System and method for agricultural risk management

Abstract

Methods and systems for managing agricultural system risks include receiving an agricultural system unit (ASU) selection for an ASU associated with an agriculture and agriculture system; and accessing an analysis for a plant corresponding to the ASU selection based on the selection type of the ASU selection. An assessment associated with the plant corresponding to the ASU selection can be accessed based on the analysis and the selection type, and a need for a risk mitigation technique can be determined based on the analysis and / or the assessment. A result of processing the ASU selection can be indicated in a graphical user interface (GUI) based on the selection type. The plants of the agriculture and forestry agriculture system can include cacao trees.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Provisional Application No. 63 / 345,859, filed on May 25, 2022, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure generally relates to systems and methods for managing the risk of agricultural product losses at various scales. Specifically, the present disclosure relates to systems and methods for managing risk in the agricultural production of plants and plant parts, such as cocoa beans. Background Art

[0004] The fermented beans of the cacao tree, the main ingredient in chocolate, grow from pods on the tree. However, despite the economic importance of cocoa beans, large-scale cultivation of cacao trees faces many challenges, at least in part because cocoa agricultural systems are agroforestry systems. Unlike agricultural systems that grow row crops (e.g., farms), cocoa agricultural systems are divided into unevenly shaped units of area (e.g., hectares) where the conditions that affect the growth of cacao trees may be relatively non-uniform. Therefore, large-scale cultivation of cacao trees, even on just a single cocoa farm, may require the use of different farming techniques and continued attention to sub-areas within the agricultural system that are affected by different growing conditions, similar to the diversity of conditions one sees in different areas of a forest.

[0005] In addition to the challenges mentioned above, cocoa trees are susceptible to different pests and diseases and are often grown in remote and hard-to-reach locations in different parts of the world. Specifically, many cocoa agricultural systems around the world are located in areas that often have poor: (a) access to technology; (b) infrastructure; and / or (c) access to information about advanced or even recognized existing farming techniques that can mitigate disease risks (such as cocoa swollen shoot disease (CSSD)) in tree plants such as cocoa. Cocoa beans around the world are mainly grown on small family farms, while the rest are grown on large commercial cocoa plantations. This is especially true in small-scale agricultural systems that grow cocoa trees. However, all system operators (e.g., farmers) of cocoa, whether in small-scale or large-scale agricultural systems, face unique challenges in managing agricultural risks posed by pests and diseases.

[0006] Especially in terms of pests, cocoa cultivation is susceptible to a variety of pests, and identifying these pests plays a vital role in implementing effective pest management strategies. In addition, certain cocoa bean pests are able to spread over long distances, which makes localized mitigation challenging.

[0007] The present disclosure is intended to address the above challenges. The background description provided herein is intended to present the background of the present disclosure in general. Unless otherwise indicated herein, the materials described in this section are not considered to be prior art or suggestions of prior art because they are included in this section. Summary of the invention

[0008] According to certain aspects of the present disclosure, the technology described herein relates to methods and systems for managing agricultural system risks, which may include: receiving an agricultural system unit (ASU) selection for an agroforestry agricultural system; accessing an analysis for a plant corresponding to the ASU selection based on a selection type of the ASU selection; accessing an assessment associated with the plant corresponding to the ASU selection based on the analysis and the selection type; determining a need for risk mitigation technology based on the analysis and / or the assessment; and indicating a result of processing the ASU selection in a graphical user interface (GUI) based on the selection type, wherein the plants of the agroforestry agricultural system include cocoa trees.

[0009] In some aspects, the technology described herein relates to systems and methods for managing risk in an agricultural system, which systems and methods may include: configuring access to the results of the analysis and the assessment according to a specified format based on at least one of the location or reporting standards of the agroforestry agricultural system; accessing the assessment includes determining the number of plants exhibiting cocoa swollen shoot disease (such as cocoa swollen shoot disease) within the ASU; accessing the assessment includes receiving an indication of a test result from a test kit; accessing the assessment includes generating a heat map including a density indicator; and the density indicator is configured to indicate the number of plants included in the ASU.

[0010] In some aspects, the technology described herein relates to systems and methods for managing risk in agricultural systems, which systems and methods may include: capturing an image of at least a portion of an ASU selected by an ASU; and receiving an image analysis of the image, the image analysis including multiple plant parts damaged within the portion of the ASU.

[0011] In some aspects, the technology described herein relates to systems and methods for managing risks in agricultural systems, which may include: determining a need for risk mitigation technology, including determining that the risk mitigation technology includes a change to a schedule for analyzing at least one group of plants included in the agroforestry system; and sending a notification to at least one computing device, wherein the notification includes the schedule with the change; determining the need for risk mitigation technology includes accessing historical weather information from one or more servers, the historical weather information for an area including the agroforestry system; and determining that the risk mitigation technology includes changing a schedule for supplying water to at least a portion of the agroforestry system based on the historical weather information.

[0012] In some aspects, the technology described herein relates to systems and methods for managing risks in agricultural systems, which may include: the results of processing the ASU selection include a prediction of the incidence of at least one disease for at least one group of plants in the agroforestry system over a defined future time period, the prediction having been made using a predictive model for the agroforestry system; and causing the results of processing the ASU selection to be indicated in the GUI to include causing the GUI to include a summary of the ASUs, the summary including the number of diseased plants associated with the ASU on a single date or within a range of dates.

[0013] In some aspects, the technology described herein relates to systems and methods for managing risks in agricultural systems, which systems and methods may include a computer system comprising: at least one memory storing instructions; and at least one processor configured to execute the instructions to perform operations, the operations comprising: receiving an agricultural system unit (ASU) selection for an ASU associated with an agroforestry agricultural system; accessing an analysis for a plant corresponding to the ASU selection based on a selection type of the ASU selection; accessing an assessment associated with the plant corresponding to the ASU selection based on the analysis and the selection type; determining a need for risk mitigation technology based on the assessment; and indicating a result of processing the ASU selection in a graphical user interface based on the selection type, wherein the plants of the agroforestry agricultural system include cocoa trees.

[0014] In some aspects, the technology described herein relates to systems and methods for managing risks in agricultural systems, which systems and methods may include a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations including: receiving an agricultural system unit (ASU) selection for an ASU associated with an agroforestry agricultural system; accessing an analysis for a plant corresponding to the ASU selection based on a selection type of the ASU selection; accessing an assessment associated with the plant corresponding to the ASU selection based on the analysis and the selection type; determining a need for risk mitigation technology based on the analysis and / or the assessment; and causing an indication of a result of processing the ASU selection in a graphical user interface based on the selection type, wherein the plants of the agroforestry agricultural system include cocoa trees.

[0015] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosed examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various exemplary examples and, together with the description, serve to explain the principles of the disclosed examples.

[0017] Figure 1 A flow chart of an exemplary method for managing risk in an agricultural system according to one or more examples is depicted.

[0018] Figure 2 Depicted is a sequence diagram of an exemplary method for managing risk in an agricultural system according to one or more examples.

[0019] Figure 3 A flow chart of an exemplary method for identifying agricultural risk mitigation techniques according to one or more examples is depicted.

[0020] Figure 4 Depicted are example system components for managing risk in an agricultural system according to one or more examples.

[0021] Figure 5 Depicted is a diagram of an exemplary graphical user interface ("GUI") for implementing various methods described herein.

[0022] Fig. 6A and Figure 6B Depicted is an illustration of an exemplary GUI for defining a configuration file for an agricultural system unit (ASU) according to one or more examples.

[0023] Figure 6CDepicted is an illustration of an exemplary GUI for summarizing a configuration file for an agricultural system according to one or more examples.

[0024] Fig. 7A and Figure 7B Depicted is an illustration of an exemplary GUI associated with a scouting agricultural system according to one or more examples.

[0025] Fig. 8A Depicted is an illustration of an exemplary GUI associated with accessing different assessments of an agricultural system according to one or more examples.

[0026] Figure 8B and Figure 8C Depicted are diagrams of exemplary GUIs for different assessments related to agricultural systems according to one or more examples.

[0027] Fig. 9A and Fig. 9B Depicted is an illustration of an exemplary GUI for selecting a farming system report type according to one or more examples.

[0028] Fig. 9C A diagram depicting an exemplary GUI for an exemplary agricultural system report according to one or more examples

[0029] Fig.10 Depicted is an illustration of an exemplary GUI related to analyzing an ASU according to one or more examples.

[0030] Fig.11 Depicted are diagrams of exemplary GUIs for implementing various methods described herein. DETAILED DESCRIPTION

[0031] The terminology used below is to be interpreted in its broadest reasonable manner, even when it is used in conjunction with the detailed description of certain specific examples of the present disclosure. In fact, certain terms may even be emphasized below; however, any term intended to be interpreted in any limiting manner will be openly and specifically defined in this detailed description. Both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting in nature.

[0032] In the present disclosure, the term "based on" means "based at least in part on". Unless the context indicates otherwise, the singular forms "a", "an", and "the" include plural referents. The term "exemplary" is used in the sense of "example" rather than "ideal". The terms "comprises", "comprising", "includes", "including" or other variations thereof are intended to cover a non-exclusive inclusion, so that a process, method, or product that includes a series of elements does not necessarily include only those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. The term "or" is used disjunctively, such that "at least one of A or B" includes (A), (B), (A and A), (A and B), (B and B), etc. Relevant terms such as "substantially" and "generally" are used to indicate possible variations of ±10% of a specified or understood value.

[0033] According to certain aspects of the present disclosure, disclosed herein are methods and systems for managing the risk of plant loss due to disease, pests (e.g., insects), and weather-related issues in agricultural systems. Some agricultural systems (such as cocoa farms) are agroforestry agricultural systems, which present unique problems when attempting to optimize plant yields. Many agroforestry agricultural systems are characterized by a hierarchical level of agricultural system units ("an ASU" or "multiple ASUs") ranging from a single plant to an entire agricultural system (e.g., a farm, a group of farms, a planting area). More specifically, in some examples, an ASU can be defined in order of size and / or number of plants as: a plant; an area unit of a plant (e.g., a hectare); a block composed of area units (e.g., a field); a segment composed of a block; an agricultural system composed of segments (e.g., a farm); and an area including one or more agricultural systems.

