant and / or the susceptible plant population in the image feed based on the detection of the first fluorescence signal expressed by the susceptible plant (i.e., the baseline signal).

[0030] The system may also append the following to the crop profile of the first region: the sensitive plant type of the sensitive plant in the sensitive plant population, such as a specific promoter-reporter pair configured to detect signals of a specific stressor among a set of stressors; and / or the crop type of the sensitive plant in the sensitive plant population (e.g., cotton, corn, soybean, grape). The sensitive plant population (e.g., sensitive plant seeds and / or sensitive plant seedlings) may then be distributed (e.g., planted) among one crop and / or multiple crops in the first region (e.g., by farmers or other users associated with the crop). Subsequently (e.g., during the growth period of the sensitive plant population and / or the crop), the system may acquire image feeds of the first region recorded by satellite at approximately a target frequency (e.g., weekly, bi-weekly, monthly). Then, in response to the detection of a fluorescence signal in the first image of the image feed, the system may: acquire the crop profile of that set of regions; and, in response to the detected fluorescence signal corresponding to a first fluorescence signal within a first wavelength range, identify the detected fluorescence signal as corresponding to a sensitive plant population of a sensitive plant type and / or crop type located in the first region.

[0031] Furthermore, in the aforementioned example, the sensitive plant population can be transgenic to include a promoter-reporter pair configured to detect a first stressor at the sensitive plant. This promoter-reporter pair includes: a promoter configured to express in response to detection of the first stressor; and a reporter configured to express a second fluorescence signal in a second wavelength range different from the first wavelength range in response to the expression of the promoter. Therefore, in this example, the sensitive plant can be configured to include a first fluorescent tag configured to express a first fluorescence signal within the first wavelength range, such that the expression of the first fluorescence signal does not interfere with the detection of the second fluorescence signal indicating the presence of the first stressor, thereby reducing errors due to the detection of additive or overlapping fluorescence signals.

[0032] Additionally or alternatively, in another embodiment, each sensitive plant population can be configured to express a baseline signal associated with a specific crop type within a set of crop types. For example, a first sensitive plant population can be configured to express a first baseline signal associated with a first crop type (e.g., soybean), which corresponds to fluorescence within a first wavelength range. A second sensitive plant population can be configured to express a second baseline signal associated with a second crop type (e.g., tomato), which corresponds to fluorescence within a second wavelength range different from the first wavelength range. Therefore, the system can: acquire one and / or multiple images of regions including both the first and second crop types; distinguish between sensitive plants of the first and second crop types based on the detection of the first and second baseline signals in these images; thereby interpreting stressor pressure, generating stress maps, deriving yield predictions for both the first and second crop types, etc.

[0033] Additionally or alternatively, in one variant, the susceptible plant may be transgenic to include an identifier configured to express a detectable signal (e.g., a fluorescence signal) associated with a growth stage of the susceptible plant. Additionally, in this variant, the susceptible plant may be transgenic to include a set of identifiers, each of which is configured to express a detectable signal from a set of detectable signals associated with a specific growth stage of the susceptible plant. For example, the susceptible plant and / or population of susceptible plants may be configured to include: a first identifier configured to express a first baseline signal during the initial growth stage (e.g., seedling, and / or early vegetative stage); a second identifier configured to express a second baseline signal during the primary growth stage (e.g., budding and / or flowering stage); and a third identifier configured to express a third baseline signal during the final growth stage (e.g., maturity). Thus, the system can track the growth of the susceptible plant throughout its entire life cycle and, based on the detection of these baseline signals at various stages of the susceptible plant's life cycle, derive insights and information related to the crop health and / or yield of a particular crop.

[0034] 4. Stressor detection The system can detect and interpret signals generated by sensitive plants by extracting features from images of sensitive plants that are correlated with the presence of specific stressors at the sensitive plant. More specifically, the system can acquire digital images (e.g., spectral images) of sensitive plants and / or plant canopies (e.g., sensitive plants and surrounding plants) captured by optical sensors (e.g., multispectral or hyperspectral imaging devices) to detect reporter sub-signals and interpret stressors present in these sensitive plants based on these reporter sub-signals.

[0035] Specifically, optical devices can (e.g., in the form of color or multispectral images) record optical signals generated by sensitive plants; and computer systems can extract features (e.g., intensity at a specific wavelength) from these images, interpret the presence and / or magnitude of specific stressors exposed to sensitive plants based on these features, and interpolate or extrapolate the health status and environmental conditions of nearby plants (e.g., non-sensitive plants; other unimaged sensitive plants) based on the presence and / or magnitude of stressors indicated by the sensitive plants.

[0036] For example, a computer system can extract the intensity of specific wavelengths corresponding to specific compounds (e.g., proteins) in a sensitive plant and, based on the intensity of these wavelengths (such as based on a stored model that associates plant stressors with wavelengths of interest, based on known characteristics of promoter and reporter genes in the sensitive plant), interpret the stress of exposure to a specific stressor in the sensitive plant before the stressor becomes visually (i.e., with the human eye) discernible in the visible spectrum. The computer system can also interpolate or extrapolate the presence or magnitude of these stressors in other plants near the sensitive plant to predict the overall health of the crop or farmland.

[0037] Specifically, in one example, the system may: acquire a first subset of images (e.g., one image, a series of images) of sensitive plants sown in farmland within a geographic area, the sensitive plants being configured to signal stress from a set of stressors in the plants; extract a first set of fluorescence measurements (such as a first set of fluorescence intensities) corresponding to a first wavelength range from the first subset of images; extract a second set of fluorescence measurements (such as a second set of fluorescence intensities) corresponding to a second wavelength range from the first subset of images; interpret a first stressor of a first stressor among the set of stressors in the plants within the geographic area based on the first set of fluorescence measurements; and interpret a second stressor of a second stressor among the set of stressors in the plants within the geographic area based on the second set of fluorescence measurements.

[0038] The system can acquire images of sensitive plants captured by optical sensors, such as those from handheld cameras, handheld spectrometers, mobile phones, UAVs, satellites, or any other devices, including high-resolution spectrometers, devices including band-specific filters, or devices otherwise configured to detect electromagnetic radiation, fluorescence, luminescence, or any other optical signals emitted by sensitive plants in the presence of a specific stressor. More specifically, the system can: acquire hyperspectral images of leaf area, the entire sensitive plant, a group of similar sensitive plants, the entire sensitive plant crop, or many fields of sensitive plants recorded by remote sensing systems (e.g., satellites, in aircraft, in manned or unmanned field equipment such as tractors, in handheld devices, or in booms or poles installed in the field); extract spectral properties from these hyperspectral images; and interpret the presence and / or magnitude of a specific stressor present in the sensitive plant, flora, crop, or field based on the correlation between the spectral properties extracted from these hyperspectral images and known properties (e.g., fluorescence) expressed by a specific promoter-reporter pair in the sensitive plant.

[0039] 5. Sensitive Plant Platform The system can compile large amounts of crop data (such as historical stress data and / or (near) real-time stress data, treatment data, environmental data and / or crop yield data) collected for sensitive plant populations planted, grown and / or harvested across multiple crops and / or multiple regions (e.g., geographic regions) to derive insights and additional information related to crop health, supply and / or management practices for specific crops, specific regions and / or global crop supply.

[0040] The system can provide this data, instructions, insights, suggestions, information and / or recommendations to users associated with specific crops, crop regions and / or crop types (such as farmers, food suppliers, insurance agents (e.g., insurance agents associated with farm assessments), retailers, etc.), enabling these users to monitor stressors in these crops and / or mitigate the risks associated with these stresses.

[0041] 5.1 Crop Profile In one implementation, the system can compile sensitive plant data collected over time for a specific crop and / or a specific region (e.g., including many crops) into a set of crop profiles for that specific crop and / or region. Therefore, the crop profile may include information representing historical sensitive plant data for the crop, such as: the type of stressor detected, the stress level of the detected stressor, and changes in the stress level of the detected stressor over time.

[0042] The system can also collect additional information about the crop from the user, such as: the crop planting schedule; the crop harvesting schedule; irrigation frequency; irrigation volume; the types of treatments typically applied to the crop; information about soil health; information about crop nutrients; and so on. Therefore, using this additional information, the system can estimate crop stress with increased sensitivity and confidence, allowing users to have greater confidence in the information provided by the system and obtain additional and more accurate insights and information about the crop's health.

[0043] 5.1.1 Baseline pressure curve In one variant, the system can identify patterns and / or trends in sensitive plant data collected over time (e.g., during the growing season) for a specific crop or region. Specifically, in this embodiment, the system can utilize sensitive plant data collected for a specific crop or region over one or more growing seasons to derive a baseline stress curve (e.g., an annual stress curve) representing detected or anticipated changes in stressor stress in that specific crop or region during a specific time period (such as corresponding to the growing season and / or a specific time within a year).

[0044] For example, during the first growing season of a crop, the system can: monitor reporter signals expressed by sensitive plants sown in the crop; derive a time series of stressors at set intervals (e.g., weekly, bi-weekly, monthly) using the detection of these reporter signals over time; and extract insights and information about: water movement on the crop; sunlight exposure on the crop (e.g., daily, weekly, monthly, seasonal); and the timing and / or movement of stressors such as insects, fungi, and / or nutrient deficiencies, based on the time series of stressors. Thus, the computer system can integrate the time series of stress and / or stressor data (corresponding to water movement, sunlight exposure, and / or stressors of other stressors) into a set of baseline stress curves for a particular crop. The system can then use these baseline stress curves to: predict crop and / or region conditions at the start of subsequent growing seasons and / or throughout the entire subsequent growing season; and / or, based on the predicted plant conditions, suggest implementation methods for cultivation practices and / or stressor treatments at the crop.

