A system and method for predicting pest pressure using geospatial features and machine learning.

Abstract

This invention provides a system and method for rapidly and accurately predicting future pest pressures that will affect crop productivity. [Solution] A method for generating pest pressure data includes receiving collection data from multiple pest traps within a geographic location, receiving meteorological data for the geographic location, receiving image data for the geographic location, identifying at least one geospatial feature within or near the geographic location, applying a machine learning algorithm to the collection data, meteorological data, image data and at least one identified geospatial feature to identify a correlation between pest pressure and at least one geospatial feature, and generating a predicted future pest pressure for the geographic location based on the identified correlation between pest pressure and at least one geospatial feature.

Description

Technical Field

[0001] Cross - Reference to Related Applications This application claims priority to U.S. Provisional Patent Application No. 62 / 984,885, filed Mar. 4, 2020; U.S. Provisional Patent Application No. 62 / 984,881, filed Mar. 4, 2020; U.S. Patent Application No. 17 / 081,263, filed Oct. 27, 2020; and U.S. Patent Application No. 17 / 081,361, filed Oct. 27, 2020. These applications are hereby incorporated by reference in their entirety.

[0002] This application generally relates to techniques that can be used to assist in predicting pest pressure, and more particularly, to network - based systems and methods for predicting pest pressure using geospatial features and machine learning.

Background Art

[0003] Due to the increase in the world's population and the decrease in the amount of arable land, methods and systems for increasing the productivity of agricultural crops are desired. At least one factor that affects the productivity of agricultural crops is pest pressure.

[0004] As a result, systems and methods for monitoring and analyzing pest pressure have been developed. For example, in at least some known systems, multiple insect traps are placed within an agricultural field of interest. To monitor the pest pressure within the agricultural field of interest, the traps are inspected periodically to count the number of pests within each trap. Based on the number of pests in each trap, a pest pressure level for the agricultural field of interest can be determined.

[0005] The number of pests monitored in each collector can also be used to predict future pest pressure. However, pest pressure is a relatively complex phenomenon governed by several factors. Therefore, accurately predicting future pest pressure based primarily on the number of specimens collected can be relatively inaccurate. Furthermore, at least some known systems for monitoring pest pressure are focused at the individual farm level, resulting in limited visualization and significant time lags in data collection. In addition, at least some known systems for predicting future pest pressure rely on static logic (e.g., fixed phenology models and / or decision trees), and therefore their ability to accurately predict future pest pressure is limited. Patent Document 1 describes a data receiving module that receives sampled agriculture-related data associated with a given geographical area. Patent Document 2 describes a method and system for displaying predictions on a spatial map, which includes using a data analyzer for analyzing heterogeneous data with spatial components to identify available data and using machine learning to automatically extract relationships from the available data. Patent Document 3 describes a method for performing pest forecasting. Patent Document 4 describes exemplary embodiments of an integrated pest management (IPM) system and an electronic insect monitoring device (EIMD). Patent Document 5 describes an integrated method and system for preventing and resolving any type of pest problem on a site, in a building, in a process, in a facility, or in an area. Patent Document 6 describes a computer system for managing the sale of agricultural products involving salespeople and a first grower.

[0006] Therefore, it would be desirable to provide a system that intelligently analyzes multiple different types of information to rapidly and accurately predict future pest pressure. Furthermore, it would be desirable to present the predicted future pest pressure and assist users in performing technical tasks to monitor pest pressure and, optionally, control pest collection and / or pest treatment systems. [Prior art documents] [Patent Documents]

[0007] [Patent Document 1] U.S. Patent Application Publication No. 2017 / 041407A1 [Patent Document 2] U.S. Patent Application Publication No. 2008 / 312942A1 [Patent Document 3] European Patent Application Publication No. 3482630A1 [Patent Document 4] International Publication No. 2012 / 054397A1 Pamphlet [Patent Document 5] International Publication No. 2004 / 110142A1 Pamphlet [Patent Document 6] U.S. Patent Application Publication No. 2015 / 025926A1 [Overview of the Initiative] [Means for solving the problem]

[0008] In one embodiment, a pest pressure prediction computing device is provided. The pest pressure prediction computing device includes memory and a processor communicatively coupled to the memory. The processor is programmed to receive collection data for a plurality of pest traps in a geographic location, wherein the collection data includes at least current and historical pest pressures in each of the plurality of pest traps; receive meteorological data for the geographic location, wherein the meteorological data includes at least current and historical meteorological conditions for the geographic location; receive image data for the geographic location; identify at least one geospatial feature in or near the geographic location; apply a machine learning algorithm to the collection data, meteorological data, image data and at least one identified geospatial feature to identify a correlation between pest pressure and at least one geospatial feature; and at least generate a predicted future pest pressure for the geographic location based on the identified correlation between pest pressure and at least one geospatial feature.