[0034] While some agricultural systems including certain types of plants (e.g., row crops such as corn) can be divided into ASUs with substantially uniform shapes at the area unit level, agroforestry agricultural systems (e.g., cocoa farms) can be divided into unevenly shaped area units (e.g., hectares) and resemble natural forests. In some aspects, agroforestry agricultural systems can consist of different areas that use or are exposed to different levels of light and nutrients. In addition, agroforestry agricultural systems can define land use systems that involve the deliberate use of trees, shrubs or other perennial woody crops and / or animals, and may require careful analysis and consideration of limiting factors before introducing plants. In addition, many of these systems must be uniquely designed and managed to achieve production diversification and maintain production, increase social, economic and environmental benefits, and reduce production costs and risks.

[0035] A common risk to agroforestry agricultural systems is asymptomatic diseases and their asymptomatic spread, which can be particularly difficult to address due to the forest-like nature of these systems. This may be due to the fact that the same type of plant may occur in multiple ways, even separately within the same ASU (such as a block), making identification of diseased plants very difficult. Even if a plant is identified as having a disease, understanding the spread of this disease in the corresponding (agroforestry) agricultural system is almost impossible until the disease fully manifests itself. Some indicators may include the presence of certain insects or fungi on or around plants, but system operators cannot always rely on this "catch it in the act" type of identification to develop comprehensive risk mitigation strategies.

[0036] Examples of agroforestry systems may include cocoa farms, which may be characterized by hills, rivers, animals, and other factors that affect where / how cocoa trees are grown. For purposes of this disclosure, the terms "cocoa" and "cacao" are considered synonymous. Consistent with other agroforestry systems, cocoa trees are not like corn or other row plants, whose area units (e.g., hectares) are typically uniformly shaped (e.g., squares). Cocoa in particular, heterogeneity extends to the appearance of these plants and how cocoa is grown, harvested, and processed.

[0037] More specifically, cocoa is a unique plant that includes flowers and pods that grow from the trunk of the cocoa tree rather than branches. The pods can be red, purple, yellow, or orange, and do not fall from the trunk. The pods must be physically cut off, which is usually done with a machete, even on large farms. This is because automated harvesting solutions are generally ineffective for trunk-based pod-growing plants such as cocoa.

[0038] Processing is another unique area of ​​the cacao tree. The pods must be opened to remove the cacao beans which are surrounded by the pulp. The cacao beans must then go through a fermentation process where the entire cacao bean ferments within the pulp. This is the first and necessary step for the cacao beans to eventually develop a flavor that most people recognize as chocolate. Fermentation can involve completely different processes depending on the region where the cacao beans are harvested. For example, in West Africa, fermentation can be done by piling the beans into large piles and covering them with banana leaves. On the other hand, in equatorial regions like Ecuador, fermentation is done by leaving piles of cacao beans out in the sun.

[0039] Cacao trees can also suffer from asymptomatic diseases that can result in catastrophic plant losses. For example, one disease found in cacao trees is cacao swollen shoot disease (CSSD), which can be caused by a number of different viruses. A key and devastating aspect of CSSD is the propensity for the disease to spread asymptomatically. In some cases, cacao trees with CSSD may be symptom-free for up to two years. However, once CSSD symptoms appear, entire agricultural systems (e.g., farms) may have to be burned or otherwise destroyed because the disease has no cure, kills infected trees, and can spread rapidly and widely. In fact, CSSD is considered by some to pose the greatest threat to the world's cocoa.

[0040] For example, in some areas of West Africa, losses of cocoa trees due to CSSD are estimated to account for more than 70% of the total number of cocoa trees in the region. System operators (e.g., farmers) around the world report chronic misdetection and attempts to control the virus that causes CSSD by applying pesticides or replanting too early, only to infect seedlings with the same virus. CSSD has also proven to have a devastating impact on livelihoods in areas of the world where cocoa is grown. Tree losses in these areas result in: reduced spending in key areas such as education, food, and health; limits people’s mobility and their ability to access credit and feed their families; reduces the number of meals people can eat, affecting food security and nutrition; and affects young people, whose schooling may be interrupted due to lack of funds and the need for older children to contribute to income generation.

[0041] The methods and systems described herein may be particularly effective in overcoming some of the unique challenges posed by agroforestry systems, including cocoa tree agricultural systems. In agroforestry systems, plant cultivation may be susceptible to a variety of pests, and identifying these pests plays a vital role in implementing effective pest management strategies. The methods and systems described herein may provide a user-friendly solution that can be customized based on the region where the plant is found (such as Southeast Asia, South America, and Central and West Africa where cocoa trees can be found), and assist system operators in identifying insects and pests that damage plants (such as cocoa trees).

[0042] In addition, system operators and agricultural experts, etc. can use the exemplary methods and systems described herein to access a comprehensive source of information (e.g., a database) about insects that may affect specific plants and are prevalent in specific areas. The methods and systems described herein can also provide real-time information about the appearance, behavior, and potential damage caused by pests, thereby enabling system operators to quickly and accurately identify specific insects that affect their plants (such as cocoa trees). In addition, the methods and systems described herein can provide localized suggestions for pest control methods and preventive measures that are particularly suitable for regional climatic conditions and agricultural practices where pest outbreaks are highly controlled. Using the customized methods and systems described herein can provide system operators (such as cocoa growers) with access to relevant and timely information, and enable them to make informed decisions to protect their plants and increase production.

[0043] In some examples, methods and systems according to the present disclosure can provide an exemplary risk management platform that is configured to: (1) collect, process, analyze, organize and integrate, characterize and re-characterize, and present in one or more forms pest, disease, weather, and plant condition data; and (2) assist in managing integrated pest risk for agricultural systems. Accordingly, aspects of the present disclosure relate to methods and systems that are particularly suitable for managing agricultural systems for growing plants, such as agroforestry agricultural systems that include tree crops.

[0044] In addition, aspects of the present disclosure relate to methods and systems particularly suitable for managing smallholder agricultural systems with non-standardized farm layouts, sizes, and agricultural practices. Aspects of the present disclosure relate to methods and systems for managing large-scale agricultural systems, including plants consisting primarily of tree crops in agroforestry systems or full-sun systems (such as systems located in tropical regions of the world). Aspects of the present disclosure relate to methods and systems particularly suitable for managing plants susceptible to pests, which are dispersed over considerable distances and / or may be difficult to identify. Aspects of the present disclosure include comprehensive databases designed specifically for each region. Such comprehensive databases may be repositories of region-specific information, including: definition / identification-based information on insects, pests, and diseases prevalent in the corresponding region and / or corresponding areas within the region and specific to the corresponding plants therein; real-time information on the presence of recorded insects, pests, and diseases; real-time information on pests, which may include details on the appearance, behavior, and potential damage of these insects and other pests; historical and real-time localized recommendations for pest control methods and preventive measures, which are particularly suitable for the climatic conditions and agricultural practices of the corresponding region where pest outbreaks may be highly controlled.

[0045] Thus, the methods and systems described herein may be configured or otherwise designed to manage risk in growing tree crops and protect the yield of these crops, which may be selected from the genus Theobroma or Herania or their interspecific and intraspecific hybrids within these genera, more preferably selected from the genus Theobroma and Theobroma grandiflora. One of ordinary skill in the art will recognize that the cocoa species may include all genotypes, particularly all commercially useful genotypes, including but not limited to Criollo, Forastero, Trinitario, Arriba, Amelonado, Contamana, Curaray, Guiana, Iquitos, Maranon, Nacional, Nanay and Purus, as well as their crosses and hybrids.

[0046] Figure 1 A flow chart of an exemplary method for managing risk in an agricultural system according to one or more examples is depicted. At step 110, an agricultural system unit ("ASU") selection may be received. In some examples, receiving an ASU selection may include receiving a selection of a plant, an area unit, a block, a section, a farm, or a region. In some examples, the ASU may be displayed for selection in a user interface implemented by a computing device. According to some aspects of the present disclosure, a computing device may include a processor, a memory, and a non-transitory computer-readable medium containing instructions executed by the processor.

[0047] In addition to the type of ASU, the ASU selection received in step 110 may specify a selection type. More specifically, the interface through which the ASU selection is received may be implemented by a risk management agent executing on a computing device through which the ASU selection is received. In some examples, the selection type may correspond to a module implemented by the exemplary risk management agent and / or the context in which the ASU is selected. As described in reference to Figures 5 to 11 Described in more detail, exemplary modules may include, but are not limited to, reporting, reconnaissance, assessment, analysis, and query modules.

[0048] In some examples, a risk management agent according to the present disclosure may be part of, or configured to be compatible with, a software product that is: installed on a computing device; provided via a web application executed in a browser running on the computing device; and / or implemented on a computing device via an application programming interface (“API”). For any specific implementation of a software product associated with the above-described exemplary risk management agent, the software product may be provided, at least in part, by a processor associated with a risk management platform implemented via a backend. In some examples, such a backend may include one or more computing devices (such as one or more servers), and each computing device of the platform may include a processor, a memory, and a non-transitory computer-readable medium containing instructions executed by the processor.

[0049] An exemplary software product implemented via an exemplary back end may be configured to instantiate, update, maintain, or otherwise support aspects of a risk management platform, risk management agent, or portions / modules thereof, and may provide tools for: mapping out reconnaissance paths; integrating new plant or ASU analysis into overall assessment information for the plant or ASU and higher-level ASUs (such as an entire agricultural system) that include the plant or higher-level ASU; distributing notifications to workers of an agricultural system in addition to any and all system operators (e.g., farmers); generating visualizations (e.g., heat maps) of an agricultural system reflecting diseased plants; generating static, conditional, and / or operation-dependent user interface components and / or selectable options provided by the exemplary risk management agent; and other related features.

[0050] At step 120, the exemplary method may include accessing an analysis of one or more plants corresponding to the ASU selected in step 110 based on the selection type. According to aspects of the present disclosure, when referring to data, protocols, analyses, assessments, recommendations, mapping services, or other elements, the term "access" may encompass: sending, such as sending a computer-implemented call to stored information; initiating, such as initiating one or more functions of a software product or computing service (such as a plant analysis service); connecting, such as connecting to a database or external or other type of information source; and displaying, such as displaying locally or remotely stored information, such as a single plant analysis, ASU assessment / assessment map, and / or report. Accessing may include other functions that may generally result in the following results: generally generating and / or presenting additional data, and generating and / or presenting additional data related to the ASU selected in step 110. The term "accessing" may also include performing the function or goal following the term.