[0045] In one implementation, during the first growth cycle of a plant sown in a first region (e.g., crop, farmland, geographic area), the system can: interpret a first set of stresses (each stress in the first set of stresses corresponds to a specific stressor in the set of stressors) at the sensitive plant in the first region based on a first image or a first set of images captured at a first time and depicting the sensitive plant in the first region at the first time; interpret a second set of stresses at the sensitive plant in the first region based on a second image or a second set of images captured at a second time after the first time and depicting the sensitive plant in the first region at the second time; and interpret a third set of stresses at the sensitive plant in the first region based on a third image or a third set of images captured at a third time after the second time and depicting the sensitive plant in the first region at the third time.

[0046] The system can then integrate time series of pressure data representing changes in the pressure of this set of stressors in a first region during the growth cycle. This time series includes: a first time value corresponding to a first time point, associated with a first set of pressures for the set of stressors; a second time value corresponding to a second time point, associated with a second set of pressures for the set of stressors; and a third time value corresponding to a third time point, associated with a third set of pressures for the set of stressors. Based on this time series of pressure data, the system can then derive a set of baseline pressure curves representing the observed changes in the pressure of this set of stressors over time. Subsequently, the system can use this set of baseline pressure curves to predict the changes in the pressure of this set of stressors over time. For example, the system can: derive a first baseline pressure curve representing the change of pressure of insect stressors in a first region over time within the set of baseline pressure curves; derive a second baseline pressure curve representing the change of pressure of fungal stressors in a first region over time within the set of baseline pressure curves; and / or derive a third baseline pressure curve representing the change of pressure of soil stressors (e.g., soil pH, nitrogen level) in a first region over time within the set of baseline pressure curves.

[0047] The system can also refine the baseline stress curve of a specific stressor over time within a specific region, for example, based on additional time-series stress data collected for a specific stressor within a specific region (e.g., a specific crop, a specific geographic area).

[0048] 5.2 Regional Pressure Map In one implementation, the system can utilize the detection of stressor stress at sensitive plants (e.g., individual plants, clusters, and / or crops) sown in a specific area to generate a stress map representing abiotic and / or biotic stressors detected in that specific area during a corresponding detection time period.

[0049] For example, the system may: acquire a first image of a first crop of sensitive plants located in a first geographic area during a first detection time period in a satellite image feed (e.g., recorded by an optical sensor mounted on a satellite); acquire a second image of a second crop of sensitive plants located in the first geographic area during the first detection time period in a satellite image feed; and acquire a third image of a third crop of sensitive plants located in the first geographic area during the first detection time period in a satellite image feed.

[0050] The system can then: interpret the first stressor stress in the first crop of a set of stressors based on optical signals (e.g., fluorescence signals) expressed by sensitive plants in the first crop of sensitive plants and detected in the first image; interpret the second stressor stress in the first crop of sensitive plants based on optical signals expressed by sensitive plants in the second crop of sensitive plants and detected in the second image; and interpret the third stressor stress in the third crop of sensitive plants based on optical signals expressed by sensitive plants in the third crop of sensitive plants and detected in the third image. Then, at a first time after the first detection period, the system can: interpret a first stress map indicating the presence of the set of stressors in the first geographic area during the first detection period based on the first stressor stress, the second stressor stress, and the third stressor stress.

[0051] Additionally and / or alternatively, in another embodiment, the system may generate a stress map of a specific stressor. For example, the system may: generate a first stress map indicating the presence of a first stressor from a set of stressors in a specific region; and generate a second stress map indicating the presence of a second stressor from the set of stressors in the specific region. Additionally and / or alternatively, in yet another embodiment, the system may generate a stress map of a specific crop type. For example, the system may: generate a first stress map indicating the presence of a set of stressors in a first crop type (e.g., cotton) in a specific region; and generate a second stress map indicating the presence of the set of stressors in a second crop type (e.g., soybean) in the specific region.

[0052] In each of these implementations, the system can repeat the process over time to generate an additional stress map representing a set of stressors present in a specific region and / or in a specific crop type. By repeating this process over time, the system can provide data and / or recommendations to users associated with crops in these regions, thereby enabling proactive mitigation of stressors in these crops. Furthermore, the system can utilize the time series of stress data represented in these stress maps to derive insights and information related to changes in stresses and / or stressors present in these regions (and / or specific crops) over time.

[0053] 5.2.1 Regional Pressure Map: Interpolation In one implementation, the system can interpolate the stress in plants and / or crops planted between different locations (e.g., crops, farmland, geographic locations) using detected and / or predicted stresses of stressors in plants at different locations (e.g., crops, farmland, geographic locations). Specifically, in this variant, the system can interpolate between stressor stresses derived from plants in a first sub-region and a second sub-region to predict one or more stressors present in plants planted in crops between the first and second sub-regions. The system can then generate a stress map of a geographic region (including the first sub-region, the second sub-region, and a series of regions between the first and second sub-regions) representing the predicted stresses of stressors across the entire sub-region, regardless of the presence of sensitive plants in each of these sub-regions.

[0054] For example, the system can: interpret a first stressor stress in a first sub-region of the geographic region based on features extracted from a first subset of images depicting sensitive plants in a first sub-region during a first time period, from an image feed of sensitive plants in the geographic region; and interpret a second stressor stress in a second sub-region of the geographic region based on features extracted from a second subset of images depicting sensitive plants in a second sub-region during the first time period, from an image feed. The system can then: predict a third stressor stress in a third sub-region of the geographic region based on the first stressor stress in the first sub-region and the second stressor stress in the second sub-region; and derive a first stress map of the geographic region during the first time period based on the first stressor stress, the second stressor stress, and the third stressor stress. Additionally and / or alternatively, in this embodiment, the system can similarly: predict a fourth stressor stress in a fourth sub-region, predict a fifth stressor stress in a fifth sub-region, predict a sixth stressor stress in a sixth sub-region, etc.; and update the first stress map accordingly.

[0055] In one variant, the system can utilize environmental data collected from crops within a geographic region to more accurately predict stressor pressures in sub-regions of the entire geographic region.

[0056] 5.2.2 Real-time pressure prediction In one implementation, the system can utilize the detection of a first stressor's first stress within a first region (e.g., crop, farmland, geographical area) to predict a second stressor's second stressor in a second region adjacent to the first region (e.g., adjacent to the first region, bordering the first region, or near the first region). For example, the system can: implement the above-described methods and techniques to predict the first stressor's first stressor in a first farmland where a first crop type is grown; and predict the second stressor's second stressor in a second farmland adjacent to the first farmland where a first crop type is grown, based on known and / or predicted patterns of the first stressor's movement, diffusion, growth, attenuation, etc.

[0057] In one example, the system may: interpret the first stress of a first stressor in the first crop, which contains a group of sensitive plants configured to signal the stress of the first stressor, based on features extracted from an image of a first crop captured at a first time; and use the first stress of the first stressor to predict the second stress of the first stressor in the second crop at approximately a first time, based on known and / or derived correlations between the stress of the first stressor in the first crop and the stress of the first stressor in the second crop.

[0058] In one variant, the system can derive a stress model that correlates the stress of a set of stressors in a first region (e.g., crop, farmland, geographic area) with the stress of that same set of stressors in a second region.

[0059] For example, during the first growth stage of a series of growth stages, the system can: acquire an image feed of a group of sensitive plants captured during the first growth stage, which are sown in a first crop and configured to signal the stress of a set of stressors at the group of sensitive plants; and interpret a first time series of stress data based on features extracted from the timestamped images in the image feed, the first time series of stress data representing the changes in the stress of the set of stressors at the group of sensitive plants throughout the first growth stage. For example, the first time series of stress data can be defined as: a first stressor stress of a first stressor in the set of stressors at a first time during an initial time period; a second stressor stress of the first stressor at a second time after the first time during the initial time period; a third stressor stress of the first stressor at a third time after the second time during the initial time period; and so on. Similarly, the first time series of stress data can include: a time series of the stress of a second stressor in the set of stressors throughout the initial time period; a time series of the stress of a third stressor in the set of stressors throughout the initial time period; and so on.

[0060] Furthermore, in the aforementioned example, the system may: prompt one or more users (e.g., farmers, crop owners, crop operators) associated with a second crop (located near the first crop and excluding sensitive plants) to manually input a second time series of stress data captured for the second crop during an initial time period. For example, farmers and / or agronomists may: record time series of soil and / or plant water content in the second crop; record time series of nitrogen uptake in plants within the second crop; record time series of soil pH levels within the second crop; record time series of insect and / or fungal density and / or presence within the second crop; and so on. Upon receiving this compiled time series stress data about the second crop from the users, the system may: implement regression, machine learning, deep learning, and / or other techniques to derive the correlation between the stress of that set of stressors in the first crop and the stress of that set of stressors in the second crop; and store these correlations in a stress model configured to predict the stress of that set of stressors in the second crop based on the stress of the set of stressors detected in the first crop.