[0009] In another embodiment, a method is provided for generating pest pressure predication data. The method is carried out using a pest pressure prediction computing device which includes memory communicably coupled to a processor. The method includes receiving collection data for a plurality of pest traps in a geographic location, wherein the collection data includes at least current and historical pest pressures at each of the plurality of pest traps; receiving meteorological data for the geographic location, wherein the meteorological data includes at least current and historical meteorological conditions for the geographic location; receiving image data for the geographic location; identifying at least one geospatial feature in or near the geographic location; applying a machine learning algorithm to the collection data, meteorological data, image data and at least one identified geospatial feature to identify a correlation between pest pressure and at least one geospatial feature; and at least generating a predicted future pest pressure for the geographic location based on the identified correlation between pest pressure and at least one geospatial feature.

[0010] In yet another embodiment, a computer-readable storage medium is provided into which computer-executable instructions are incorporated. When executed by a pest pressure prediction computing device including at least one processor communicating with memory, the computer-readable instructions are to cause the pest pressure prediction computing device to receive collection data for a plurality of pest traps in a geographic location, the collection data for each of the plurality of pest traps The techniques of the Disclosure include receiving data including at least current and historical pest pressure, receiving meteorological data for a geographic location, wherein the meteorological data includes at least current and historical meteorological conditions for the geographic location, receiving image data for the geographic location, identifying at least one geospatial feature within or near the geographic location, applying a machine learning algorithm to the collection data, meteorological data, image data, and at least one identified geospatial feature to identify a correlation between pest pressure and at least one geospatial feature, and generating a predicted future pest pressure for the geographic location based on the identified correlation between pest pressure and at least one geospatial feature. It can be understood that the techniques of the Disclosure provide predicted future pest pressure and assist a user in performing technical work to monitor pest pressure and optionally control a pest collection system and / or pest treatment system. It can be understood that the techniques of the Disclosure enable, for example, the provision of a dynamic internal state of a pest pressure monitoring system at a future point in time.

[0011] Figures 1 to 10 illustrate exemplary embodiments of the methods and systems described herein. [Brief explanation of the drawing]

[0012] [Figure 1] Figure 1 is a block diagram of a computer system used to predict pest pressure according to one embodiment of the present disclosure. [Figure 2] Figure 2 is a block diagram showing the data flow within the system shown in Figure 1. [Figure 3] Figure 3 shows an exemplary configuration of a server system, such as the pest pressure prediction computing device shown in Figures 1 and 2. [Figure 4] Figure 4 shows an exemplary configuration of the client system shown in Figures 1 and 2. [Figure 5]FIG. 5 is a flowchart of an exemplary method for generating pest pressure data using the system shown in FIG. 1. [Figure 6] FIG. 6 is a flowchart of an exemplary method for generating a heat map using the system shown in FIG. 1. [Figure 7] FIG. 7 is an exemplary screenshot of a user interface that can be generated using the system shown in FIG. 1. [Figure 8] FIG. 8 is an exemplary screenshot of a user interface that can be generated using the system shown in FIG. 1. [Figure 9] FIG. 9 is an exemplary screenshot of a user interface that can be generated using the system shown in FIG. 1. [Figure 10] FIG. 10 is an exemplary screenshot of a user interface that can be generated using the system shown in FIG. 1. [Figure 11] FIG. 11 is an exemplary screenshot of a user interface that can be generated using the system shown in FIG. 1. [Figure 12] FIG. 12 is an exemplary screenshot of a user interface that can be generated using the system shown in FIG. 1.

DETAILED DESCRIPTION OF THE INVENTION

[0013] The specific features of the various embodiments may be shown in some of the drawings and not in others, but this is merely for convenience. Any feature in any drawing may be referred to and / or claimed in combination with any feature in any other drawing.

[0014] The systems and methods described herein relate to a computer-implemented system for predicting future pest pressure using machine learning. Pest pressure prediction computing The wing device includes a memory and a processor communicatively coupled to the memory. The processor is programmed to receive collection data for a plurality of pest traps within a geographical location, the collection data including at least current and historical pest pressure at each of the plurality of pest traps. The processor is further programmed to receive weather data for the geographical location, the weather data including at least current and historical weather conditions for the geographical location, and to receive image data for the geographical location. Further, the processor is programmed to identify at least one geospatial feature within or proximal to the geographical location, and to apply a machine learning algorithm to the collection data, weather data, image data, and at least one identified geospatial feature to identify a correlation between the pest pressure and the at least one geospatial feature. Based on the at least one identified correlation, the processor is programmed to generate a predicted future pest pressure for the geographical location.

[0015] The systems and methods described herein facilitate the accurate prediction of pest pressure in one or more geographic locations. As used herein, “geographic location” generally refers to an agricultural geographic location (e.g., a location including one or more farmlands and / or agricultural fields for crop production). Furthermore, as used herein, “pest pressure” refers to a qualitative and / or quantitative assessment of the abundance of pests present in a particular location. For example, high pest pressure indicates the presence of a relatively large abundance of pests in that location (e.g., compared to expected abundance). Conversely, low pest pressure indicates the presence of a relatively low abundance of pests in that location. In at least some of the embodiments described herein, pest pressure is analyzed for agricultural purposes; that is, pest pressure is monitored and predicted for one or more farmlands. However, those skilled in the art will understand that the systems and methods described herein can be used to analyze pest pressure in any suitable environment.