[0051] In one example, accessing the analysis in step 120 may include determining, sending a request for, or otherwise initiating an exemplary process for analyzing a plant or group of plants that may be the subject of ASU selection in step 110. Such a process for analyzing may be incorporated by viewing or capturing an image or video using a camera, or accessing a stored image or video. Additionally, accessing the exemplary analysis may further include loading, sending, uploading, or otherwise providing the view, image, or video through a plant analysis service.

[0052] In some examples, the plant analysis service may be provided through a web application, an API integrated into a risk assessment agent or tool of the risk management platform, or other types of software products, which may be an independent product with which the exemplary risk management platform is configured to exchange data. In other examples, the plant analysis service may be embodied as a module within a portion of the risk management platform, such as a risk management agent. In addition, the plant analysis service initiated by accessing the analysis in step 120 may be configured to analyze a single plant, several plants, or a plant group defining a higher level ASU (such as an area unit) at one time or through a series of analysis processes. In some examples, the analysis process may include some type of optical or other type of scanning of a plant or a group of plants (or insects or pests). In other examples, the analysis process utilized by the plant analysis service may be combined with the use of a LIDAR sensor.

[0053] In some examples, accessing the analysis may include initiating or requesting the performance of a plant analysis, such as by a plant analysis service, such as via electronic communication. Such a plant analysis service may be combined with pest management and / or plant entomology services that may be implemented directly or indirectly by, included in, or in communication with an example risk management platform or risk management agent according to the present disclosure. Initiating the performance of such a plant analysis may generate information about one or more plants, or detect or identify values ​​of tracked parameters associated with one or more plants. Such tracked parameters may include: the number of plant parts that may be damaged; the number of plants or plant parts (e.g., leaves, trunks, branches, pods, etc.) that exhibit some degree of damage; the presence of one or more insects when the analysis is performed; weather characteristics, such as whether it is raining; the amount of sunlight or the lack of sunlight; the humidity present in the environment surrounding one or more plants; the humidity exhibited by one or more plant parts; the color of a particular plant part (e.g., the color of a cocoa pod); the size of the plant; the age of the plant; the presence or absence of pesticides, chemicals, etc.; the temperature of the air; and other aspects that may detect or otherwise identify and / or may track a plant, plants, and / or the environment in which the plant or plants reside. According to one or more aspects of the present disclosure, the parameters associated with the analysis that may be accessed in step 120 may include parameters that may be used to diagnose whether a plant is diseased (e.g., exhibiting CSSD).

[0054] In some examples, accessing the step of performing an analysis, which may include performing an analysis as described above, may include, for example, a plant analysis performed by a pest management or entomology service implemented by or included in or in communication with an example risk management platform or risk management agent according to the present disclosure, and may generate information about one or more insects or other pests, or detect or identify values ​​of tracked parameters associated with one or more insects or other pests. Such insect or pest characteristics acquired in step 120 may include patterns of damage to the plant, such as chewed leaves, stunted leaf growth, leaf discoloration, leaf spots, deformed plant parts, wilting or yellowing, gall formation, boreholes / tunnels, and / or fruit damage, or a combination thereof. The analysis may help identify pests, such as cocoa pod borers, blind bugs, bark and ragweed beetles, moths, aphids, whiteflies, or mealybugs, or a combination thereof.

[0055] In one example, accessing the analysis in step 120 may include determining and implementing a protocol regarding a previously performed analysis, which may be stored on a server or other computing device of a risk management platform according to the present disclosure. In some examples, a risk assessment agent implemented on a computing device that initially receives the ASU selection in step 110 may utilize an identification of the ASU selected by the ASU to access a processor or service implemented on a back end to determine whether an analysis for the ASU was previously performed within a predetermined amount of time. In other examples, as specified by the back end, the risk assessment agent may temporarily store a predetermined amount of analysis information of a predetermined age in a memory or storage component of the computing device implementing the risk assessment agent. Thus, the risk assessment agent may access a temporary cache of this information and determine whether the ASU was previously analyzed within a specified amount of time. In the event that an analysis that meets the specified time limit is available, in a computing device used by an operator or back end processor, Figure 1 The exemplary method of may load the analysis in step 120. Otherwise, the analysis may be performed as previously described.

[0056] In step 130, the exemplary method may include accessing an assessment associated with a plant or group of plants corresponding to the ASU selection based on the analysis and selection type. In one example, the assessment may include an information package that may be processed as part of the access in step 130 to generate a visual representation of: a general status of the plant or plants; an analysis of the plant or plants; or a summary of analysis-related and / or diagnostic-related information for the ASU selected in step 110 or for ASUs including the ASU selected. In some examples, the assessment may include presenting a visual representation of the data included in the information package in the context of one or more maps and / or map types.

[0057] As reference FIG. 6A to FIG. 6C Described in more detail, the assessment may include heat maps, dot density maps, and the like. Specifically, such an assessment may provide a map of an agricultural system, wherein different portions of the map are presented in different ways relative to other portions to reflect the extent of the presence or absence of plants, insects, pests, or parameters associated with plants within the physical area of ​​the agricultural system corresponding to the respective portions of the map. In some examples, the assessment may include one or more maps, wherein different portions are shown with different colors, densities of graphical elements, and the like to indicate: different numbers of plants; different numbers of one or more types of plants relative to one or more other types of plants; different numbers of diseased plants; different levels of pests and insects; different levels of plant yield; and other quantitative measurements that may be associated with growing one or more types of plants.

[0058] In one example, accessing the assessment in step 130 may include generating the assessment based on the analysis accessed in step 120. In other examples, accessing the assessment in step 130 may simply include incorporating the information generated by accessing the analysis in step 120 into an information package for the assessment. For example, accessing the analysis in step 120 may include performing an analysis on a previously analyzed plant, and the values ​​of one or more parameters for the analysis have changed compared to the previous analysis. In such an example, accessing the assessment in step 130 may include updating the corresponding aggregated parameter values ​​for all ASUs of the plant that include the changed parameter values.

[0059] At step 140, the exemplary method may include determining a need for one or more risk mitigation techniques based on the results of accessing the analyses and assessments in steps 120 and 130. More specifically, information from the example analyses of the ASU accessed in step 120 may be processed, interpreted, or otherwise used to determine whether a plant or more than one plant requires further assessment. In another example, the risk management platform may use the analysis results in a diagnostic process in step 140 that may identify one or more plants corresponding to the ASU selection as being diseased, at risk of disease, subject to harmful pest activity, and / or damaged due to, for example, the application of a pesticide. In another example, the analysis results used by the risk management platform in step 140 may identify pests that have newly entered an area.

[0060] The determination at step 140 may be made by one or more operations of an exemplary backend of an exemplary risk management platform according to the present disclosure. In one or more instances, the exemplary method may include identifying within a higher level ASU a disease exhibited by one or more plants or pest damage exhibited by one or more plants. Additionally, at step 140, the severity or progression of the disease or pest damage may be determined or estimated.

[0061] In addition, step 140 may include identifying any risk mitigation techniques that can address the presence of the disease or identified pests and insects that are exhibited. In some examples, this may include accessing a database or other information source that includes tables, directories, or other index data related to risk mitigation techniques for growing plants. After accessing such an information source, an exemplary risk management platform or a risk management agent implemented on a computing device used by a system operator may perform a series of searches or requests and receive a process that leads to a diagnosis (including matching disease severity or pest identification with one or more risk mitigation techniques). In one example, there may be a reporting function that identifies new pests or diseases in an agricultural system or region. In one example, the database includes information about potential risks associated with pests, including their behavior, preferred habitats, and plants known to be infected by them, as well as best practices for implementing preventive actions and biosafety methods. In one example, less pesticides, fungicides, or other chemical treatments may be required because the information provided allows system operators to conduct targeted interventions for existing pests or diseases, and for large-scale agricultural systems, only the parts required in the agricultural system are intervened and treated.

[0062] In step 150, processing the results of the ASU selection received at step 110 may be configured based on at least one of the location and reporting standards of the ASU selected in step 110. Processing the results of the ASU selection may include data obtained, modified, validated, or otherwise processed by accessing one or more analyses and / or one or more assessments in steps 120 and 130, and / or determining the need for risk mitigation techniques and / or required risk mitigation techniques in step 140. Step 150 may include one or more processors identifying an initial format for such data, as well as any differences in the format specified for historical analysis and assessment records based on the location of the agricultural system that includes the selected ASU, or reporting standards established by an organization or some type of regulatory body associated with the plant type included in the ASU selected in step 110.

[0063] In some examples, the location of the ASU may determine how the data and / or any information derived therefrom is formatted in step 150 for dissemination in some form to operators or other workers of the agricultural system in which the selected ASU is located. This may include formatting elements such as units of measurement, file type, language, data categories, characteristics of data associated with one ASU relative to data of other ASUs (e.g., hierarchy), etc. Such formatting elements may be specific to the region of the world in which the selected ASU is located and take into account or otherwise reflect, for example, established reporting standards, communication protocols used, data restrictions imposed, persistent data transfer restrictions, and / or languages ​​spoken in the region of the world in which the selected ASU is located.

[0064] Such data as noted above may or may not ultimately be presented in one form or another to an operator or other worker of the agricultural system, for example, via a computing device. However, depending on the plant type associated with the ASU selected in step 110, reporting requirements established by a regulatory agency or organization may dictate (alone or in addition to location-based formatting specifications) the format (e.g., units of measurement, language, data categories, characterization of data relative to other ASUs (e.g., hierarchy)) of new and / or updated analysis and assessment information and / or risk mitigation needs and / or technologies identified by processing the ASU selection. Thus, step 150 may include one or more processes in which data resulting from accessing one or more analyses and / or assessments and / or determining risk mitigation needs and / or required technologies in steps 120 and 130 may be processed, matched to certain data fields, and formatted based on due diligence and sustainability reporting standards for the import of certain products and materials, including plants such as cocoa and its derivatives.