[0061] 5.3 Pressure Prediction: Changes over Time In one variant, the system can predict the future stress of a stressor in plants within a specific region based on the current stress of the stressor in plants within that specific region. Specifically, in this variant, the system can: interpret the first stress of a first stressor in a first crop, comprising a group of sensitive plants configured to signal the stress of the first stressor, based on features extracted from an image of a first crop captured at a first time; and predict the second stress of the first stressor in the first crop at a second time after the first time, based on the observed and / or predicted diffusion (e.g., dispersion or movement, growth, decay) of the first stressor within the first crop over time.

[0062] In one implementation, the system can derive a stress model configured to predict future stress of stressors in a particular crop and / or region based on (currently) detected stress in that crop and / or region. Specifically, the system can utilize time series of stressor data to predict current or future stress of stressors in a specific geographic area, the time series representing the presence and / or magnitude of a set of stressors detectable in sensitive plants within that specific geographic area over a specific time period.

[0063] For example, during a first time period, the system can: interpret the first pressure of a first stressor in a first sub-region of the geographic region; interpret the second pressure of a first stressor in a second sub-region of the geographic region; and interpret the third pressure of a first stressor in a third sub-region of the geographic region. The system can then derive a first pressure map based on the first, second, and third pressures, indicating the presence of a first stressor in the geographic region during the first time period. Then, during a second time period, the system can: interpret the fourth pressure of a first stressor in the first sub-region; interpret the fifth pressure of a first stressor in the second sub-region; and interpret the sixth pressure of a first stressor in the third sub-region. The system can then derive a second pressure map based on the fourth, fifth, and sixth pressures, indicating the presence of a first stressor in the geographic region during the second time period. The system can then use the first and second pressure maps to derive a pressure model configured to predict the time-varying pressure of a first stressor in the geographic region.

[0064] Therefore, in the aforementioned example, during the third time period following the second time period, the system can: derive a third stress map based on the detected stress of the first stressor in the first sub-region, the second sub-region, and / or the third sub-region, the third stress map indicating the presence of the first stressor in the geographic region during the third time period; obtain a stress model; and predict a fourth stress map based on the third stress map and the stress model, the fourth stress map indicating the presence of the first stressor in the geographic region during the fourth time period following the third time period.

[0065] Furthermore, in another embodiment, the system can additionally acquire environmental data time series corresponding to the time series of stressor data for a specific crop and / or region, such as weather data time series and / or treatment data time series (e.g., crop treatment data). In this embodiment, the system can fuse the environmental data time series with the stressor data time series to derive a stress model configured to predict future stress and / or stress changes of stressors in the specific crop and / or region based on detected stress and / or environmental data (e.g., current crop treatment, weather, crop management information) of the stressors detected in the specific crop and / or region.

[0066] Therefore, the system can derive correlations between stressor data (e.g., stressor stress recorded over time) and recorded environmental data for a specific crop and / or region to: identify stressor treatments best suited to that specific crop and / or region; and predict changes in stressor stress in that specific crop and / or region based on detected stressor stress and / or recorded environmental data. Thus, by tracking historical stressor data for that specific region or crop over time (e.g., within a month, within a crop season, or across multiple crop seasons), the system can derive correlations configured to predict future stressor stress in that specific region or crop, enabling users associated with that crop (e.g., farmers, agronomists, field workers) to quickly implement techniques configured to mitigate and / or prevent stressor stress and thus increase crop yields and / or reduce costs and / or crop losses associated with treating stressors in that crop.

[0067] 5.3.1 Environmental Data: Diffusion Conditions In one variant, the system can use time series of environmental data recorded for a specific region (e.g., crops, farmland, geographic area) to predict current and / or future stress of stressors in that specific region.

[0068] In one implementation, the system can predict the change in stress of a specific stressor over time based on environmental data time series. Specifically, the system can: predict a first stressor present in plants sown within a crop area based on a first image of sensitive plants captured at a first time; acquire a first time series of environmental data (such as weather data, treatment data, observed stressor data, etc.) corresponding to environmental conditions within the crop area during a first time period including the first time; and predict a second stressor of the first stressor at future times based on the first stressor and the first time series of environmental data. In particular, the system can utilize known and / or derived correlations between environmental data and the change in stress of the first stressor over time to predict the second stressor of the first stressor at future times.

[0069] Furthermore, in the aforementioned embodiments, the system can utilize the detected stress of a specific stressor in the first region to predict the stress of that specific stressor in a second region (e.g., near the first region) based on environmental data recorded for each of these regions.

[0070] Additionally or alternatively, in another embodiment, the system may utilize known characteristics of a specific stressor or multiple stressors to predict changes in the stress of a specific stressor over time. For example, at a first point during the growing season of crops in a specific region, the system may: predict a first stress of fungal stressor in a first sub-region of that specific region; and predict a second stress of fungal stressor in a second sub-region of that specific region. The system may then: acquire a set of diffusion conditions defined for the fungal stressor and defining the conditions required for the spread of the fungal stressor among plants in that specific region, such as minimum and / or maximum temperatures (e.g., air temperature), minimum and / or maximum rainfall, minimum and / or maximum sunlight exposure, a set of soil conditions (e.g., nitrogen level, pH level), plant maturity in that specific region, etc. The system can then: acquire time series of environmental data captured for a specific area during a time period including a first time, including time series of conditions (e.g., weather, treatment) at plants in that specific area; characterize the correlation between the set of diffusion conditions and the time series of environmental data; and, in response to the correlation exceeding a threshold correlation, predict the diffusion of fungal stressors in that specific area, such as diffusion at a first rate and / or according to a first pattern or distribution. Based on the predicted diffusion, the system can therefore predict: a third pressure of fungal stressors in a first sub-region at a second time following the first time; and a fourth pressure of fungal stressors in a second sub-region at the second time.

[0071] 5.4 Production Forecast In one implementation, the system can predict the yield of a specific crop type (e.g., soybean, tomato, cotton, lettuce) and / or a specific crop within a specific geographical area.

[0072] Typically, a system can predict the yield of a crop based on the stress of stressors present in a specific crop type. Specifically, the system can: utilize images of crops within a geographic region to detect optical signals expressed by sensitive plants present in those crops; predict the stress of a set of stressors throughout the geographic region based on the detected optical signals; derive a stress map representing the magnitude and / or distribution of the stress of that set of stressors throughout the geographic region based on the predicted stress of that set of stressors; and predict the yield of a specific crop type within the geographic region based on the derived stress map.

[0073] For example, the system can: predict a first stress of the first stressor in a first crop of a first crop type (including a first group of sensitive plants configured to signal the presence of the first stressor) within a geographic area; predict a second stress of the first stressor in a second crop of the first crop type (including a second group of sensitive plants configured to signal the presence of the first stressor) within the geographic area; predict a third stress of the first stressor in a third crop of the first crop type (including a third group of sensitive plants configured to signal the presence of the first stressor) within the geographic area; and derive a stress map representing the stress of the first stressor throughout the geographic area based on the first stressor, the second stressor, and the third stressor. The system can then predict the crop yield of the first crop type within the geographic area based on the stress map. The system can then repeat this process to similarly predict the crop yield of each of the set of crop types present in the geographic area.

[0074] In one variant, the system can use environmental data (including weather data, treatment data, and / or observed stressor data) recorded for a geographic region in conjunction with a stress map to predict crop yield. For example, the system can: derive a stress map representing conditions (such as soil conditions (e.g., soil pH, nitrogen content), insect or fungal presence, disease, drought, or flood) over an entire geographic region including a group of crops of a first crop type; acquire a time series of environmental data recorded for the geographic region during the growing season; acquire a time series of treatment data recorded for the geographic region during the growing season, such as the type and / or dosage (e.g., quantity, duration) of treatments applied to one or more crops (e.g., pesticides, fungicides, water, soil pH adjusters, fertilizers); and predict the crop yield of the first crop type within the geographic region based on the stress map and the environmental data time series.

[0075] 5.4.1 Production Model In one implementation, the system can utilize yield models to predict the yield of a specific crop type (e.g., cotton, soybean, corn) within a specific crop, in a specific region, and / or globally. The system can then selectively distribute insights, instructions, and / or recommendations to various users associated with different sectors of the agricultural supply chain based on the predicted yield of that specific crop type.

[0076] In this implementation, the system can derive a yield model configured to predict the yield of a specific crop, a specific region, and / or a specific crop type within a specific region. Specifically, the system can: record time series of stress data representing the stress of a set of stressors within a region (e.g., a crop, a geographic area) throughout the initial growth period; record the final crop yield of a crop type (e.g., soybean, cotton, lettuce, tomato) within that region, such as the final crop yield recorded at the end of the initial growth period during and / or after harvesting that crop type; store the time series of stress data and the final crop yield in a first growth period group (e.g., a data group); and based on the time series of stress data and the final crop yield, derive a yield model that correlates the stress of a set of stressors within a geographic area with the crop yield of that crop type within that geographic area.

[0077] The system can repeat this process further during subsequent growth stages of the crop of that crop type within a geographic region to further refine the yield model. Specifically, the system can: generate a series of growth stages, such as including a first growth stage group, a second growth stage group generated for the second growth stage, a third growth stage group generated for the third growth stage, etc.; and refine the yield model based on each growth stage group generated for the crop of that crop type in a specific region. Furthermore, the system can perform this process to derive a yield model for each crop type present in the region. For example, the system can: derive a first crop yield model configured to predict the crop yield of tomato crops in the region; derive a second crop yield model configured to predict the crop yield of soybean crops in the region; derive a third crop yield model configured to predict the crop yield of cotton crops in the region; and so on.