[0016] As used herein, the term “pest” refers to organisms whose presence is generally undesirable in a particular geographical location, especially in an agricultural geographical location. For example, in an implementation for analyzing pest pressure for one or more farmlands, pests may include insects that tend to damage crops in those farmlands. However, those skilled in the art will understand that the systems and methods described herein may be used to analyze pest pressure for other types of pests. For example, in some embodiments, pest pressure may be analyzed for fungi, weeds, and / or diseases. The systems and methods described herein refer to “pest trap” and “trap data.” As used herein, “pest trap” may refer to any device capable of trapping and / or monitoring the presence of pests of interest, and “trap data” may refer to data collected using such a device. For example, for insects, “pest trap” may be a conventional trapping device for securing pests. Alternatively, for fungi, weeds, or diseases, “pest trap” may refer to any device capable of monitoring the presence and / or levels of fungi, weeds, and / or diseases. For example, in embodiments where “pest” is one or more species of fungi, “pest trap” may refer to a sensing device capable of quantitatively measuring the level of spores associated with one or more species of fungi in the surrounding environment around the sensing device. In one embodiment, where “pest” is one or more species of insects, the terms “pest trap” and “pest trap group” refer to “insect trap” and “insect trap group,” respectively.

[0017] A further detailed description of embodiments of this disclosure refers to the attached drawings. The same reference in different drawings The identification symbols may identify the same or similar elements. Furthermore, the following detailed description does not limit the claims.

[0018] This specification describes computer systems such as pest pressure prediction computing devices. As described herein, all such computer systems include a processor and memory. However, any processor in a computer device referred to herein may also refer to one or more processors, where the processor may reside in one computing device or in multiple computing devices operating in parallel. In addition, any memory in a computer device referred to herein may also refer to one or more memory, where the memory may reside in one computing device or in multiple computing devices operating in parallel.

[0019] As used herein, a processor may include any programmable system that uses a microcontroller, a reduced instruction set circuit (RISC), an application-specific integrated circuit (ASIC), a logic circuit, and any other circuit or processor capable of performing the functions described herein. The examples above are merely illustrative and are therefore not intended to limit the definition and / or meaning of the term “processor.”

[0020] As used herein, the term “database” may refer to the body of data, a relational database management system (RDBMS), or both. As used herein, a database may include any set of data, including hierarchical databases, relational databases, flat-file databases, object-relational databases, object-oriented databases, and any other structured set of records or data stored in a computer system. The examples given above are merely illustrative and are therefore not intended to limit the definition and / or meaning of the terms, database, etc. Examples of RDBMS include, but are not limited to, Oracle® Database, MySQL, IBM® DB2, Microsoft® SQL Server, Sybase®, and PostgreSQL. However, any database that enables the systems and methods described herein may be used. (Oracle is Oracle Corporation, Redwood) Shores is a registered trademark of California, IBM is a registered trademark of International Business Machines Corporation, Armonk is a registered trademark of New York, and Microsoft is a registered trademark of Microsoft (Corporation, Redmond, and Washington are registered trademarks, and Sybase is a registered trademark of Sybase, Dublin, and California.)

[0021] In one embodiment, a computer program is provided, and the program is embedded on a computer-readable medium. In an exemplary embodiment, the system runs on a single computer system without requiring a connection to a server computer. In a further embodiment, the system runs within a Windows® environment (Windows is a registered trademark of Microsoft Corporation, Redmond, and Washington). In yet another embodiment, the system runs on a mainframe environment and a UNIX® server environment (UNIX is a trademark of X / Open Company, located in Reading, Berkshire, United Kingdom). (Registered trademark of Limited). The application is flexible and has key functionality. It is designed to run in a variety of different environments without any loss of performance. Depending on the embodiment, the system includes multiple components distributed among multiple computing devices. One or more components may be in the form of computer-executable instructions embedded in a computer-readable medium.

[0022] When used herein, an element or step described in the singular form and following the word “a” or “an” should be understood not to exclude multiple elements or steps unless multiple exclusions are stated. Furthermore, any reference in this disclosure to “exemplary embodiments” or “one embodiment” is not intended to be construed as excluding the existence of additional embodiments that similarly incorporate the described features.

[0023] As used herein, the terms “software” and “firmware” are interchangeable and include any computer program stored in memory for execution by a processor, including RAM memory, ROM memory, EPROM memory, EEPROM memory, and non-volatile RAM (NVRAM) memory. The types of memory described above are merely examples and are therefore not a limitation on the types of memory that can be used to store computer programs.

[0024] The systems and processes are not limited to the specific embodiments described herein. In addition, each system and process component may be implemented independently and separately from other components and processes described herein. Each component and process may also be used in combination with other assembly packages and processes.