[0065] According to some aspects of the present disclosure, the information accessed in steps 110 to 140 (which may include capturing, processing, preparing for display, storing, analyzing, and / or updating underlying data associated with the accessed information) may be further processed in step 150 according to reporting standards established by various organizations. Such standards may be established to ensure responsible growing practices, particularly in areas where field logistics are difficult. This may include agricultural systems in remote areas of the world where access to various technologies is limited and / or farming and record keeping practices may be performed using equipment that is no longer in use and / or manually in many, if not most, parts of the world. However, the systems and methods described herein may enable the distribution, capture, and standardized formatting of data related to remote area cultivation of plants (e.g., cocoa trees) using baseline technologies (e.g., cellular telephones) that are available to many, if not most, people living in the areas where the subject agricultural systems are located.

[0066] Reporting standards (such as those mentioned above) may be intended to eliminate or reduce the negative impact of plant production / processing / supply on environmental and human rights issues. Participants in plant supply chains (such as cocoa supply chains, etc.) may be responsible for focusing on ensuring and being able to prove that plant byproducts produced, processed and supplied from a particular location are substantially free of deforestation and human rights violations. Public and private regulatory mechanisms can reliably and transparently track plants grown, processed and supplied in certain parts of the world, can promote compliance and correct non-compliance. The reporting level that can be promoted by the exemplary process performed in step 150 and can be standardized in various specific implementations of the exemplary platform described herein can effectively help reduce deforestation, reduce the carbon footprint of certain plants (such as cocoa), and ensure the humane treatment and working conditions of individuals employed in various plant planting industries (such as the cocoa industry).

[0067] At step 160, the exemplary method may include indicating in a graphical user interface ("GUI") a result of processing the ASU selection received in step 110 based on a selection type previously identified by a processor of a backend of a risk management agent and / or risk management platform according to the present disclosure. In one example, the GUI may be provided via an interface (e.g., a screen) of a computing device on which the risk management agent may execute or otherwise be implemented. The GUI may be displayed on a computing device and, depending on the selection type associated with the ASU selection in step 110, may represent: an analysis of the plant or a higher-level ASU that includes the plant; an assessment of the selected ASU or an ASU that includes the selected ASU; a report related to the selected ASU or an ASU that includes the selected ASU; a reconnaissance map for the selected ASU or an ASU that includes the selected ASU; a profile summary (including a system profile) for the selected ASU or an ASU that includes the selected ASU; or a module that searches for risk mitigation technologies from a larger group of technologies based on the ASU selection in step 110. As will be referenced Figures 5 to 11 In more detail, the elements of the GUI indicating the results of processing the ASU selection in step 160 may provide a series of information intended to manage the plant loss risk of the agricultural system including the ASU selected in step 110 .

[0068] Figure 1The exemplary method is combined with an exemplary computing device configured to implement the method to provide an integrated solution that can help identify and manage agricultural risks, thereby effectively acting as an assistant to agricultural system operators. In addition, the exemplary risk management platform described herein may be particularly suitable for mitigating plant losses in agroforestry agricultural systems (such as cocoa farms) and optimizing plant yields. This may be due in part to the ability to provide such risk management platforms using technology available at remote locations, which are limited to access to more advanced and / or complex technologies than cellular phones or other handheld or computing devices of similar complexity (e.g., tablet computers, laptops, etc.). The exemplary risk management methods and systems according to the present disclosure can be uniquely flexible, and to some extent, any platform described herein can be customized for different types of plants (e.g., perennial plants), regions of the world, locations within the regions, and agricultural systems of different types and sizes (such as large commercial or other high-productivity farms, and small-scale agricultural systems operated by individual farmers, families, or 5 to 10 operators (hereinafter referred to as "smallholder systems")).

[0069] For high productivity farms that can carry out large-scale plant cultivation, Figure 1 The methods and other exemplary methods and systems described herein may provide tools for pest monitoring and management. In addition, the risk management platform according to the present disclosure may be used by system operators as well as agronomists to identify pests, track their prevalence, and assess the extent of damage in different areas of an agricultural system. Subsequently, the information provided by the methods and systems according to the present disclosure may: help make data-driven decisions about pest control measures, such as targeted pesticide applications or implementation of an integrated pest management strategy; provide real-time updates and recommendations for specific regions, thereby ensuring accurate identification of pest threats; and enable quick and effective response to pest outbreaks to minimize potential plant losses and maintain consistent yields.

[0070] When applied to smallholder systems, exemplary methods and systems according to the present disclosure can provide several advantages for system operators, particularly those operators who may have limited access to resources, technical expertise, and information about pest management. A risk management platform according to one or more aspects of the present disclosure can fill resource, expertise, and / or information gaps by providing computer-implemented tools and interfaces that enable smallholder system operators to easily identify pests as early as possible and understand the risks associated with such pests. In some examples, the risk management platform can include a software-based recommendation service that provides cost-effective and environmentally friendly pest control solutions suitable for smallholder systems. In some examples, these solutions can take into account financial constraints and available resources. In addition, the exemplary recommendation services described herein can be used as educational tools and provide smallholder system operations with valuable insights into: pest biology; prevention strategies; agricultural best practices; and increase the opportunity to acquire knowledge, enabling these operators to increase productivity and reduce plant losses.

[0071] Thus, an exemplary agricultural risk management platform according to the present disclosure can assist agricultural system operators (e.g., farmers) in managing agricultural risks, particularly those risks that may exist in cocoa trees and agricultural systems designed to optimally grow or otherwise cultivate cocoa trees.

[0072] Figure 2 A sequence diagram of an exemplary method for managing risk in an agricultural system according to one or more examples is depicted. At step 210, the exemplary method may include receiving an ASU selection via an interface of a user device. In one example, the ASU selection may be selected via a display including a list, map, or other type of representation of the ASUs for the agricultural system. In some examples, at step 210, the selection of the ASU may be received at an interface from a test suite device, an image processing service, a drone operation service, a user, or via a user interface. Figure 2 The selection of the ASU may be received by an API of another service implemented on a user device or in communication with the user device. The selection may be provided by a user (such as a system operator or other individual associated with the agricultural system) using various types of input / output (I / O) devices and / or services implemented by the user device, which may be a computing device as defined herein. This may include a mouse, a touch screen, a voice recognition service, and / or other biometric related services.

[0073] In some examples, the ASU may be selected with reference to ASUs that have been tested with the test suite.In addition, the test suite may include a device that may include an interface and is configured to communicate with the user device such that the ASU selection received in step 210 is received from the test suite device.

[0074] In step 214, the risk management agent implemented on the user device may identify the selected ASU, the type of ASU selection made, and any access protocols that may be associated with the selection type. In addition, at step 214, the risk management agent may cause data (including data of the selected ASU, the type of ASU selection made, and the access protocol) to be sent (e.g., via the user device) to a processor at the back end. In one example, the user device may communicate with the ASU via a network or in accordance with other communication protocols (such as reference Figure 4 The processor or service at the back end may employ similar types of data transmission in the following operations: accessing external information as part of, for example, step 222 discussed below; accessing maps and historical weather information as part of, for example, step 242 discussed below; and sending information packages to risk management agents as part of, for example, step 246 discussed below.

[0075] The selected ASU may be identified based on an identifier included in a data instance generated or referenced as part of the selection process or type. In some examples, the selection type may be identified based on the source and / or method of receiving the ASU selection in step 210. In other examples, the selection type may correspond to an option displayed in a GUI implemented through an interface of a user device. For example, a reconnaissance path option may be associated with an ASU, and selection of the reconnaissance path option in the context of an associated ASU may provide or otherwise define the identity and type selection of the ASU. The access protocol may be identified by a risk assessment agent, as permitted by the risk management platform backend. In other examples, data associated with the access protocol may not be available to a risk management agent implemented on a particular device (e.g., an unauthorized device or a public device) and / or a risk handling agent implemented through a particular implementation of the risk management agent (e.g., a specific implementation through a network application).

[0076] As previously described, an exemplary risk management agent according to the present disclosure may be part of, or configured to be compatible with, a software product that is: installed on a computing device; provided via a web application executed in a browser running on the computing device; and / or implemented on the computing device via an application programming interface (“API”). For any specific implementation of a software product associated with the exemplary risk management agent described above, the software product may be provided at least in part by a web application executed in a browser running on the computing device; and / or implemented on the computing device via an application programming interface (“API”). Figure 2 The backend implementation of the risk management platform shown is provided by a processor associated with it.

[0077] In some examples, the backend may include one or more computing devices (such as one or more servers), and each computing device of the platform may include a processor, a memory, and a non-transitory computer-readable medium containing instructions executed by the processor. In some examples, the backend of the example risk management platform according to the present disclosure may implement the following processes: generate GPS-rendered scouting maps; enable data collection at the plant, block, section, farm, and region levels; use statistical sampling methods and patterns for data collection; use GPS technology to guide system operators or designated data collectors (e.g., workers, drones) of agricultural systems through statistical scouting and / or sampling patterns; be configured to extrapolate data based on summary and geostatistical data and create heat map visualizations based on the extrapolated data; and / or assist in field diagnosis, which may include performing image recognition of pathogens, pests, and abiotic symptoms (nutrients, fertilizers, water stress).

[0078] At step 218, the exemplary method may include the back end implementing a plant analysis or ASU reconnaissance access protocol. In one example, step 218 may be performed by a processor of the back end. Specific implementation of the access protocol may include retrieving, requesting, implementing safety procedures, and / or sending, generating, or allowing access to an analysis or reconnaissance path that includes one or more plants corresponding to the ASU selected by the ASU received in step 210. In some examples, step 218 may include communicating with Figure 1 A similar process is performed as in step 120 of the exemplary method.

[0079] In step 222, the backend may access external information sources, for example via a processor. This may include accessing an unmanned aerial vehicle system, a server and / or other information source associated with a weather information system ("weather server"), and / or a server and / or other information source associated with a location and mapping system ("location / map server"). The weather information input to the backend from step 222 may relate to local, regional, and global weather events and conditions. In some examples, the information from the unmanned aerial vehicle system may be provided by a drone, which may scout the ASU upon receiving a selection of an ASU at step 210 (or step 110).