[0078] For example, the system may: acquire a first time series of stress data representing changes in the stress of a set of stressors in a first region during a first growth period; acquire a first crop yield of a first crop type (e.g., cotton) in the first region during a first harvest period corresponding to the first growth period; acquire a second time series of stress data representing changes in the stress of the same set of stressors in the first region during a second growth period following the first harvest period; and acquire a second crop yield of the first crop type (e.g., cotton) in the first region during a second harvest period corresponding to the second growth period. The system may then implement regression, machine learning, deep learning, and / or other techniques to derive the correlation between stressor stress and crop yield in that particular region and / or in a particular crop within that region.

[0079] 5.5 Production Summary In one variant, the system can derive a yield profile that represents the predicted yield of a set of crop types (e.g., soybeans, tomatoes, cabbage, corn, cotton) within a specific region.

[0080] Specifically, in this variant, the system can: implement the methods and techniques described above to interpret the stress of a set of stressors in various sub-regions within a specific region and derive a stress map for that specific region accordingly; based on the stress map, predict crop yields in a set of crop yields for each of a set of crop types; and compile the set of crop yields into a yield profile for that specific region, which defines the predicted crop yield for each of the set of crop types. Over time, the system can update the yield profile based on detected and / or predicted changes in the stress of a set of stressors throughout the geographic region.

[0081] For example, during the growing season, the system may: acquire a first set of images captured during a first time period within the growing season, depicting sensitive plants sown in a first geographic region; interpret the stress of a set of stressors within the geographic region based on features extracted from the first set of images; and accordingly integrate a first stress map depicting the stress of that set of stressors within the first geographic region during the first time period. The system may then: predict a first crop yield for the first crop type within a first set of crop yields based on a first subset of features extracted from the first stress map of regions corresponding to the first crop type (e.g., soybean); generate a first yield profile for the first geographic region within a set of yield profiles, representing the predicted yield of the crop of that set of crop types during the first time period; and store the first crop yield associated with the first crop type in the first yield profile.

[0082] The system may also: predict the second crop yield of the second crop type (e.g., tomato) in the first set of crop yields based on a second subset of features extracted from the regions of the second crop type corresponding to the second crop from the first stress map; store the second crop yield associated with the second crop type in a first yield profile; and repeat the process for each crop type in the set of crop types to integrate the comprehensive yield profile for the first geographic region during the first time period.

[0083] Subsequently, during the growing season, the system can: acquire a second set of images captured during a second time period following the first time period, depicting sensitive plants sown in crops within the first geographic region; interpret the stress of a set of stressors within the geographic region based on features extracted from the second set of images; accordingly integrate a second stress map depicting the stress of a set of stressors within the first geographic region during the first time period; predict crop yield in a second set of crop yields for each crop type in the set of crop types based on features extracted from the second stress map corresponding to the regions of crops for each crop type in the set of crop types; and generate a second yield profile in a set of yield profiles for the first geographic region, the second yield profile representing the predicted yield of crops for that set of crop types during the second time period.

[0084] The system can then: store a second set of crop yields (each crop yield associated with a specific crop type) in a second yield profile; associate the first yield profile with a first time value (e.g., a timestamp) corresponding to a first time period; and associate the second yield profile with a second time value corresponding to a second time period; thereby deriving a time series of crop yield profiles for the first geographic region, including the first yield profile associated with the first time value (e.g., a timestamp) corresponding to the first time period and the second yield profile associated with the second time value corresponding to the second time period. The system can repeat this process for the remainder of the growing season and for each subsequent growing season to derive a comprehensive time series of crop yield profiles for the first geographic region.

[0085] 5.6 Crop Health Status In one implementation, the system may use time series of crop data (e.g., stress, stressor, and / or environmental data) collected for a particular crop and / or region to characterize the health status of that particular crop and / or region (hereinafter referred to as "crop health status").

[0086] For example, the system may acquire a first set of crop data—corresponding to the operation of a first crop located in a first region during a first time period—including: the number of stressors detected during the first time period; the average stress of each detected stressor; the crop's resistance to each detected stressor (e.g., the average duration of recovery); the total yield of the crop during the harvest season corresponding to the first time period; and / or (such as assessments by users associated with the crop during the harvest season) the quality of the harvested crop; and so on. The system may then characterize the crop's health score (e.g., a percentage between 0% and 99%, a scale value from 1 to 10, categorized as "poor," "average," "good," or "excellent") based on the first set of crop data collected during the first time period.

[0087] In the aforementioned example, the system can repeat this process for multiple crops and / or crop regions to integrate a health status map representing the crop health status in and / or across these regions during a specific time period. Furthermore, the system can update this health status map over time, such as with multiple growth stages.

[0088] In one variant, the system can predict the crop yield of a crop type within a specific region based on the predicted crop health status of that crop type within that region. Specifically, in this variant, the system can: characterize the plant health status of a crop type within a region based on a set of crop data (such as time series of stress data and / or environmental data (e.g., processing data, weather data)) collected for that crop type; acquire a yield model that correlates the plant health status of that crop type with crop yield; and predict the crop yield of that crop type (e.g., at the end of the current growing season) based on the plant health status and yield model of that crop type within the region.

[0089] For example, at a first point during the growing season, the system may: acquire a first time series of crop data for a first crop type among a set of crop types sown in a first sub-region of the region during a first time period prior to the first point, including a first time series of stress data and a first time series of environmental data; acquire a second time series of crop data for a first crop type planted in a second sub-region of the region during the first time period, including a second time series of stress data and a second time series of environmental data; and acquire a third time series of crop data for a first crop type planted in a third sub-region of the region during the first time period, including a third time series of stress data and a third time series of environmental data. The system can then: predict a first health score for a first crop type in a first subregion based on a first time series of crop data; predict a second health score for a first crop type in a second subregion based on a second time series of crop data; predict a third health score for a first crop type in a third subregion based on a third time series of crop data; and predict the first crop yield of the first crop type in a third subregion based on a yield model and the set of health scores (such as at a future time after the first time series, e.g., at the end of the growing season).

[0090] 5.7 Tips In one implementation, the system can selectively generate and distribute prompts related to the detection and mitigation of stressors within a crop or a specific area. Specifically, the system can identify and suggest stress mitigation techniques configured to: reduce stressors detected in a crop or area; minimize the spread of detected stress within a crop or in a specific area; and maximize crop yield within a specific crop and / or in a specific area.

[0091] For example, as described above, the system can derive a first stress map for a specific region, representing the location of various stressors detected during a first time period. The system can then: predict a second stress map based on the first stress map and a stress model generated for that specific region, representing the predicted location of predicted stressors detected during a second time period following the first time period; and / or estimate the predicted crop yield of the first crop type in the specific region based on the first stress map, the second stress map, and a yield model that correlates the stress maps with the crop yield of the first crop type in the specific region.

[0092] The system can then send a set of prompts to a group of crop operators associated with crops in a specific area, based on a first stress map, to implement a set of mitigation techniques configured to increase the efficiency of crop handling and maintenance over time and / or maintain or increase crop yield. Furthermore, the system can update crop profiles associated with crops in the specific area based on the first stress map, a second predicted stress map, and predicted crop yield. The system can then send this data to additional end users (e.g., crop handling developers, clothing retailers, food retailers) who are associated with and / or interested in the yield and / or health of crops in that specific area.

[0093] 5.7.1 Processing Results In one implementation, the system can characterize the effect of crop treatment based on changes in the stress of a specific stressor or multiple stressors detected.

[0094] For example, the system may: interpret a first stress of a first stressor in a crop of a specific crop type based on features extracted from a first image of the crop recorded during a first time period; and in response to interpreting the first stress of the first stressor, generate a prompt to apply a first treatment (such as a treatment of a specific dose and / or type (e.g., pesticide, fungicide, irrigation, fertilizer, soil pH treatment)) to the crop during a second time period following the first time period, and send the prompt to a user associated with the crop (e.g., a farmer). The system may then: interpret a second stress of the first stressor in the crop based on features extracted from a second image of the crop recorded during a third time period following the second time period; characterize the difference between the first and second stressors of the first stressor; and characterize the effect of the first treatment in alleviating the stress of the first stressor based on this difference.

[0095] For example, if the detected stress of the first stressor decreases in response to the application of the first treatment (e.g., by more than a threshold amount) in response to a difference exceeding a threshold difference, the system can characterize the first treatment as highly effective in alleviating the stress of the first stressor. However, if the detected stress of the first stressor increases in response to the application of the first treatment and / or exhibits minimal reduction (e.g., by less than a threshold amount) in response to a difference decreasing below a threshold difference, the system can characterize the first treatment as ineffective in alleviating the stress of the first stressor. The system can store this information in the crop profile of the crop to inform future treatment recommendations for the first stressor in that particular crop, crops of that crop type, and / or all crop types.

[0096] 5.8 Supply Chain Tracking In one implementation, the system can track the distribution of populations of sensitive plants modified to include specific identifiers throughout the entire life cycle of these sensitive plants (e.g., along the crop supply chain) during the transfer of sensitive plants through the crop supply chain, such as from the growing season within the crop, to loading onto a specific transport vehicle, to storage in a specific storage facility, to processing in a specific facility, etc.