[0025] The following detailed description illustrates embodiments of this disclosure and is not intended to limit them. This disclosure is intended to have general applications to predicting pest pressure.

[0026] Figure 1 shows a pest pressure prediction (PPP(pest)) according to one exemplary embodiment of the present disclosure. This is a block diagram of an exemplary embodiment of a computer system 100 used to predict pest pressure, including a computing device 112. The PPP computing device 112 may also be referred to herein as a heatmap generation computing device, as described herein. In the exemplary embodiment, the system 100 is used to predict pest pressure and generate a pest pressure heatmap, as described herein.

[0027] More specifically, in exemplary embodiments, System 100 includes a Pest Pressure Prediction (PPP) computing device 112 and a number of client subsystems, also referred to as client systems 114, connected to the PPP computing device 112. In one embodiment, the client system 114 is a computer including a web browser, thereby enabling the PPP computing device 112 to access the client system 114 via the Internet and / or Network 115. The client system 114 is interconnected to the Internet through many interfaces, including Network 115, such as a local area network (LAN) or wide area network (WAN), dial-in connection, cable modem, Integrated Services Digital Network (ISDN) line, and RDT network. The client system 114 may include systems associated with farm managers, growers, scouts, etc., as well as external systems used to store data. The PPP computing device 112 also communicates with one or more data sources 130 using Network 115. Furthermore, the client system 114 may also, additionally, Communication with the data source 130 can be made using 115. Furthermore, depending on the embodiment, one or more client systems 114 may act as the data source 130, as described herein. The client system 114 may be any device capable of interconnecting to the Internet, including a web-based telephone, PDA, or other web-based connectable device.

[0028] As will be described in more detail below, the database server 116 is connected to a database 120 that contains information on various matters. In one embodiment, the centralized database 120 is stored on a PPP device 112 and can be accessed by a potential user in one of the client systems 114 by logging on to the PPP computing device 112 through one of the client systems 114. In an alternative embodiment, the database 120 may be stored remotely from the PPP device 112 and be decentralized. The database 120 may be a database configured to store information used by the PPP computing device 112, including, for example, transaction records, as described herein.

[0029] Database 120 may include a single database having separate sections or partitions, or it may include multiple databases, each distinct from the others. Database 120 may store data received from data source 130 and data generated by PPP computing device 112. For example, database 120 may store meteorological data, imaging data, collection data, reconnaissance data, grower data, pest pressure prediction data, and / or heatmap data, as described in detail herein.

[0030] In exemplary embodiments, the client system 114 may be associated with, for example, a cultivator, a reconnaissance entity, a pest management entity, and / or any other party capable of using the system 100 as described herein. In exemplary embodiments, at least one of the client systems 114 includes a user interface 118. For example, the user interface 118 may include a graphical user interface with interactive functionality, thereby displaying pest pressure forecasts and / or heatmaps transmitted from the PPP computing device 112 to the client system 114 in a graphical format. A user of the client system 114 may interact with the user interface 118, view, explore, and otherwise interact with the displayed information.

[0031] In an exemplary embodiment, the PPP computing device 112 receives data from multiple data sources 130, aggregates the received data, analyzes it (e.g., using machine learning), and generates pest pressure predictions and / or heatmaps, as described in detail herein.

[0032] Figure 2 is a block diagram showing the data flow within system 100. In the embodiment shown in Figure 2, data source 130 includes a meteorological data source 202, an imaging data source 204, a collection data source 206, a reconnaissance data source, a grower data source 210, and another data source 212. Those skilled in the art will understand that data source 130 shown in Figure 2 is merely an example, and system 100 may include any suitable number and types of data sources.

[0033] The weather data source 202 provides weather data to the PPP computing device 112 for use in generating pest pressure forecasts. The weather data includes, for example, temperature data (e.g., indicating current and / or past temperatures measured at one or more geographic locations), humidity data (e.g., measured at one or more geographic locations) This may include current and / or past humidity data, wind data (e.g., current and / or past wind levels and directions measured at one or more geographic locations), precipitation data (e.g., current and / or past rainfall levels measured at one or more geographic locations), and forecast data (e.g., predicted future weather conditions for one or more geographic locations).

[0034] The imaging data source 204 provides image data to the PPP computing device 112 for use in generating pest pressure predictions. The image data may include, for example, acquired satellite and / or drone images of one or more geographic locations.

[0035] The collection data source 206 provides collection data to the PPP computing device 112 for use in generating pest pressure predictions. The collection data may include, for example, the number of pests from at least one pest collector within a geographical location (e.g., expressed as the number of pest species, the density of pest species, or similar). Furthermore, the collection data may include, for example, in the case of insects, the type of pest (e.g., taxonomic genus, species, variety, etc.), and / or the developmental stage and sex of the pest (e.g., larva, juvenile, adult, male, female, etc.). The pest collector may be, for example, an insect trap. Alternatively, the pest collector may be any device capable of determining the presence of pests and providing collection data to the PPP computing device 112, as described herein. For example, in some embodiments, the pest collector may be a sensing device capable of sensing the environmental level of spores associated with one or more species of fungi. In such embodiments, the collected data may include, for example, the number of spores (representing the number of harmful organisms), the type of fungus, and the developmental stage of the fungus.