[0080] In some examples, external information sources may include one or more types of plant disease detection test kits. Specifically, such test kits may be configured to determine whether a plant (e.g., a cocoa tree) is infected with an asymptomatic disease (such as CSSD disease). An exemplary test kit may be able to convey whether a cocoa tree is positive for CSSD, and may employ, for example, a dip test or other types of tests that avoid false positives or do not involve complex results or complex processes for reading results. In some examples, such test kits may include a test strip that may be observed to view a positive or negative reading, or may be scanned with a device that indicates a positive or negative result to a user. In some examples, an exemplary test kit that may be accessed by a back end or a risk management agent may include one or more devices that are configured to be connected to a network or to transmit data to a back end in some manner, for example, via a telephone, which may further process test results about plants, blocks, sections, systems, and / or regions.

[0081] At step 226, the exemplary method may include the processor implementing one or more assessment access protocols. At step 228, the integration service may update the assessment for the agricultural system and the ASU profile based on the processes performed by the processor and the communications with the processor. In some examples, steps 226 and 228 may include communicating with Figure 1 A similar process is performed as in step 130 of the exemplary method.

[0082] Additionally, step 226 may include a processor for the back end performing image data processing and management of geo-corrected farm image data processing and map creation, analysis of linked data types input from various data layers (e.g., level of ASUs), visualization of data, generation of data packages for implementing decision dashboards on user devices through interfaces provided by the back end and / or via risk management agents, and combinations thereof. In other examples, the assessment access protocol implemented at step 226 may be combined with drone flight data analysis processing and management, and / or drone stress monitoring using hyperspectral, thermal, and RGB sensors, and other sensor types required for stress identification. Additionally, at step 228, a processor for the exemplary risk management platform back end may integrate drone data, such as drone flight protocols for stress monitoring and artificial intelligence (“AI”) analysis, and data from drone flight disease stress identification technology.

[0083] With further reference to step 228, in one or more examples, the ASU configuration file can be updated with plant specific information, which can correspond to information obtained by implementing the access protocol described above.

[0084] In some examples, a profile for an ASU (e.g., an agricultural system (e.g., a farm)) may include information or values ​​for the agricultural system corresponding to parameters or attributes including, but not limited to: location; agricultural system size; age; plant type (e.g., cocoa); plant species type (e.g., hybrid cocoa); number of co-planted plants; number of high-yielding plants; monthly / annual average yield (e.g., kilograms of cocoa yield per hectare); pests or insects previously determined to be present in the agricultural system; number of healthy plants per scouting event and per season; system maintenance practices (yes / no questions about best practices); fermentation process; degree of adherence to harvest and / or post-harvest best practices; proximity to neighboring agricultural systems; monthly / annual average rainfall; monthly / annual average temperature; monthly / annual average humidity; type of agricultural system; % of plants in shade; % of plants in full sun; % of planting density; harvesting method; and other parameters.

[0085] In other examples, a profile for an ASU (e.g., a plant (e.g., a cocoa tree)) may include information or values ​​for the plant corresponding to parameters or attributes including, but not limited to: genus; species (scientific); canopy cover; plant size (e.g., height, diameter at breast height); number of plant parts produced; number of damaged leaves; number of damaged non-leaf plant parts; presence of insects or pests; fertilizer used; branch count; proximity to co-planted plants; location in an agricultural system; resistance traits; disease history of nursery plots; pest and disease history of fields / plots; age; current disease status; type of ASU including the plant (e.g., uniform area unit, non-uniform area unit); type of agricultural system including the plant (e.g., agroforestry system); and other parameters or attributes.

[0086] As shown, the backend may implement an integration service, as well as an integration service and a recommendation service, one or more of which may provide a software product that may be provided, at least in part, by a processor of the backend or other computing device associated with the risk management platform implemented by the backend. Thus, one or more of the integration, modeling, and recommendation services may be configured to instantiate, update, maintain, or otherwise support aspects of the risk management platform, the risk management agent, or portions / modules thereof.

[0087] At step 230, Figure 2 An exemplary method of may include generating a modeling instruction at a processor. In one example, the modeling instruction may include analyzing, reconnaissance, evaluation, and / or externally obtained information from any of the foregoing steps described above. In another example, the modeling instruction may include information input as part of the ASU selection received in step 210. For example, the ASU selection may include a request for a model that specifies an ASU and a time period for the model.

[0088] In step 234, a modeling service implemented by the back end may access historical data related to the agricultural system corresponding to the ASU selected in step 210 and generate a model for the selected ASU and / or ASUs including the selected ASU. In some examples, the modeling service may perform machine learning predictive management and provide machine learning predictive analysis. In other examples, the modeling service may be configured to perform yield, disease, and / or loss predictions for the selected ASU and / or ASUs including the selected ASU (e.g., the entire agricultural system). The modeling service may utilize, generate, or otherwise implement stochastic and mechanical predictive models and combinations thereof for prediction. In addition, step 234 may include utilizing, generating, or otherwise implementing metadata machine learning analysis, sensor inputs from various sources linked in time and space, and historical data analysis for predictive management.

[0089] At step 238, the exemplary method may include the processor determining a need for risk mitigation measures and implementing the recommended service based on the determined need. In some examples, step 238 may include similar to Figure 1 The process, inputs, and outputs of step 140 of the exemplary method of FIG. At step 242 , the recommendation service may evaluate the propagated threat and identify one or more risk mitigation options.

[0090] In some examples, this may include notifying the user of one or more guides selected from one or more sets of guides related to integrated pest management best practices and providing access to such guides. Such guides may be selected by the recommendation service and / or processor based on analysis, evaluation, and / or external information from other steps such as steps 218, 222, and 226. In addition, the recommendation service may provide access to decision tools that may direct the operator to one or more guides. In addition, the recommendation service may process Figure 2 any information accessed, received, or generated in any of the preceding steps of the exemplary method, and identifying virtual and other types of training guides in various media formats that relate to: plant diseases, insects, abiotic symptoms; insect and disease science knowledge; and combinations thereof. In other examples, at step 242, based on the risk mitigation needs determined in step 238, the recommendation service can identify, suggest, provide access to, and / or obtain information related to: sampling techniques for pathogens and insects; diagnostic help functions; diagnostic identification and sampling instructions; accessing and using a network of diagnostic professionals; and / or finding a local diagnostic laboratory and / or providing directions to a local diagnostic laboratory; and combinations thereof.

[0091] At step 246, the exemplary method may include generating an information package and information distribution instructions at a processor at the back end based on the combination of data associated with the processes performed, implemented or completed in steps 218 to 242. Such an instruction package may include instructions that, when executed by a processor of a user device under the direction of a risk management agent, for example, at step 250, may cause one or more GUIs to be displayed on the user device. In addition, the instructions of step 246 may include instructions, communication protocols, etc. for disseminating information related to the analysis, assessment, model and / or risk mitigation techniques of the previous steps. Such instructions may specify a distribution list of individuals and / or organizations for receiving the information. This may include other workers or operators of the agricultural system; management agencies associated with the plants selected by the ASU corresponding to step 210; operators of other agricultural systems that may be located near or within the general area that includes the agricultural system (including the ASU selected in step 210); and other relevant individuals or organizations.

[0092] In step 250, the risk management agent may process the information package and the distribution instructions and generate a graphical user interface based thereon. At step 254, the exemplary method may include displaying an interface of the GUI generated in step 250. In some examples, the information package received in step 250 may include dissemination instructions that the risk management agent executes in step 260. Thus, at step 260, depending on how the risk management agent may be implemented on the user device (e.g., as a dedicated application, a web application, an API, via a cloud-based service, etc.), the risk management agent may send, request permission to send, or request delivery of a notification to individuals and / or organizations associated with an agricultural system, or group of agricultural systems, or a region that includes an ASU specified in the ASU selection in step 210.

[0093] Figure 3 A flowchart of an exemplary method for identifying agricultural risk mitigation techniques according to one or more examples is depicted. In some examples, Figure 3 The method may be particularly applicable to cocoa trees and agricultural systems including cocoa trees. At step 310, a profile of at least one plant may be received. At step 320, the exemplary method may include determining a risk score based on information included in the profile, additional historical data, and / or any analysis or assessment information related to the plant that may be referenced in the profile or accessible as a result of an indexing process that may be implemented by an exemplary risk management platform according to the present disclosure. In one example, an assessment of an individual plant may include a diagnosis or identification of damaged leaves and / or an indication of the presence of one or more insects.

[0094] At step 330, the exemplary method may include determining whether the risk score indicates that the plant is diseased. In a specific implementation specific to an agricultural system including cocoa trees, as shown, step 330 may be specific to determining whether one or more plants exhibit CSSD. In some examples, the risk score determined in step 320 may be compared to a threshold score in step 330. In the event that the risk score is greater than the threshold, at step 340, the respective proximity of the one or more plants or an ASU including the one or more plants to another ASU (e.g., another block or section) and / or another agricultural system may be evaluated. In the event that the ASU being evaluated is within a minimum distance of another ASU or agricultural system, the implementation Figure 3 The risk management platform of the exemplary method can issue a global alert at step 342. In some examples, the global can refer to all operators and other workers of the agricultural system. In other examples, the global can refer to the region including the agricultural system (the agricultural system including one or more plants from step 310), and other agricultural systems located in the region.

[0095] In some examples, if the risk score does not exceed the threshold score, then in step 332, the risk management platform may compare the risk score to a lower threshold. The lower threshold may indicate a combination of conditions for other plants that did not exhibit CSSD when those conditions were observed, but later exhibited CSSD. Depending on certain aspects, these conditions may or may not be considered symptoms of CSSD. Instead, such conditions may be co-morbid for plants that ultimately exhibit CSSD. In other examples, the profiles of one or more plants may be (again) examined in step 332 for any parameter values ​​and / or attributes that, in isolation, are associated to some extent with the plants that ultimately exhibited CSSD. At step 334, current condition information as well as historical condition and assessment information may be accessed and a determination may be made as to whether one or more plants exhibit another problematic condition that may be unrelated to CSSD.

[0096] Once a global alert is issued in step 342, an ASU is determined not to be near another ASU in step 340, one or more plants are determined to be potentially afflicted with CSSD in step 332, or another issue is identified in step 336, the risk management platform may identify risk mitigation techniques in step 350. In some examples, one or more processes performed in step 350 may be similar to Figure 2 The process in step 238 and / or step 242 of the exemplary method.