[0097] For example, for a first sensitive plant including a fluorescent tag configured to express a baseline fluorescence signal, the system can: acquire a first image (e.g., a hyperspectral image) captured in a set of images by a farmer or agronomist (e.g., via a mobile device) associated with the crop containing the sensitive plant, the first image including a first timestamp and depicting the baseline fluorescence signal; acquire a second image in the set of images captured by an optical sensor arranged within a crop storage facility, the second image including a second timestamp and a batch identifier regarding the batch containing the sensitive plant, and depicting the baseline fluorescence signal; acquire a third image in the set of images captured by an optical sensor installed within a processing and / or manufacturing facility (e.g., a food manufacturing and / or processing facility, a garment manufacturing facility), the third image including a third timestamp and depicting the baseline fluorescence signal; and acquire a fourth image in the set of images captured by an optical sensor installed within a retail facility (e.g., a grocery store, a clothing store), the fourth image including a fourth timestamp and depicting the baseline fluorescence signal. Therefore, the system can associate sensitive plants (e.g., products of sensitive plants) sold in the retail facility with the crop and / or region of origin based on the detection of the baseline fluorescence signal in the set of images.

[0098] Over time, based on these correlations, the system can acquire additional information about crop yield and crop distribution, and thus update the crop profile for a specific crop and / or a specific crop region based on this information. The system can then utilize this information to derive more precise insights or information related to crop yield, crop supply, crop health, crop quality, and / or crop management for a specific crop and / or crop region. For example, soybean plants (e.g., sensitive soybean plants) can be modified to express a baseline fluorescence signal configured to fluoresce only in soybean pods, thereby enabling direct reporting of soybean yields across the entire lifecycle of these soybean plants, such as during growth, harvest, and / or distribution throughout the supply chain. Specifically, the system can: acquire images of soybean plants sown in and / or harvested from the crop; characterize the magnitude (e.g., intensity) of the baseline fluorescence signal detected in these images; and estimate the soybean crop yield based on the magnitude of the baseline fluorescence signal. The system can then repeat this process to update the soybean crop yield estimate over time.

[0099] Furthermore, in this implementation, the system can use this information to: identify a subset of users associated with the supply chain of a specific crop and / or crop region; and, over time, selectively send information, insights, instructions, recommendations, and / or suggestions to these different subsets of users, such as information, insights, instructions, recommendations, and / or suggestions related to actual and / or predicted crop yields, crop supply, crop health status, crop quality, crop management, etc.

[0100] For example, the system can identify a subset of users associated with garments made from cotton grown in a specific region based on the identification of baseline fluorescence signals in cotton stored in a manufacturing plant associated with that subset of users, signals that are associated with cotton grown in that specific region. Then, during the next life cycle of the cotton in that specific region, the system can selectively provide notifications and / or alerts to that subset of users in response to: the detection of high stress from a specific stressor in that region; a prediction of a very low crop supply of cotton in that specific region; a prediction of a very high crop supply of cotton in that specific region; and so on. Thus, the system can then (nearly) provide that subset of users with valuable insights or information relating to derived data and / or predictions regarding the cotton supply for that specific subset of users and the cotton supply from that specific region during that growth cycle.

[0101] In one variant, the system can utilize the detection of the baseline signal to distinguish between plants (e.g., sensitive plants) and weeds growing within the crop. For example, the system can: acquire images of the crop, including a group of sensitive plants configured to express baseline fluorescence signals, recorded by optical sensors (e.g., optical sensors mounted on manned or unmanned field equipment such as tractors, optical sensors on handheld devices operated by farmers or agronomists, and / or optical sensors mounted on booms or poles in the field); isolate areas in the images corresponding to the absence of baseline fluorescence signals; and mark these areas for application of specific weed treatments (e.g., by alerting farmers to apply the specific weed treatment and / or by triggering the application of the weed treatment by automated field equipment (e.g., an automatic sprayer mounted on a tractor)) and / or for further review. The system can repeat this process periodically (e.g., daily, weekly) to review the presence of weeds and / or other threats (e.g., invasive plants) in the crop, thereby reducing the risk to the crop and achieving increased yield.

[0102] 6. Simulate plant health status In one implementation, the system can use sensitive plant data collected over time from specific sensitive plants or groups of sensitive plants growing within a particular crop to characterize the plant health status of individual plants, plant groups, and / or all plants in a particular crop.

[0103] Specifically, in this embodiment, the system may focus on a specific set of conditions (e.g., environmental conditions) indicative of the plant health status of plants in a particular crop (e.g., a single sensitive plant within a particular crop, a group of sensitive plants, and / or the entire sensitive plant crop), such as the presence of a set of stressors (e.g., abiotic and / or biotic stressors), soil conditions (e.g., pH level, nitrogen level), weather conditions, etc. Therefore, the system can: detect signals (e.g., fluorescence signals) expressed by a group of sensitive plants in the particular crop; predict a set of current conditions at the group of sensitive plants based on these signals; and interpret the plant health status, such as the individual plant health status of each sensitive plant in the group and / or the composite plant health status of the group of sensitive plants, based on the set of current conditions detected at the group of sensitive plants.

[0104] Based on predicted plant health, the system can select specific crop treatments tailored to specific plants or plant groups within a crop and configured to improve or maintain plant health.

[0105] Therefore, in this embodiment, the system can use sensitive plant data collected over time for one or more sensitive plants sown in a particular crop to predict conditions at the plant sites throughout that particular crop, such as the magnitude and / or distribution of plant stressors (e.g., soil pH level, nitrogen uptake, water retention, insect presence, fungal presence), and thus characterize the health status of individual plants or plant groups at high resolution, thereby enabling customized treatment of specific plant groups in the crop in response to changes in plant health status.

[0106] 6.1 Target Conditions In one implementation, the system can define a set of target plant conditions (e.g., soil pH, soil nitrogen level, irrigation level, fertilizer level, fungicide level) for a specific crop. Typically, in this implementation, the system can: derive a set of target plant conditions that produce at least a target crop health condition, such as a set of target plant conditions corresponding to a threshold crop yield (e.g., minimum crop yield); and store these sets of target plant conditions as constituting (e.g., in a crop profile generated for that specific crop) "healthy crop" or "healthy plant".

[0107] Specifically, in this embodiment, during an initial time period, the system can: track plant conditions in sensitive plants within the crop, such as the magnitude of insect stress, fungal stress, drought stress (e.g., dehydration), plant nitrogen content (e.g., the amount of nitrogen consumed by the plant from the soil), etc.; and analyze these data to derive the correlation between plant conditions and plant health status. Therefore, the system can: derive a set of target plant conditions that produce at least the minimum or target plant health status in the crop; designate sensitive plants to signal plant conditions approaching this set of target plant conditions (e.g., within a threshold deviation of this set of target plant conditions) that qualify as “healthy” plants, such as by outputting a set of fluorescence signals in a specific wavelength range associated with these plant conditions; and during the growing season, implement this set of target plant conditions to selectively distinguish “healthy” plants and “unhealthy” or “less healthy” plants in the crop, which, without treatment, could lead to crop loss (e.g., reduced crop yield).

[0108] In one example of the foregoing implementation, the system may: track time series of plant conditions of sensitive plants growing within a crop during an initial time period, such as stress data, soil data, weather data, etc.; acquire time series of crop data recorded for plants within the crop during the initial time period, such as plant health status data (e.g., observed growth, wilting, plant death, color change, fruit growth) and / or yield data; calculate the correlation between plant conditions and plant health status of sensitive plants in a specific crop based on the time series of plant conditions and the time series of crop data; and define a set of target plant conditions associated with a threshold plant health status, such as a set of target plant conditions associated with a threshold probability of achieving a threshold crop yield, based on the correlation. More specifically, in this example, the system may implement machine learning, artificial intelligence, neural networks, or other analytical techniques to characterize plant health status as a function of plant conditions based on detected plant conditions and observed health status data of sensitive plants in the specific crop. Based on a target or threshold health score (e.g., minimum health score) defined for plants in a specific crop, such as a target or threshold health score predicted to achieve a threshold crop yield specified by an advertiser for an advertising campaign, the system can derive a set of target conditions predicted to produce that threshold health score for plants in the crop.

[0109] 6.1.1 Example: Nitrogen content in soil In one example, the system can define a target nitrogen content for plants in a specific crop. Specifically, in this example, the crop (e.g., soybean, corn, cotton) may include a group of sensitive plants, such as a group of sensitive plants planted in clusters in various regions of the crop and / or throughout the field, such that the group of sensitive plants includes each plant in the crop configured to signal the soil conditions at the location of that group of sensitive plants. Specifically, in this example, each sensitive plant in the group may include: a promoter associated with the presence of nitrogen at the plant; and a reporter associated with the promoter (e.g., a fluorescent protein), which is configured to express a fluorescent signal representing the absorption of nitrogen by the sensitive plant. Therefore, in this example, the system can: (e.g., in images of the sensitive plants recorded by a satellite) detect the fluorescent signal and interpret the amount of nitrogen consumed by the sensitive plant based on the intensity of the fluorescent signal.