[0036] In some embodiments, the collection data source 206 is a pest collector that is communicably coupled to the PPP computing device 112 (for example, via a wireless communication link). In such embodiments, the collection data source 206 may have the ability to automatically determine the number of pests in the pest collector (for example, using an image processing algorithm) and transmit the determined number of pests to the PPP computing device.

[0037] The reconnaissance data source 208 provides reconnaissance data to the PPP computing device 112 for use in generating pest pressure predictions. The reconnaissance data may include any data provided by human reconnaissance personnel monitoring one or more geographic locations. For example, the reconnaissance data may include crop conditions, pest counts (e.g., manually counted by human reconnaissance personnel in pest traps), etc. In some embodiments, the reconnaissance data source 208 is one of the client systems 114. That is, the reconnaissance personnel can use the same computing device (e.g., a mobile computing device) to provide reconnaissance data to the PPP computing device 112 and to view pest pressure prediction data and / or heatmap data.

[0038] The grower data source 210 provides grower data to the PPP computing device 112 for use in generating pest pressure predictions. The grower data may include, for example, farmland boundary data, crop condition data, etc. Furthermore, similar to the reconnaissance data source 208, in some embodiments, the grower data source 210 is one of the client systems 115. That is, the grower can use the same computing device (e.g., a mobile computing device) to provide reconnaissance data to the PPP computing device 112 and view pest pressure prediction data and / or heatmap data.

[0039] Other data sources 212 are other types that are not available from data sources 202-210. The data may be provided to the PPP computing device 112. For example, depending on the embodiment, the other data source 212 may include a mapping database that provides mapping data (e.g., topographic maps of one or more geographic locations) to the PPP computing device 112.

[0040] In an exemplary embodiment, the PPP computing device 112 receives data from at least one of the data sources 202-212, aggregates and analyzes the data (e.g., using machine learning) as described herein, and generates pest pressure prediction data. Furthermore, the PPP computing device 112 may also aggregate and analyze the data and generate heatmap data, as described herein. The pest pressure prediction data and / or heatmap data may be transmitted to the client system 114 (e.g., for display to a user of the client system 114).

[0041] In some embodiments, data from at least one of the data sources 202-210 is automatically pushed to the PPP computing device 112 (for example, without the PPP computing device 112 polling or querying the data sources 202-210). Furthermore, in some embodiments, the PPP computing device 112 polls or queries at least one of the data sources 202-210 (for example, periodically or continuously) to retrieve relevant data.

[0042] Figure 3 shows an exemplary configuration of a server system 301, such as the PPP computing device 112 (shown in Figures 1 and 2), according to one exemplary embodiment of the present disclosure. The server system 301 may also include, but is not limited to, a database server 116. In the exemplary embodiment, the server system 301 generates pest pressure prediction data and heatmap data, as described herein.

[0043] The server system 301 includes a processor 305 for executing instructions. Instructions may be stored, for example, in a memory area 310. The processor 305 may include one or more processing units (for example, in a multi-core configuration) for executing instructions. Instructions may be executed within various different operating systems on the server system 301, such as UNIX, LINUX, Microsoft Windows®, etc. It should also be understood that various instructions may be executed during initialization at the start of the computer-based method. Some operations may be required to perform one or more processes described herein, while other operations may be more general and / or specific to a particular programming language (e.g., C, C#, C++, Java, or other preferred programming languages, etc.).

[0044] The processor 305 is operably coupled to the communication interface 315, thereby enabling the server system 301 to communicate with user systems or remote devices such as another server system 301. For example, the communication interface 315 may receive requests from a client system 114 over the internet, as shown in Figure 2.

[0045] The processor 305 may also be operably coupled to a storage device 134. The storage device 134 is any computer operating hardware suitable for storing and / or retrieving data. In some embodiments, the storage device 134 is integrated within a server system 301. For example, the server system 301 may include one or more hard disk drives as the storage device 134. In other embodiments, the storage device 134 is a server It is located outside of server system 301 and can be accessed by multiple server systems 301. For example, storage device 134 may include multiple storage units such as hard disks or solid-state disks in a redundant array of inexpensive disks (RAID) configuration. Storage device 134 may include a storage area network (SAN) and / or network-attached storage (NAS) system.

[0046] In some embodiments, the processor 305 is operably coupled to the storage device 134 via a storage interface 320. The storage interface 320 is any component capable of providing the processor 305 with access to the storage device 134. The storage interface 320 may include, for example, an Advanced Technology Attachment (ATA) adapter, a Serial ATA (SATA) adapter, a Small Computer System Interface (SCSI) adapter, a RAID controller, a SAN adapter, a network adapter, and / or any component that provides the processor 305 with access to the storage device 134.