[0097] At step 360, the exemplary method may include the risk management platform and / or risk management agent issuing and / or sending a local alert. In some examples, at step 310, the local alert may be sent to computing devices associated with all workers and operators of an agricultural system including one or more plants. In other examples, the alert may be sent to a selected group of individuals associated with the agricultural system. In some examples, the alert may specify an identified problem or disease, a list of individuals to receive the alert, an identified risk mitigation technique, proximity between ASUs, and / or an indication of urgency.

[0098] At step 370, the record of the agricultural system including the one or more plants from step 310 may be updated. In some examples, this may include updating the assessment and corresponding profile associated with the one or more ASUs including the one or more plants. In addition, step 370 may include updating the Figure 2 A similar process is performed as in step 228 of the exemplary method.

[0099] Figure 4 Depicted are example system components for managing risk in an agricultural system according to one or more examples. Figure 4 The exemplary system components shown in can provide or otherwise define an exemplary risk management platform, which is configured to assist in collecting and / or act as a repository for collecting plant level, area unit level, section level, agricultural system level and regional level data from fields, farms, greenhouses and nurseries. In some examples, the exemplary system components can monitor and operate based on the conditions observed in the exemplary agricultural system 410, as shown in the figure. Such an agricultural system may include plants 412 (e.g., cocoa trees), which include identifiable plant parts, such as leaves 414 and non-leaf parts 416 (e.g., pods), which can be monitored for diseases, insects, pests and / or pesticide exposure levels. In some examples, the agricultural system 410 can be an agroforestry agricultural system, wherein the plant 414 grows below the non-cultivated plant 418 (e.g., large trees), which can provide shade for the plant 412 unevenly across the area defining the agricultural system 410.

[0100] The data collected can include pest and disease data for various plants (e.g., cocoa trees) and plant parts (e.g., organs, leaves, pods, tissues) that may be affected by: (a) fungi, bacteria, viruses, and other pathogens; (b) insect and mite species; and / or (c) abiotic symptoms (nutrient, fertilizer, water stressors).

[0101] The system component 400 may include a backend 450, one or more user devices 420, one or more computing devices dedicated to data collection such as drones 424 and test suites 428, and various additional (external information) sources. In some examples, additional information sources may include devices such as satellites 430 and / or servers or computing systems that provide or otherwise define information systems. As shown, such information systems may include weather information systems 460, map systems 470, and reporting systems 480. System components and information systems may communicate via a diverse network 440 that includes different subnets such as the Internet 442 and one or more cellular networks 444. In addition, user devices 420, drones 424, and test suites 428 may communicate directly with each other via wireless communication protocols (e.g., Bluetooth, Bluetooth low energy, Zigbee, or Wifi chips - this option may allow direct communication with, for example, the cloud).

[0102] In one example, the back end 450 may include one or more physical servers, and / or cloud-based virtual servers that support services and agents running on other system components. In addition, the back end 450 may be equipped with software-based tools through which administrators can monitor, manage, update, and modify various aspects of risk management agents implemented, for example, on one or more user devices 420. In addition, the back end may support the operation of services and agents (e.g., software applications) implemented on various devices. Such devices (which may or may not include user devices 420) may be managed devices that are directly controlled by the back end 450. Regardless of the level of control that the back end 450 may have, each service and / or agent running or otherwise implemented on the back end 450, user devices 420, drones 424, and test suites 428 may be part of a software product provided at least in part by the back end 450, or configured to be compatible with the software product.

[0103] The back end 450 may be supported by analysis, evaluation, and diagnostic repositories 452, 454, 456. According to one aspect of the present disclosure, each of these repositories may be a database hosted on one or more servers. In another example, one or more repositories may be cloud-based storage components as part of an infrastructure that includes various computing devices (e.g., user devices and wearable devices) and cloud-based services interconnected via local area networks, wide area networks, wireless communications, and the Internet.

[0104] For example, additional features of the systems and methods described herein (including recommendation services implemented on the back end 450) may include: receiving pesticide inputs and monitoring resistance program alignment; providing pesticide compliance guidance and monitoring; providing biocontrol compliance guidance and benefit monitoring; and combinations thereof. In some examples, for example, the risk management platform provided by the back end 450 and / or the risk management agent implemented on the user device 420 may employ point cloud data storage, in-network and out-of-network data upload and processing capabilities, and APIs of agricultural system management software, and combinations thereof.

[0105] The system and method described herein can assist in the early detection and monitoring of pests in agricultural systems. Operators (e.g., farmers) and agricultural experts can use the risk management agent implemented by the risk management platform to quickly identify unfamiliar insects and report their existence through computing devices. An exemplary risk management platform can promote the timely sharing of information, and appropriate measures can be implemented to prevent colonization and propagation of invasive pests. In addition, the risk management agent implemented by the risk management platform through computing devices can provide information about the potential risks associated with pests, including corresponding behavior, preferred habitats, and crops known to be attacked by these pests. Then, the operator may have the knowledge required for taking preventive measures, implementing biosafety measures, and effectively managing potential pest invasions. Finally, the system and method described herein can promote sustainable plant (e.g., cocoa) production by minimizing pest damage and promoting effective pest management practices.

[0106] Figure 5 Depicted is a diagram of an exemplary graphical user interface ("GUI") for implementing the various methods described herein. More specifically, Figure 5 An illustration of an exemplary GUI 500 is provided that presents a home page 510 and a menu / navigation bar 580 for selecting different modules that may be provided by the risk management platform through a risk management agent implemented on a user device 502. In one example, individual ASUs for an agricultural system may be selected from any of the modules described herein. The combination of specified ASUs selected within a particular module may define the type of selection for purposes of aspects of the exemplary methods described herein (e.g., step 120, step 214).

[0107] In one example, the home page 510 may provide: a system configuration file option 505 for accessing a reference FIG. 6A to FIG. 6C The profile module 600 described in more detail; the report option 520 for accessing reference 9A to 9C More detailed description of the report module 900; Scouting plan option 530 for accessing reference Fig. 7A and Figure 7B The reconnaissance module 700 described in more detail; the diagnosis / assessment option 540 for accessing reference FIG. 8A to FIG. 8C The evaluation module 800 described in more detail; the analysis option 550 is used to access the reference Fig.10 The analysis module 1000 described in more detail; the guide option 560 for accessing guides and recommendations, which may include recommendations through example recommendation services (such as Figure 2 and query option 570 for accessing references Fig.11 The query module 1100 is described in more detail. In addition to the options described above, the menu / navigation bar 580 may include reporting, reconnaissance, analysis, evaluation, and query selection options 582, 584, 586, 588, 589 for accessing the corresponding modules.

[0108] Fig. 6A and Figure 6B Depicted is an illustration of an exemplary GUI for defining a profile module 600 for an agricultural system according to one or more examples. Specifically, Fig. 6A A system profile GUI 610 is shown, which in one example includes a system properties and parameters table 614 ("system table 614") for defining a profile for an agricultural system that may have been entered via a user device 502 to access the system. Figure 5 500. On the other hand, Figure 6B A plant profile GUI 630 is shown that, in one example, includes a plant attribute and parameter table 634 ("plant table 634") for defining, in one example, a profile of a plant included in an agricultural system of the system profile GUI 610. The attributes and parameters included in the system and plant tables 614, 634 may depend on the system type (e.g., agroforestry, row planting, small, large, commercial), location, and other factors associated with the agricultural system corresponding to the system and profile GUI 610, 630.

[0109] Both the system table 614 and the plant table 634 may provide data entry options, including a free form option 616, a non-binary drop-down option 617, a binary drop-down option 619, and a formatted input option 618, which an operator or worker may select to enter information about an agricultural system. In some examples, the non-binary drop-down option 617, when selected, may cause a list of selectable parameters or attribute values ​​to be displayed (e.g., 100 / 200 / 300 acres, plant / block / section ASU). On the other hand, the binary drop-down option 619, when selected, may cause a list of two selectable options to be displayed (e.g., yes / no, Y / N, 1 / 0).

[0110] In addition to the above tables, the system and plant profile GUIs 610, 630 may also include a note data entry field 624, a save option 626 for saving the entered information, a clear option 628 for clearing the entered information, and a more option 629 that may be selected to view additional properties and parameters. In addition, the system and plant profile GUIs 610, 630 may include a menu / navigation bar 580 that allows the user to navigate to other modules. In addition, the system and plant profile GUIs 610, 630 may include a profile summary option 605 for accessing Figure 6C A profile summary GUI 640 is shown.

[0111] Figure 6C An illustration of an exemplary profile summary GUI 640 profile module 600 for summarizing a profile of an agricultural system according to one or more examples is depicted. As shown, the profile summary GUI 640 may include a system identification portion 650, a statistical evaluation portion 660, a map evaluation portion 670, and a weather information portion 680. The information included in the system identification portion 650 may include name, location, and size information. In other examples, the system identification portion 650 may include operator identification and number information and worker number information. Figure 6C As shown, weather information section 680 may include current and forecasted weather conditions for the area including the agricultural system associated with the information provided in profile summary GUI 640 .

[0112] The statistical evaluation section 660 may include a date input field 662, a plant statistical summary 664, and a plant part statistical summary 668. As shown, the statistical summary may provide the percentage of plants and plant parts found to be infected. In one example, the map evaluation section 670 may include a map type menu 672 and a map 674. The map 674 may include a legend 678. In one example, the illustrated map 674 may include a heat map or a dot density map, and the legend 678 may inform the user which type of plant / ASU information is associated with the different gradients (colors or dot densities) presented on the map 674 to reflect, for example: areas within the agricultural system and the volume of plants or other ASU types within those areas that exhibit certain conditions, such as disease (e.g., CSSD); the presence of pests; different levels of vegetation; and other aspects of the agricultural system (e.g., other parameters or attributes that may be tracked).

[0113] The information included in all of the illustrated sections may correspond to a date or date range entered into the date input field 662. In the case of a range, the information provided in the illustrated sections may be provided in the form of averages. For example, the system identification section 650 may display the average number of workers working in the agricultural system over the date range specified in the date input field 662. In a similar manner, averages for a plurality of plants, a plurality of plant parts, point density over time, and daily historical precipitation percentages may be displayed when a date range is specified.