[0110] During the first growing season of a particular crop, the system can predict plant health throughout the first growing season using global target nitrogen content, such as a general nitrogen content defined for substantially all plants or all plants for a particular crop type (e.g., soybean, corn, cotton). Specifically, the system can: acquire image feeds of the crop (e.g., recorded by satellite); detect fluorescence signals expressed by a group of sensitive plants within the crop and depicted in images within the image feed; interpret the amount of nitrogen absorbed by the sensitive plants within that group of sensitive plants based on these fluorescence signals; and characterize plant health (e.g., across the entire crop and / or in specific sub-regions of the crop) based on the amount of nitrogen absorbed by the sensitive plants in the crop and the global target nitrogen content.

[0111] As the system collects additional data on sensitive plants within the crop over time (such as time series of nitrogen content, time series of nitrogen treatment data (e.g., frequency and amount of nitrogen applied to the soil), plant health data, and / or crop yield data), the system can focus on target nitrogen content specific to the crop and / or specific to the plant, such as by updating general nitrogen content based on this additional data collected over time. For example, during the first growing season, the system can collect surveys (e.g., at different times throughout the first growing season) completed by users associated with the crop, and these surveys indicate plant health across the entire crop, such as specifying visual characteristics of plants in the crop (e.g., color, wilting, height, fruit size, fruit growth), treatments applied to the crop (e.g., nitrogen, pesticides, fungicides, irrigation), crop losses, crop yield, etc. Based on this data, combined with nitrogen content detected in sensitive plants throughout the crop, the system can focus on target nitrogen content corresponding to that particular crop and / or a specific subregion of that crop. As the system continues to collect additional data on the crop over time, it can continuously refine the target nitrogen content, enabling one or more users associated with the crop to apply nitrogen to the soil at specific times of the growing season and / or in specific sub-regions of the crop, based on a target nitrogen content defined for that particular crop and / or a sub-region of the crop, to produce healthy plants in that crop.

[0112] Furthermore, during this first growing season, the system can: acquire the amount of nitrogen applied by a user associated with the crop (e.g., a farmer, agronomist), such as applied to the crop and / or soil in a specific sub-region of the crop; and characterize the uptake of nitrogen by plants in the crop (e.g., plants in a specific sub-region of the crop and / or all plants across the crop) based on the difference between the amount of nitrogen applied and the amount of nitrogen detected at sensitive plants in the crop (e.g., based on fluorescence signals expressed by sensitive plants).

[0113] For example, the system can acquire the initial nitrogen application rate applied to the soil in the crop at an initial time corresponding to the start of the growing season. Then, at the first time, the system can: acquire a first image of the crop recorded by a satellite; detect a first fluorescence signal expressed by sensitive plants in a first sub-region of the crop; detect a second fluorescence signal expressed by sensitive plants in a second sub-region of the crop; interpret the first amount of nitrogen consumed by plants (e.g., from the soil) in the first sub-region based on the first fluorescence signal; and interpret the second amount of nitrogen consumed by plants in the second sub-region based on the second fluorescence signal. Then, for the first sub-region, the system can: calculate a first ratio of the first nitrogen amount to the initial nitrogen application rate; calculate the duration between the first time and the initial time; and characterize the first nitrogen uptake (e.g., nitrogen consumption rate) based on the first ratio and the duration. Similarly, for the second sub-region, the system can: calculate a second ratio of the second nitrogen amount to the initial nitrogen application rate; and characterize the second nitrogen uptake (e.g., nitrogen consumption rate) based on the second ratio and the duration. Therefore, before subsequently applying nitrogen to the soil in the crop, the system can: derive a first nitrogen application rate for a first sub-region of the crop, which is predicted to produce nitrogen uptake corresponding to a target nitrogen content in the plants in the first sub-region; derive a second nitrogen application rate for a second sub-region of the crop, which is predicted to produce nitrogen uptake corresponding to a target nitrogen content in the plants in the second sub-region; generate a prompt to apply the first nitrogen application rate and the second nitrogen application rate to the first sub-region and the second sub-region respectively at a second time (e.g., during the first growing season); and send the prompt to a user or user group associated with the crop.

[0114] 6.2 Characterization plant health status The system can characterize the plant health status of a crop based on a set of target plant conditions defined for that crop.

[0115] In particular, in this embodiment, the system can characterize plant health based on the difference between a set of current plant conditions (such as those derived from fluorescence signals expressed by sensitive plants in the crop and detected in images of the crop) and a set of target plant conditions defined for the crop.

[0116] For example, the crop may include sensitive plants configured to signal nitrogen uptake in (e.g., within the crop). Specifically, each sensitive plant in a group of sensitive plants within the crop may be configured to output a fluorescence signal within a target wavelength range, representing the amount of nitrogen consumed by the sensitive plant (e.g., from the soil). In this example, during a first time period, the system may: derive a target nitrogen content in the soil of the crop (such as a target nitrogen dose defining the frequency of nitrogen application and the amount of nitrogen applied at each application), the target nitrogen content being configured to produce plants that are "healthy" in that particular crop, such as those characterized by a health score exceeding a threshold health score; and store the target nitrogen content in a crop profile generated for the crop.

[0117] Then, during a second time period following the first time period, the system may: acquire image feeds of sensitive plants in the crop recorded during the second time period by an imaging system (e.g., a satellite, an optical sensor mounted on a drone, a tractor, or a pole mounted in the crop, or a camera on a mobile device), the imaging system being configured to capture fluorescence signals output by the sensitive plants, the sensitive plants being configured to output fluorescence signals within a target wavelength in response to various plant stressors; extract a first intensity of the fluorescence signal (e.g., a composite fluorescence signal output by a group of sensitive plants) within the target wavelength range; and predict the current nitrogen level in the plants in the crop based on the first intensity of the fluorescence signal.

[0118] In the aforementioned example, the system can then: obtain a target nitrogen content defined for that particular crop and stored in a crop profile; characterize the difference between the current nitrogen content and the target nitrogen content; and characterize the health status (or “plant health status”) of the plants in the crop based on that difference. For example, the system can estimate a health score for the plants in the crop, represented as a percentage between 0% and 100%, a score between 0 and 10, or a rating of poor health, moderate health, good health, or excellent health. In one example, in response to the difference exceeding an upper threshold difference defined for the plants in that particular crop, the system can estimate a relatively low health score for the plants in the crop (e.g., “5%”, “1 / 10”, poor health). Alternatively, in response to the difference falling below the upper threshold difference and exceeding the lower threshold difference, the system can estimate a relatively moderate health status score for the plants in the crop (e.g., “50%”, 5 / 10, moderate health). Alternatively, in response to the difference falling below the lower threshold difference, the system can estimate a relatively high health score for the plants in the crop (e.g., “95%”, 9 / 10, excellent health).

[0119] 6.2.1 Health situation Model In one variant, the system can derive a plant health status model that is configured to incorporate a set of current conditions detected for a specific sensitive plant or group of sensitive plants and output a prediction of the current plant health status for that specific sensitive plant or group of sensitive plants.

[0120] For example, during the first growing season of a specific crop, the system may: track a first set of plant conditions at a first set of sensitive plants located in a first sub-region of the crop; track a second set of plant conditions at a second set of sensitive plants located in a second sub-region of the crop; acquire a first set of plant surveys completed by one or more users associated with the crop, which indicates the health status of the plants in the first sub-region throughout the first growing season; acquire a second set of surveys completed by one or more users associated with the crop, which indicates the health status of the plants in the second sub-region throughout the first growing season; and / or acquire a first set of crop data collected for the crop during the first growing season, such as weather data, crop yield data (e.g., crop yield data for the entire crop and / or for sub-regions of the crop), crop treatment data (e.g., crop treatment data for the entire crop and / or for sub-regions of the crop), etc.

[0121] Then, the system can: derive a first health status model based on a first set of plant conditions, a first set of plant surveys, and a first set of crop data, the first health status model being configured to predict the health status of plants in the first sub-region of the crop based on plant conditions at sensitive plant sites in the first sub-region; and derive a second health status model based on a second set of plant conditions, a second set of plant surveys, and a second set of crop data, the second health status model being configured to predict the health status of plants in the second sub-region of the crop based on plant conditions at sensitive plant sites in the second sub-region.

[0122] Then, during the subsequent growing season, the system can: acquire a first image depicting plants in a first sub-region of the crop; interpret a first set of plant conditions based on fluorescence signals extracted from the first image; and characterize the health status of the plants in the first sub-region, such as through a first plant health status score, based on the first set of plant conditions and a first health status model. Furthermore, the system can: acquire a second image depicting plants in a second sub-region of the crop; interpret a second set of plant conditions based on fluorescence signals extracted from the second image; and characterize the health status of the plants in the second sub-region, such as through a second plant health status score, based on the second set of plant conditions and a second health status model. In this example, the system can then select a specific treatment approach to be implemented in each sub-region of the crop, thereby enabling the customization of treatment for the plants in each sub-region based on changes in the health status of the plants in these sub-regions.

[0123] In one example, the system can derive a health status model configured to output a health status score representing the health status of plants in a specific sub-region of a crop, based on the amount of nitrogen consumption detected in sensitive plants in a specific sub-region, the amount of water consumption detected in sensitive plants in a specific sub-region, the amount of fungal stress detected in a specific sub-region, and / or the amount of insect stress detected in a specific sub-region.

[0124] 6.3 Targeted Treatment The system can use the difference between a set of target conditions defined for a crop and the (currently) detected conditions in that crop to suggest targeted treatments for plants in that crop.