[0047] Memory area 310 may include, but is not limited to, random access memory (RAM), such as dynamic RAM (DRAM) or static RAM (SRAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and non-volatile RAM (NVRAM). The above-mentioned types of memory are merely examples and are therefore not a limitation on the types of memory that can be used for storing computer programs.

[0048] Figure 4 shows an exemplary configuration of a client computing device 402. The client computing device 402 may include, but is not limited to, a client system ("client computing device") 114. The client computing device 402 includes a processor 404 for executing instructions. Depending on the embodiment, executable instructions are stored in a memory area 406. The processor 404 may include one or more processing units (e.g., in a multi-core configuration). The memory area 406 is any device that allows information, such as executable instructions and / or other data, to be stored and retrieved. The memory area 406 may include one or more computer-readable media.

[0049] The client computing device 402 also includes at least one media output component 408 for presenting information to the user 400. The media output component 408 is any component capable of conveying information to the user 400. Depending on the embodiment, the media output component 408 includes an output adapter such as a video adapter and / or an audio adapter. The output adapter is operably coupled to the processor 404 and a display device (e.g., a liquid crystal display (LCD)). (display), organic light-emitting diode (OLED) display, cathode ray tube (CRT), or "electronic ink" display), or audio output device ( For example, it can be operationally coupled to an output device such as a speaker or headphones.

[0050] Depending on the embodiment, the client computing device 402 includes an input device 410 for receiving input from the user 400. The input device 410 may include, for example, a keyboard, a pointing device, a mouse, a stylus, a touch-sensitive panel (e.g., a touchpad or touchscreen), a camera, a gyroscope, an accelerometer, a position detector, and / or an audio input device. A single component, such as a touchscreen, may function as both an output device for the media output component 408 and an input device 410.

[0051] The client computing device 402 may also include a communication interface 412 that can be communicatively coupled to a server system 301 or a remote device such as a web server. The communication interface 412 may be connected to, for example, a mobile phone network (e.g., a Global System for Mobile Communications (GSM)). This may include wired or wireless network adapters or wireless data transceivers for use with mobile communications (3G, 4G, 5G, or Bluetooth) or other mobile data networks (for example, Worldwide Interoperability for Microwave Access (WiMAX)).

[0052] Storing within the memory area 406 are, for example, computer-readable instructions for providing a user interface to user 400 via media output component 408, and optionally for receiving and processing input from input device 410. The user interface may include, among other possibilities, a web browser and a client application. The web browser allows user 400 to view and interact with media and other information embedded on web pages or websites, typically from a web server. The client application allows user 400 to interact with a server application. The user interface facilitates the display of pest pressure information provided by the PPP computing device 112 via either or both the web browser and the client application. The client application may have the ability to operate in both online mode (where the client application communicates with the PPP computing device 112) and offline mode (where the client application does not communicate with the PPP computing device 112).

[0053] Figure 5 is a flowchart of an exemplary method 500 for generating pest pressure data. Method 500 can be implemented, for example, using a PPP computing device 112.

[0054] Method 500 includes receiving (502) collection data for a plurality of pest collectors within a geographical location. In exemplary embodiments, the collection data includes both current and historical pest pressures at each of the plurality of collectors. The collection data may be received from, for example, a collection data source 206 (shown in Figure 2) (502). Furthermore, the PPP computing device 112 may analyze the received (502) collection data and generate additional data. For example, from the received (502) collection data, the PPP computing device 112 may determine the number of collectors at each level for a plurality of different pest pressure levels (defined, for example, by preferred upper and lower thresholds). Furthermore, the PPP computing device 112 may determine the average pest pressure across the plurality of collectors and / or across at least a portion of the geographical location. This additional data This can be used to identify correlations and predict future pest pressures, as described herein.

[0055] Method 500 further includes receiving meteorological data 502 for a geographical location (504). In exemplary embodiments, the meteorological data includes both current and historical meteorological conditions for the geographical location. Furthermore, depending on the embodiment, the meteorological data may include predicted future meteorological conditions for the geographical location. The meteorological data may be received from, for example, a meteorological data source 202 (shown in Figure 2) (504).

[0056] In exemplary embodiments, method 500 further includes receiving image data for a geographic location (506). The image data may include, for example, satellite and / or drone image data. The image data may be received from, for example, an imaging data source 204 (shown in Figure 2) (506).

[0057] Furthermore, method 500 includes identifying at least one geospatial feature within or near a geospatial location (508).

[0058] As used herein, “geospatial feature” refers to a geographical feature or structure that may influence pest pressure. For example, geographical features may include bodies of water (e.g., rivers, streams, lakes, etc.), elevation features (e.g., mountains, hills, canyons, etc.), transportation routes (e.g., roads, railway lines, etc.), farm locations, or factories (e.g., cotton mills).

[0059] In one embodiment, at least geospatial features are identified from existing map data (508). For example, the PPP computing device 112 may retrieve previously generated maps (e.g., topographic maps, elevation maps, road maps, survey maps, etc.) from a map data source (such as another data source 212 (shown in Figure 2)) which define the boundaries of one or more geospatial features.