[0114] Fig. 7A and Figure 7B Depicted is an illustration of an exemplary GUI of a scouting module 700 for assisting operators and workers in monitoring an agricultural system according to one or more examples. Specifically, Fig. 7A A scouting inventory GUI 710 is shown, which in one example includes an ASU identification portion 711 and an ASU inventory map portion 720. A menu bar 580 may also be displayed along with a module identifier 790 indicating the module currently being displayed. The ASU inventory map portion 720 may include ASU illustrations 722 of plants or other types of ASUs included in the ASUs identified in the ASU identification portion 711. As shown, the plants or other types of ASUs 722 may be shown in clusters 724 and thereby reflect the relative volume of plants or other types of ASUs in an actual area of ​​the agricultural system corresponding to a location a within the map portion 720 in which the clusters 724 are shown.

[0115] In some examples, a cluster 724 or an individual ASU 722 may be selected or hovered over to obtain more information about the ASU, or to identify an ASU whose corresponding reconnaissance path the user may want to view by subsequently selecting a path option 726 included in the reconnaissance module 700. Thus, the reconnaissance module 700 may provide a reconnaissance path GUI 740, such as Figure 7B The scouting route GUI 740 may include a scouting route map portion 745 in which route information 750 for an ASU selected from the search catalog GUI 710 or identified in the ASU identification portion 711 is displayed. In another example, when the route option 726 is selected, an ASU or ASU cluster within the inventory map portion 720 may not be selected. In these cases, the scouting module 700 may display route information for the ASU list displayed in the scouting list GUI 710.

[0116] The path information 750 may include a boundary 752 of the ASU and an illustration of a reconnaissance path 754 within the boundary 752 of the ASU. The reconnaissance path 754 may include a segment 756 extending between nodes 758. In some examples, the node 758 may represent a plant or other type of ASU to be analyzed. In another example, the ASUs for analysis may be distributed along the segment 756 between the nodes 758. In this example, the node 758 may correspond to a location where the analysis information should be transmitted to another entity or component of the risk management platform in some manner. In other examples, depending on the area covered by the reconnaissance path 754, the node 758 may correspond to a stopping point. Selecting one of the nodes 758 in this example may result in displaying a deadline for the reconnaissance activity that includes the node 758 and / or a duration required to complete the reconnaissance activity.

[0117] In addition to the path option 726, both the reconnaissance list GUI 710 and the reconnaissance path GUI 740 may include various types of navigation and view options that may be selected. Specifically, a direction option 728, a current location option 730, and an alternate view option 732 may be provided. In some examples, an ASU 722 or an ASU cluster 724 may be selected, followed by the direction option 728. In some examples, this series of selections may cause the risk management agent implementing the reconnaissance module 700 to access the location information of the user device 502 and the selected ASU / cluster and generate directions therebetween, which may be displayed in the reconnaissance path GUI 740. In some examples, a satellite such as satellite 430 and / or a mapping system such as mapping system 470 may be accessed in order to generate the directions.

[0118] Functionality similar to the directions option 728 may be provided with the alternate view option 732. That is, in the event that no ASU is selected, selecting the alternate view option 732 may cause the risk management agent to access location information of the user device 502. A “street view” of the ASUs identified in the ASU identification portion 711 may then be provided from the perspective of the obtained location of the user device 502. In other examples, in the event that an ASU within the ASU inventory map portion 720 is selected prior to selecting the alternate view option 732, a view (e.g., a “street view”) of the selected ASU may be presented by the reconnaissance module 700.

[0119] Fig. 8AAn illustration of an exemplary assessment menu GUI 810 of the assessment module 800 for selecting an assessment type according to one or more examples is depicted. As shown, the assessment menu GUI 810 may include several selectable level options 812 corresponding to a portion of an agricultural system (such as a nursery or field), and types of activities that may be performed in the agricultural system (such as planting and harvesting). In one example, selecting the field option 812 may cause the assessment module 800 to display the Figure 8B A first ASU assessment GUI 820 is shown.

[0120] like Figure 8B As shown, the first ASU assessment GUI 820 may include a drawing (map) of the ASUs of the agricultural system 822. Specifically, the first ASU assessment GUI 820 shows at least three ASU levels, including a segment level 823 with segment ASUs, an area unit level 825 with area unit ASUs, and a plant level 829 with plant ASUs. Additional information may include ASU identifiers 826 and density indicators 828, which may convey the scale at which a condition (e.g., CSSD) of one level of ASU (e.g., plant level) occurs within a higher level of ASU (e.g., area unit level).

[0121] In other examples, the density indicator 828 may convey the size of a population of one ASU level (e.g., plant level) within a higher level ASU (e.g., block). In other examples, one or more ASU level indicators (such as the segment ASU 823, the area unit ASU 825, and the plant level ASU 829) included in the ASU assessment GUI 820 may be presented in a different manner to also represent the density indicator and / or corresponding ASU level of some aspect of the agricultural system 822. For example, in some examples, the density indicator 828 (i.e., plants piled together) may convey the size of a plant population (plant ASU 829) within a corresponding area unit (area unit ASU 825). In addition, each plant ASU 825 may present plants in a manner (e.g., color, shape, pattern within shape) that reflects a corresponding condition (e.g., plant type, disease state (general), disease type such as CSSD, yield, age, insect / pest presence, etc.).

[0122] In some examples, an ASU displayed on the first ASU assessment GUI 820 may be selected (ASU selection), and the assessment module 800 may generate a second ASU assessment GUI 850 regarding the selected ASU, such as Figure 8CIn one example, the second ASU assessment GUI 850 may indicate the selection of the Segment 1 Segment ASU 823 as shown in the legend 830 of the first ASU assessment GUI 820 .

[0123] exist Figure 8B and Figure 8C In the exemplary first ASU assessment GUI 820 and second ASU assessment GUI 850, each area unit ASU 825 (area unit shape) can represent one hectare (e.g., farm) of an agricultural system 822. In one example, Figure 8B The agricultural system 822 shown may represent a cocoa tree farm. Therefore, the area unit ASU 825 is a non-uniform shape because the agricultural system 822 is an agroforestry agricultural system. In one example, a Figure 8B The plant ASUs 829 at points in the graph may provide a map of the presence of Phytophthora (which causes black pods) and other types of fungi that may cause problems in cocoa trees. Additionally, density indicators 828 may indicate the presence of multiple types of fungi where the plant ASUs 829 are closely clustered.

[0124] In some examples, a risk management platform according to the present disclosure may provide a first ASU assessment GUI 820 and a second ASU assessment GUI 850 in a form including multiple versions for different dates or date ranges that overlap each other. In this example, the displayed ASU assessment GUI may represent a mapping of the agricultural system 822 over time, which also includes a mapping of the presence of fungi in the agricultural system 822 (and its ASUs 823, 825, 829) over time. Thus, the displayed ASU assessment GUI may highlight / identify a combination of factors (e.g., weather), which, once identified, may be used to predict what may occur at other times when the same or similar combination of factors persists.

[0125] For example, such a time-reflective ASU assessment GUI may provide information that the northern part of agricultural system 822 is rainy and warm in May each year. In addition, the ASU assessment GUI may reflect that during this period, the northern part of agricultural system 822: (1) exhibits an increase in the level of fungal types and / or an increase in the level of a particular type of fungus (e.g., Phytophthora); and (2) at this time of year, there are more black pods in trees in this area of ​​agricultural system 822 than at other times of the year. In addition to causing the assessment to be displayed in assessment module 800 on user device 502, the exemplary risk management platform may also employ, for example, Figure 2The risk management platform may then access (determine, estimate, calculate) a prediction that another region of agricultural system 822, which has similar characteristics to the north, may experience an increase in black pod levels in November when conditions (rainy and warm) are the same or similar to those in the north in May.

[0126] As discussed above, an exemplary risk management platform according to the present disclosure can link weather data, agricultural system layout data, and mapped ASU status information, and use a combination of these data to predict what a potential epidemic outbreak may look like during a certain time in the future. Based on this information, the system operator can, for example, make adjustments to the water system to reduce or increase the supply and / or increase the frequency of analyzing and evaluating plants. In some agricultural systems, monitoring procedures (e.g., performing reconnaissance activities) may require individuals to personally walk several hectares of land to observe plants using a computing device such as described herein. It is likely that it is not feasible to perform this type of monitoring every day or even every week. Therefore, various aspects of the present disclosure can be directed to a risk management platform that configures a monitoring plan based on the assessment generated thereby, and the risk management platform determines the critical period during the plant growth cycle when monitoring should be increased based on the assessment. In addition, an exemplary risk management platform according to the present disclosure can be configured to automatically update such monitoring plans based on weather forecasts, seasonality, and yield forecasts over time and the continued operation of agricultural systems such as cocoa farms.

[0127] Fig. 9A and Fig. 9B An illustration of an exemplary GUI of a report module 900 for selecting a type of agricultural system report is depicted according to one or more examples. Fig. 9A As shown, the report module 900 may include a plant focus setting GUI 910 accessible via a plant part selection option 912. The plant focus setting GUI 910 may include a plant part selection option 916 to specify the focus of the report to be generated. In addition, a filter selection option 914 may also be included in the plant focus setting GUI 910, and selection thereof may cause the report module 900 to display a filter setting GUI 920, as shown in FIG. Fig. 9B shown.

[0128] The filter settings GUI 920 may include a filter summary section 922 showing the filters that have been selected for the report to be generated. In addition, a search section 930 may allow a user to select a date or date range and identify an ASU, a group of ASUs, or a group of ASUs at a higher level to include in the report. The exemplary report 942 is shown in FIG. Fig. 9C940. As shown, report 942 is based on the search criteria section 930 (see Fig. 9B ) by one or more corresponding diseases, providing a comparison between types of diseases 946.

[0129] Fig. 9C The illustrated report 942 is one type of report that the risk management platform and agents described herein may generate.One of ordinary skill in the art will readily appreciate that reports having different parameters and focuses may be provided utilizing the systems and methods described herein.