[0125] In particular, the system can selectively suggest treatments (such as to farmers or agronomists associated with the crop) that are configured to shift the current conditions within the crop toward a set of target conditions defined for that crop and / or for a specific subset of plants within that crop (e.g., in a specific sub-region).

[0126] Therefore, the system can: acquire one or more images of sensitive plants in a crop; extract fluorescence signals representing a first condition for these sensitive plants (such as the amount of fungal stressors present at the site of these sensitive plants or the amount of nitrogen consumed by the sensitive plants) using a reporter submodel defined for these sensitive plants; acquire a target condition defined for the plants in the crop and corresponding to the first condition, such as a threshold value (e.g., a maximum value) of fungal stressors that the plants in the crop can tolerate, or a target nitrogen content configured to maximize plant health or growth (e.g., within a target range); characterize the difference between the first condition and the target condition; and, based on this difference, select a treatment pathway for the plants in the crop configured to adjust the first condition toward the target condition. The system can then prompt a user associated with the crop to implement the treatment pathway and / or, for example, automatically trigger the implementation of the treatment pathway via an automated treatment system.

[0127] Furthermore, by utilizing signals generated by sensitive plants distributed throughout the crop, the system can selectively suggest different treatment types and / or treatment dosages in different regions within a particular crop. Therefore, the system can enable targeted treatment of plants in a specific crop and / or geographical region (e.g., across multiple crops) based on conditions within each of these different regions.

[0128] For example, the system may: acquire an image feed of a sensitive plant population, comprising a first group of sensitive plants sown in a first sub-region of the crop and a second group of sensitive plants arranged in a second sub-region of the crop; interpret a first set of conditions at the plants in the first sub-region based on a first subset of features extracted from the first image in the image feed (such as fluorescence intensity in a first wavelength range); acquire a set of target conditions defined for the plants in the crop; characterize a first difference between the first set of conditions and the set of target conditions; and select a first treatment pathway for application to the plants in the first sub-region in response to the first difference exceeding a threshold difference. The system may also: interpret a second set of conditions at the plants in the second sub-region based on a second subset of features extracted from the first image (such as fluorescence intensity in a first wavelength range); characterize a second difference between the second set of conditions and the set of target conditions; and select a second treatment pathway for application to the plants in the second sub-region in response to the second difference exceeding a threshold difference. The system may then: generate a notification including a prompt to apply the first treatment pathway in the first sub-region and the second treatment pathway in the second sub-region; and send the prompt to the farmer associated with the crop.

[0129] 6.3.1 Processing the diagram In one variant, the system can derive a treatment map for a particular crop based on a set of target conditions defined for that crop. Specifically, in this variant, the system can integrate the treatment map based on treatment pathways selected for individual sub-regions of the crop, specifying the location and magnitude (e.g., frequency and / or amount) of application for each selected treatment pathway for the crop.

[0130] For example, the system can: acquire an image of the crop recorded by a satellite at a first time, depicting a set of fluorescence signals expressed by sensitive plants in the crop; interpret a first nitrogen content in plants in a first sub-region of the crop based on a first fluorescence signal in the set of fluorescence signals; interpret a second nitrogen content in plants in a second sub-region of the crop based on a second fluorescence signal in the set of fluorescence signals; and interpret a third nitrogen content in plants in a third sub-region of the crop based on a third fluorescence signal in the set of fluorescence signals. Then, for the first sub-region of the crop, the system can: acquire a first target nitrogen content corresponding to the plants in the first sub-region from a set of target nitrogen contents derived for the crop; characterize the difference between the first nitrogen content and the first target nitrogen content; and derive a first nitrogen application rate for soil application to the first sub-region at a second time after the first time based on the difference. The system can similarly repeat this process for the second and third sub-regions to derive a second nitrogen application rate for soil application to the second sub-region at the second time and a third nitrogen application rate for soil application to the third sub-region at the second time. The system can then: export a treatment map for implementation at approximately a second time, the treatment map indicating the application of a first nitrogen application rate, a second nitrogen application rate, and a third nitrogen application rate in a first sub-region, a second sub-region, and a third sub-region of the crop, respectively; and send the treatment map to the user for implementation in the crop at approximately a second time. Additionally and / or alternatively, in this example, the system can upload the treatment map to an autonomous vehicle (e.g., an autonomous tractor or drone) configured to autonomously traverse the crop and apply nitrogen to the soil in the crop according to the treatment map.

[0131] In one implementation, the system can export a treatment map specifying the type and dosage (e.g., amount and / or duration of treatment) of treatment applied to a specific region and / or geographic region of a crop. For example, the system can: interpret a first stress of a first stressor in the first region of the crop based on features extracted from a first portion of a sensitive plant depicting a first region in a first image; interpret a second stress of the first stressor in the second region of the crop based on features extracted from a second portion of a sensitive plant depicting a second region in a first image; select a first mitigation technique (e.g., applying a pesticide or fungicide, watering the plant, fertilizing the plant), the first mitigation technique being configured to alleviate the stress of the first stressor in the crop; define a dosage gradient for applying the first mitigation technique to the crop based on the first and second stresses; and generate a treatment map based on the first mitigation technique and the dosage gradient. For example, the system can generate a treatment map that defines: a first dosage of the first mitigation action in the first region of the crop; and a second dosage of less than the first dosage of the first mitigation action in the second region of the crop in response to a decrease in the second stress to below the first stress.

[0132] 6.4 Crops stress resistance In one variant, the system can characterize a particular crop’s resistance to a set of plant stressors (e.g., abiotic and / or biotic stressors), such as drought, heat, nutrient deficiencies (e.g., nitrogen and phosphorus deficiencies), overwatering, salinity, soil pH, soil pollution, insects, fungi, weed growth, etc.

[0133] Specifically, in this implementation, the system can characterize a crop's resistance to a specific stressor from a set of plant stressors based on target plant conditions associated with that specific stressor, defined for the crop. For example, the system can quantify the plant's resistance to nitrogen deficiency as an inverse function of a target nitrogen content defined for the plant in the crop. More specifically, in this example, if the target nitrogen content defined for the plant in the crop is relatively low, the system can quantify the plant's resistance to nitrogen deficiency as relatively high. Alternatively, in this example, if the target nitrogen content defined for the plant in the crop is relatively high, the system can quantify the plant's resistance to nitrogen deficiency as relatively low.

[0134] Additionally and / or alternatively, in another embodiment, the system may characterize the crop's resistance to a specific stressor in a set of plant stressors based on the sensitivity of the plant in the crop to deviations from target plant conditions associated with that specific stressor. For example, the system may: interpret the sensitivity of the plant in the crop to nitrogen deficiency (such as below a target nitrogen content defined for the plant in the crop) based on observed changes in plant health status; and quantify the plant's resistance to nitrogen deficiency as an inverse function of sensitivity. The system may similarly repeat this process for each stressor in the set of plant stressors to characterize the crop or plant in that particular crop's resistance to that set of plant stressors.

[0135] The systems and methods described herein can be embodied and / or implemented at least in part as a machine configured to receive a computer-readable medium storing computer-readable instructions. The instructions can be executed by a computer-executable component integrated with hardware / firmware / software components of an application, app, host, server, network, website, communication service, communication interface, user computer or mobile device, wristwatch, smartphone, or any suitable combination thereof. Other systems and methods of the embodiments can be embodied and / or implemented at least in part as a machine configured to receive a computer-readable medium storing computer-readable instructions. The instructions can be executed by a computer-executable component integrated with a computer-executable component 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.

[0136] As will be appreciated by those skilled in the art from the foregoing detailed description and from the drawings and claims, modifications and variations may be made to the embodiments of the invention without departing from the scope of the invention as defined in the appended claims.

Claims

1. A method for simulating crop yield, comprising: - Acquire image feeds of sensitive plants of a sensitive plant type sown in a group of farmlands within a geographic region, the image feeds being recorded during a first time period, the sensitive plants of the sensitive plant type being configured to signal the presence of a set of stressors at the sensitive plants; -Based on features extracted from a first subset of images depicting sensitive plants in a first sub-region of the geographic region from the image feed, interpret the first stressor of the first stressor in the first sub-region of the set of stressors; -Based on features extracted from a second subset of images depicting sensitive plants in a second subregion within the geographic region from the image feed, the second stressor of the first stressor in the second subregion is interpreted; - Derive a first stress map of the geographic region based on the first stress and the second stress, the first stress map indicating the presence of the set of stressors in the geographic region during the first time period; - Obtain a yield model that correlates the stress of a set of stressors in the geographic region with the crop yield of a set of crop types in the target region; and - Based on the first stress map and the yield model, predict the first crop yield of the first crop type among the set of crop types in the geographical region.

2. The method according to claim 1: -in, Predicting the yield of the first crop of the first crop type based on the first stress map and the yield model includes predicting the yield of the first crop of the first crop type based on a first subset of features extracted from the region of the first stress map corresponding to the first crop type and the yield model. and -Also includes: --Based on a second feature subset extracted from the region of the second crop type in the first stress map corresponding to the second crop type in the set of crop types and the yield model, predict the second crop yield of the second crop type in the geographic region; and --Based on the first crop yield of the first crop type and the second crop yield of the second crop type, a first yield profile for the geographic region is generated in a set of yield profiles.