[0060] In another embodiment, the PPP computing device 112 identifies one or more geospatial features by analyzing the received (506) image data (508). For example, the PPP computing device 112 may apply raster processing to the image data to generate a digital elevation map, where each pixel (or other similar subdivision) of the digital elevation map is associated with an elevation value. The PPP computing device 112 then identifies one or more geospatial features from the digital elevation map based on the elevation values ​​(508). For example, elevation features and / or bodies of water may be identified using such a technique.

[0061] Method 500 further includes applying a machine learning algorithm to collection data, meteorological data, image data, and at least one identified geospatial feature (510) to identify a correlation between pest pressure and at least one geospatial feature. Applying a machine learning algorithm to collection data, meteorological data, image data, and at least one identified geospatial feature (510) can be considered as applying a machine learning-based scheme to collection data, meteorological data, image data, and at least one identified geospatial feature (510) to identify a correlation between pest pressure and at least one geospatial feature. In one or more exemplary embodiments, applying a machine learning algorithm to collection data, meteorological data, image data, and at least one identified geospatial feature (510) may include determining a pest pressure value associated with a pest collector based on a relationship (e.g., correlation) between pest pressure and at least one geospatial feature.

[0062] In some embodiments, the PPP computing device 112 applies a machine learning algorithm (510) to (for example, at the location of a pest trap) It can be determined that pest pressure varies based on distance from at least one identified geospatial feature. For example, the PPP computing device 112 may determine that pest pressure is higher near a body of water (e.g., due to increased levels of pests in the body of water). In another example, the PPP computing device 112 may determine that pest pressure is higher near a transport route (e.g., due to increased levels of pests resulting from materials transported along the transport route). In yet another example, the PPP computing device 112 may determine that pest pressure is higher near a factory (e.g., due to increased levels of pests resulting from materials processed in the factory). In yet another example, the PPP computing device 112 may determine that pest pressure is reduced near at least one identified geospatial feature.

[0063] Those skilled in the art will understand that applying a machine learning algorithm (510) can identify other correlations between pest pressures at at least one geospatial feature. Specifically, a machine learning algorithm can consider a combination of collection data, meteorological data, image data, and at least one identified geospatial feature and have the ability to detect complex interactions between those different types of data that may be undetectable by a human analyst. For example, in some embodiments, non-distance-based correlations between at least one identified geospatial feature and pest pressures can be identified.

[0064] For example, in one or more exemplary embodiments, applying a machine learning algorithm to collection data, meteorological data, image data, and at least one identified geospatial feature (510) may include determining a pest pressure value associated with a pest trap based on a model (e.g., a machine learning model, a pest life cycle model) that characterizes the relationship (e.g., correlation) between pest pressure and collection data (optionally, the collection data includes insect data and / or insect developmental stage data). Furthermore, in one or more exemplary embodiments, applying a machine learning algorithm to collection data, meteorological data, image data, and at least one identified geospatial feature (510) may include determining a pest pressure value associated with a pest trap based on a model (e.g., a machine learning model) that characterizes the relationship (e.g., correlation) between pest pressure and collection data and meteorological data.

[0065] Furthermore, depending on the embodiment, the pest pressure for a first pest may be correlated with the pest pressure for a second different pest, and this correlation may be detected using the PPP computing device 112. For example, at least one geospatial feature is a particular field having a known high pest pressure for the second pest. Using the systems and methods described herein, the PPP computing device 112 may determine that proximal locations of a particular field have a high pest pressure for the first pest, which generally correlates with the pest pressure level of the second pest within that particular field. These “inter-pest” correlations may be complex relationships that are identifiable by the PPP computing device 112 but would be unidentifiable by a human analyst. Similarly, “inter-crop” correlations may be identifiable by the PPP computing device 112 between different crops, nearby geographical locations, etc.

[0066] Subsequently, method 500 includes generating predicted future pest pressure for a geographical location based on at least identified correlations (512). Specifically, the PPP computing device 112 uses the identified correlations in combination with one or more models, algorithms, etc., to predict future pest pressure values ​​for a geographical location. For example, the PPP computing device 112 combines a spray timer model, a pest lifecycle model, etc., with the identified correlations, collection data, meteorological data, and image data. Based on the identified patterns, predicted future pest pressures can be generated (512). Those skilled in the art will understand that other types of data may also be incorporated into the generated (512) predicted future pest pressures. For example, data on previously planted crops, adjacent farm data, farmland water level data, and / or soil type data may be considered when predicting future pest pressures. In one or more exemplary methods, Method 500 further includes outputting control signals to control one or more additional systems at a geographic location, such as a system for monitoring pest pressures at a geographic location, a system for controlling pest pressures at a geographic location, and / or a pest treatment system at a geographic location, based on the predicted future pest pressures.

[0067] As an example of a model, the developmental stage of a pest of interest (e.g., insects or fungi) may be governed by ambient temperature. Therefore, using a "degree-day" model, the developmental stage of the pest can be predicted based on heat accumulation (determined, for example, from temperature data).