[0130] Fig.10 An illustration of an exemplary analysis GUI 1010 of an analysis module 1000 for analyzing ASUs according to one or more examples is depicted. In some examples, selecting and requesting or actuating a type of analysis may be functionality provided by the analysis GUI 1010. As shown, the analysis GUI 1010 includes a navigation portion that may include instructions 1022 for using a device to analyze an ASU (e.g., one or more plants) according to the present disclosure. An activation option 1025 may be selected to initiate image capture of an object to be analyzed. In one example, the analysis GUI 1010 may include an object recognition portion 1030 for inputting a type of object to be included in an image to be captured or in a previously captured image.

[0131] Fig.11 A diagram of an exemplary query menu GUI 1110 for a query module 1100 according to an aspect of the present disclosure is depicted. As shown, the query menu GUI 1110 may include several selectable options 1120 that may provide tools that an operator may be able to use when operating and troubleshooting problems that arise in an agricultural system.

[0132] Figure 5 GUI 500 and accessible through the home page 510 of GUI 500 FIG. 6A to FIG. 11The modules represented in can jointly provide a risk management agent. Such a risk management agent can be effectively used as a virtual field assistant by a system operator or worker of an agricultural system, as provided, supported and maintained by a risk management platform according to the present disclosure. In addition, the exemplary risk management agent described herein can be customized by a corresponding risk management platform for individuals typically found in agricultural systems and the technologies available to these individuals in terms of communication, information availability and exchange / transmission capabilities, as well as equipment for operating agricultural systems (e.g., sowing, harvesting, pesticide spreading and other types of agricultural equipment). For example, various exemplary risk management agents according to the present disclosure can be customized for large-scale farms, smallholder farms and commercial agricultural systems located in different types of areas, including very difficult-to-reach rural areas (e.g., mountainous areas in Indonesia, rural areas in Colombia or Ecuador). In addition, customization of the exemplary risk management agent can include the type of profiles maintained, the attributes and parameters tracked, the type of assessment performed, and other aspects according to the present disclosure.

[0133] Thus, the methods and systems described herein may provide exemplary risk management platforms that are configured to account for the constraints of equatorial tree crops and other agricultural systems where access to technology is suboptimal, at least at the operator level. In some examples, a risk management platform according to the present disclosure may instantiate, maintain, and otherwise support risk management agents customized for an 18 degree belt around the equator. This belt may include places where there is often limited structural availability in agricultural system management and certain technologies (limited internet access or computer access), but may be the best place to monitor the public for the presence of diseases that may affect plant yields on a regional and global scale.

[0134] The program aspects of the disclosed technology can be considered as a "product" or "article of manufacture" generally in the form of executable code and / or associated data, which is carried or contained in a type of machine-readable medium. "Storage" type media include any or all tangible memories of computers, processors, etc., or their associated modules, such as various semiconductor memories, tape drives, disk drives, etc., which can provide non-transitory storage for software programming at any time. Sometimes all or part of the software may be transmitted over the Internet or various other telecommunications networks. For example, such communication can enable software to be loaded from one computer or processor to another computer or processor, such as from a management server or host computer of a mobile communication network to a computer platform of a server and / or from a server to a mobile device. Therefore, another type of medium that can carry software elements includes light waves, radio waves, and electromagnetic waves such as used on physical interfaces between local devices through wired and optical landline networks and through various air links. Physical elements that carry such waves, such as wired or wireless links, optical links, etc., can also be considered as media that carry software. As used herein, unless restricted to non-transitory, tangible "storage" media, terms such as computer or machine "readable media" refer to any medium that participates in providing instructions to a processor for execution.

[0135] A computer system (such as a system or device implementing the processes or operations in the above examples) may include one or more computing devices. One or more processors of the computer system may be included in a single computing device or distributed in multiple computing devices. The memory of the computer system may include a corresponding memory of each computing device in the multiple computing devices.

[0136] The computer may be configured as a device for executing the exemplary examples of the present disclosure. For example, the computer may be configured according to the exemplary examples of the present disclosure. In various examples, any system herein may be a computer, including, for example, a data communication interface for packet data communication. The computer may also include a central processing unit ("CPU") in the form of one or more processors for executing program instructions. The computer may include an internal communication bus and a storage unit (such as ROM, HDD, SDD, etc.), which may store data on a computer-readable medium, although the computer may receive programs and data via network communications. The computer may also have a memory (such as RAM) storing instructions for executing the technology presented herein, although these instructions may be temporarily or permanently stored in other modules of the computer (e.g., processor and / or computer-readable medium). The computer may also include input and output ports and / or displays to connect to input and output devices (such as keyboards, mice, touch screens, monitors, displays, etc.). Various system functions may be implemented in a distributed manner on multiple similar platforms to distribute the processing load. Alternatively, the system may be implemented by appropriate programming of a computer hardware platform.

[0137] Furthermore, while some examples described herein include some features included in other examples but not others, the combination of features from different examples is intended to be within the scope of the present invention and to form different examples, as will be understood by those skilled in the art.

[0138] Therefore, although certain examples have been described, those skilled in the art will recognize that other and further modifications may be made to the embodiment without departing from the spirit of the invention, and it is intended to claim all such changes and modifications that fall within the scope of the invention. For example, functionality may be added or deleted from the block diagrams, and operations may be interchanged in functional blocks.

[0139] The subject matter disclosed above should be considered illustrative rather than restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments that fall within the true spirit and scope of the present disclosure. Therefore, to the maximum extent permitted by law, the scope of the present disclosure will be determined by the broadest permissible interpretation of the appended claims and their equivalents, and shall not be restricted or limited by the foregoing detailed description. Although various embodiments of the present disclosure have been described, it is obvious to those of ordinary skill in the art that more embodiments may be within the scope of the present disclosure. Therefore, the present disclosure is not limited except in accordance with the appended claims and their equivalents.

Claims

1. A computer-implemented method for managing agricultural system risk, the method comprising: Receiving, by one or more processors, an agricultural system unit (ASU) selection for an ASU associated with an agroforestry agricultural system; accessing, by the one or more processors, an analysis for a plant corresponding to the ASU selection based on a selection type of the ASU selection; accessing, by the one or more processors, an assessment associated with the plant corresponding to the ASU selection based on the analysis and the selection type; determining, by the one or more processors, a need for risk mitigation techniques based on the analyzing and / or the evaluating; as well as causing, by the one or more processors, an indication in a graphical user interface (GUI) of a result of processing the ASU selection based on the selection type, The plants in the agroforestry system include cocoa trees.

2. A computer-implemented method as described in claim 1, further comprising configuring access to the results of the analysis and the evaluation according to a specified format by the one or more processors based on at least one of the location or reporting standards of the agroforestry system.

3. The computer-implemented method of claim 1, wherein accessing the assessment comprises determining a number of plants within the ASU that exhibit disease.

4. The computer-implemented method of claim 3, wherein the disease is cocoa swollen shoot disease.

5. The computer-implemented method of claim 1, wherein accessing the assessment comprises receiving an indication of a test result from a test suite. The computer-implemented method of claim 1 , wherein accessing the assessment comprises generating a heat map including a density indicator.

7. The computer-implemented method of claim 6, wherein the density indicator is configured to indicate a number of plants included in the ASU.

8. The computer-implemented method of claim 1 , wherein accessing the analysis comprises: capturing, by the one or more processors, an image of at least a portion of the ASU selected by the ASU; as well as An image analysis of the image is received by the one or more processors, the image analysis including a plurality of plant parts damaged within the portion of the ASU.

9. The computer-implemented method of claim 1 , wherein determining the need for the risk mitigation technology comprises: determining, by the one or more processors, that the risk mitigation technique includes a change to a schedule for analyzing at least one group of plants included in the agroforestry agricultural system; as well as A notification is sent, by the one or more processors, to at least one computing device, wherein the notification includes the schedule with the change.

10. The computer-implemented method of claim 1 , wherein determining the need for the risk mitigation technology comprises: accessing, by the one or more processors, from one or more servers, historical weather information for an area including the agroforestry agricultural system; Determining, by the one or more processors, that the risk mitigation technique includes changing a schedule for supplying water to at least a portion of the agroforestry system based on the historical weather information.

11. A computer-implemented method as described in claim 1, wherein the results of processing the ASU selection include predictions of the incidence of at least one disease for at least one group of plants in the agroforestry system over a defined future time period, the predictions having been made using a predictive model for the agroforestry system.

12. The computer-implemented method of claim 1, wherein causing the result of processing the ASU selection to be indicated in the GUI comprises causing the GUI to include a summary of the ASU, wherein the summary includes a number of diseased plants associated with the ASU on a single date or over a range of dates.

13. A computer system for managing agricultural system risk, the computer system comprising: at least one memory storing instructions; as well as at least one processor configured to execute the instructions to perform operations comprising: receiving an agricultural system unit (ASU) selection for an ASU associated with an agroforestry agricultural system; accessing an analysis for a plant corresponding to the ASU selection based on a selection type of the ASU selection; accessing an assessment associated with the plant corresponding to the ASU selection based on the analysis and the selection type; determining the need for risk mitigation technologies based on the assessment; and causing an indication in a graphical user interface of a result of processing the ASU selection based on the selection type, The plants in the agroforestry system include cocoa trees.

14. The computer system of claim 13, the operations further comprising configuring, by the at least one processor, access to the results of the analysis and the evaluation according to a specified format based on at least one of a location or reporting criteria of the agroforestry system.

15. The computer system of claim 13, wherein accessing the assessment comprises determining a number of plants within the ASU that exhibit disease.

16. The computer system of claim 15, wherein the disease is cocoa swollen shoot disease.

17. The computer system of claim 15, wherein accessing the assessment comprises generating a heat map including a density indicator.

18. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations for managing agricultural system risk, the operations comprising: receiving an agricultural system unit (ASU) selection for an ASU associated with an agroforestry agricultural system; accessing an analysis for a plant corresponding to the ASU selection based on a selection type of the ASU selection; accessing an assessment associated with the plant corresponding to the ASU selection based on the analysis and the selection type; determining the need for risk mitigation technologies based on said assessment; as well as causing an indication in a graphical user interface of a result of processing the ASU selection based on the selection type, The plants in the agroforestry system include cocoa trees.

19. The non-transitory computer readable medium of claim 18, wherein accessing the assessment comprises determining a number of plants within the ASU that exhibit cocoa swollen shoot disease.

20. The non-transitory computer-readable medium of claim 18, wherein accessing the assessment comprises generating a heat map comprising a density indicator.

Images