3. The method according to claim 1: -in, Exporting the first pressure map includes: --Predict the third pressure of the first stressor in a third sub-region within the geographic region based on the first pressure of the first stressor in the first sub-region and the second pressure of the first stressor in the second sub-region; and --Derive the first pressure map of the geographical area based on the first pressure, the second pressure, and the third pressure; and - Wherein, predicting the first crop yield of the first crop type in the geographical region includes predicting the first crop yield of the first crop type in the geographical region that includes the following: --The first crop of the first crop type located in the first sub-region and including the first group of sensitive plants of the sensitive plant type; --A second crop of the first crop type located in the second sub-region and including a second group of sensitive plants of the sensitive plant type; and --A third crop of the first crop type located in the third sub-region.

4. The method according to claim 1: -Also includes: --Based on features extracted from the first image subset, interpret the third stressor of the second stressor in the first sub-region of the set of stressors; and --Based on features extracted from the second image subset, interpret the fourth stressor in the second sub-region of the set of stressors; and - Wherein, deriving the first pressure map of the geographic region based on the first pressure and the second pressure includes deriving the first pressure map of the geographic region based on the first pressure of the first stressor, the second pressure of the first stressor, the third pressure of the second stressor, and the fourth pressure of the second stressor.

5. The method according to claim 4: -in, The first stress, interpreted based on features extracted from the first image subset, in the first sub-region as the first stressor, includes: --Extract a first set of fluorescence measurements within a first wavelength range from the first image subset; and --The first stressor in the first sub-region is interpreted based on the first set of fluorescence measurements; and - Wherein, interpreting the third pressure based on features extracted from the first image subset in the first sub-region as the second stressor includes: --Extract a second set of fluorescence measurements within the second wavelength range from the first image subset; and --The third pressure of the second stressor in the first sub-region is interpreted based on the second set of fluorescence measurements.

6. The method of claim 1, further comprising, during the initial time period: -For each growth period in a series of growth periods within the initial time period: --Record a time series of stress data, the time series of stress data representing the stress of the set of stressors in the geographic region throughout the entire growth period; --Record the final crop yield of the crop type in the geographical area; and --Store the time series of the stress data and the final crop yield in one of a series of growing season groups; and - Based on the aforementioned series of growth period groups, a model is derived that correlates the stress of the aforementioned set of stressors within the geographic region with the crop yield of the aforementioned crop type within the geographic region.

7. The method according to claim 1: -Also includes: Obtain the time series of weather data recorded for the geographic region during the first time period; and - Wherein, predicting the first crop yield based on the first stress map and the yield model includes predicting the first crop yield based on the first stress map, the time series of the weather data, and the yield model.

8. The method according to claim 1, further comprising: - Based on the first stress map, predict the third stress of the first stressor in the first sub-region at a second time after the first time. - Based on the first stress map, predict the fourth stress of the first stressor in the second sub-region at the second time; - Derive a second pressure map of the geographic region based on the third pressure of the first stressor and the fourth pressure of the first stressor; - Generate a processing map based on the second pressure map for implementation at the second time; and - Send the processing map to a group of users associated with crops in the geographic region.

9. The method according to claim 8: -in, Generating the processing graph includes: --Select a first mitigation technique from a set of mitigation techniques, the first mitigation technique being configured to alleviate the stress of the first stressor in the geographic area; and --A dose gradient is defined based on the first pressure map, the dose gradient comprising an array of doses for applying the first mitigation technique across the geographical region; and -Sending the processing map to the group of users associated with crops in the geographical region includes: --Send the processing map to a first subset of users in the group of users associated with applying the first mitigation technique within the geographical region; and --The processing diagram is sent to a second subset of users within the group who are associated with the manufacture of chemicals related to the first mitigation technology.

10. The method according to claim 1, further comprising: - Obtain the target pressure range defined for the pressure of the first stressor in the first sub-region; - Characterizes the difference between the first pressure and the target pressure range; and -In response to the difference exceeding a threshold difference: --Select a first relief action from a set of relief actions, the first relief action being configured to relieve the stress of the first stressor; --Select the first dose of the relief action based on the difference; --A prompt is generated in the crop of the crop type in the first sub-region to implement the first mitigation action at the first dose; and --Send the notification to a group of users associated with the crops in the first sub-region.

11. The method according to claim 1, further comprising: - At a second time following the first time, in response to harvesting crops of the crop type within the geographic area, obtain the final crop yield of the crop type harvested during the growing season; - Obtain a time series of stress maps derived for the geographic region during the growing season, the time series of stress maps including the first stress map; and - The yield model is revised based on the time series of the stress map and the final crop yield.

12. The method according to claim 1, further comprising: -Based on the first pressure map: --Select a first relief action from a set of relief actions, the first relief action being configured to relieve the stress of the first stressor; -- Generate a first prompt to implement the first mitigation action on crops of the crop type within the geographic area during a second time period following the first time period; and --Send the first prompt to a group of users who are associated with crops of the crop type in the geographic region; -Based on features extracted from a third subset of images depicting sensitive plants in the first sub-region from the image feed, the third stress of the first stressor in the first sub-region is interpreted; -Based on features extracted from a fourth subset of images depicting sensitive plants in the second sub-region from the image feed, the fourth pressure of the first stressor in the second sub-region is interpreted; - Characterizing the first difference between the third pressure and the first pressure in the first sub-region; - Characterizes the second difference between the second pressure and the fourth pressure in the second sub-region; -In response to the first difference exceeding a threshold difference: --Generate a second prompt to implement the first mitigation action in crops of the crop type in the first sub-region during a third time period following the second time period; and --Send the second prompt to a first subset of users in the group of users who are associated with crops of the crop type in the first sub-region; and -In response to the second difference decreasing below the threshold difference: --Select a second relief action from the set of relief actions to replace the first relief action, and the second relief action is configured to relieve the stress of the first stressor; -- Generate a third prompt to implement the second mitigation action in crops of the crop type in the second sub-region during the third time period; and --Send the third prompt to a second subset of users in the group of users who are associated with crops of the crop type in the second sub-region.

13. The method according to claim 1: -in, The image feed for acquiring sensitive plants includes acquiring the image feed for sensitive plants of the sensitive plant type, wherein the sensitive plants are configured as follows: --Based on the set of stressors, selectively output fluorescence signals across a set of wavelength ranges; and -- Output a baseline fluorescence signal within a target wavelength range associated with the crop type, wherein wavelengths within the target wavelength range are outside the set of wavelength ranges; - Wherein, interpreting the first stressor in the first sub-region based on features extracted from the first image subset includes: --Identifying a first group of crops of the crop type within the first sub-region based on the detection of baseline fluorescence signals within the first image subset; and --The first stress of the first stressor in the first group of crops is interpreted based on the detection of fluorescence signals across the set of wavelengths within the first image subset; and - Wherein, interpreting the second stressor in the second sub-region based on features extracted from the second image subset includes: --Identifying a second group of crops of the crop type within the second sub-region based on the detection of baseline fluorescence signals within the second image subset; and --The second stress of the first stressor in the second group of crops is interpreted based on the detection of fluorescence signals across the set of wavelength ranges within the second image subset.

14. The method according to claim 1, wherein, Acquiring the image feed of the sensitive plant of the sensitive plant type includes acquiring the image feed of the sensitive plant of the sensitive plant type that includes the following: - A first promoter in a set of promoters, the first promoter being configured to be activated in response to stress from the first stressor; and - A first reporter in a set of reporters, the first reporter being associated with the first promoter and configured to express a detectable fluorescent signal in response to activation of the first promoter and corresponding to the stress of the first stressor.

15. The method according to claim 1: -in, The first stressor that explains the first stressor includes explaining a first value of nitrogen uptake in the plants in the first sub-region; - Wherein, the second pressure explaining the first stressor includes a second value explaining nitrogen uptake in plants in the second sub-region; and -Among them, the predicted total crop yield includes: --Obtain the target nitrogen uptake defined for plants in the geographic region; --Based on the first value of nitrogen absorption and the target nitrogen absorption, predict the first health score of the plant in the first sub-region; --Based on the second value of nitrogen uptake and the target nitrogen uptake, a second health score of the plant is predicted in the second sub-region; and --Predict the total crop yield of the geographic region based on the first health score, the second health score, and the yield model.

16. A method for simulating crop yield, comprising: - Acquire an image feed of a sensitive plant population in a crop of a certain crop type sown in a target area, and the sensitive plant population is configured to signal the presence of a set of stressors at the sensitive plants, the image feed being captured by an optical sensor during a first time period; -Based on features extracted from a first subset of images captured during a first time period in the image feed, a first time series of stress data of plants in a first sub-region of a set of sub-regions in the target region is interpreted, the first time series of stress data representing the changes in the stress of a set of stressors at the plants in the first sub-region during the first time period; -Based on features extracted from a second subset of images captured during the first time period in the image feed, a second time series of stress data of plants in a second sub-region of a set of sub-regions in the target region is interpreted, the second time series of stress data representing the changes in the stress of the set of stressors at the plants in the second sub-region during the first time period; - Obtain a yield model that correlates the stress of the set of stressors in the target region with the crop yield of the crop of the crop type in the target region; and - Based on a first time series of the stress data, a second time series of the stress data, and the yield model, predict the first crop yield of one of the crop types in the set of crop types in the target region during a target harvest period following the first time period.

Images