[0068] The generated (512) predicted future pest pressure is an example of pest pressure prediction data that can be transmitted to and displayed on a user computing device, such as a client system 114 (shown in Figures 1 and 2). For example, the predicted future pest pressure can be transmitted to a user computing device, which can then present the predicted future pest pressure in text, graphical, and / or audio format, or any other preferred format. In some embodiments, as will be described in detail below, one or more heatmaps showing the predicted future pest pressure are displayed on the user computing device.

[0069] From the generated (512) predicted future pest pressure, the systems and methods described herein may also be used (e.g., using machine learning) to generate remedial recommendations for geographical locations to address the predicted future pest pressure. For example, using accurate predictions of future pest pressure at a site, the PPP computing device 112 may automatically generate remedial plans for geographical locations to mitigate future levels of high pest pressure. The remedial plan may specify, for example, one or more substances (e.g., insecticides, fertilizers, etc.) and specific times (e.g., daily, weekly, etc.) when those one or more substances should be applied. Alternatively, the remedial plan may include other data to facilitate improvements in agricultural performance in consideration of the predicted future pest pressure.

[0070] Furthermore, depending on the embodiment, the generated (512) predicted future pest pressure may be used to control additional systems (e.g., by a PPP computing device 112). In one embodiment, a system for monitoring pest pressure (e.g., a system including pest traps) may be controlled based on the predicted future pest pressure. For example, the PPP computing device 112 may be configured to output control signals for controlling one or more additional systems, such as a system for monitoring pest pressure, a system for controlling pest pressure, and / or a pest treatment system, based on future pest pressure. For example, a heatmap computing device may be configured to output control signals for controlling one or more additional systems, such as a system for monitoring pest pressure, a system for controlling pest pressure, and / or a pest treatment system, based on future pest pressure. For example, the frequency and / or type of collection data reported by one or more pest traps may be changed based on the predicted future pest pressure. In another example, a spraying device (e.g., for spraying insecticides) or other agricultural equipment may be controlled based on the predicted future pest pressure.

[0071] As mentioned above, the PPP computing device 112 also provides pest control pressure prediction. One or more heatmaps can be generated using the measured data. For the purposes of this description, the PPP computing device 112 may be referred to herein as the heatmap generation computing device 112.

[0072] Figure 6 is a flowchart of an exemplary method 600 for generating a heatmap. Method 600 can be carried out, for example, using a heatmap generation computing device 112 (shown in Figure 1).

[0073] Method 600 includes receiving collection data for a plurality of pest collectors within a geographical area (602). In exemplary embodiments, the collection data includes both current and historical pest pressures in each of the plurality of collectors. The collection data may be received from, for example, a collection data source 206 (shown in Figure 2) (602).

[0074] Furthermore, method 600 includes receiving meteorological data for a geographical location (604). In exemplary embodiments, the meteorological data includes both current and historical meteorological conditions for the geographical location. Furthermore, depending on the embodiment, the meteorological data may include predicted future meteorological conditions for the geographical location. The meteorological data may be received from, for example, a meteorological data source 202 (shown in Figure 2) (604).

[0075] In exemplary embodiments, method 600 further includes receiving image data for geographic locations (606). Image data may include, for example, satellite and / or drone image data. Image data may be received from, for example, an imaging data source 204 (shown in Figure 2) (606).

[0076] Method 600 further includes applying a machine learning algorithm to collection data, weather data, and image data (608) to generate predicted future pest pressure values ​​in each of a plurality of pest traps.

[0077] In addition, method 600 includes generating a first heatmap (610) and generating a second heatmap (612). In exemplary embodiments, the first heatmap is associated with a first time point, and the second heatmap is associated with a different second time point. The first and second heatmaps may be generated as follows (610, 612):

[0078] In exemplary embodiments, each heatmap is generated by plotting multiple nodes on a map of geographical locations. Each node corresponds to the location of a specific pest trap among multiple pest traps. Furthermore, in exemplary embodiments, each node is indicated by a color representing the pest pressure value for the corresponding test trap at a given time point. In one example, each node is indicated by green (indicating a low pest pressure value), yellow (indicating a moderate pest pressure value), or red (indicating a high pest pressure value). In Figures 7-9, green is indicated by a diagonal line pattern, yellow by a crosshatch pattern, and red by a dot pattern. Those skilled in the art will understand that a number of other colors and different colors may be used in embodiments described herein. Depending on the time point associated with the heatmap, the node color may indicate past pest pressure values ​​(when the time point is in the past, e.g., before the current date or a specific day before the date of the most recent reading of the collection data), current pest pressure values ​​(when the time point is the present, e.g., the current date or the date of the most recent reading of the collection data), or predicted future pest pressure values ​​(when the time point is in the future, e.g., after the current date or a specific day after the date of the most recent reading of the collection data). The predicted future pest pressure values ​​are as described herein. For example, they can be generated using machine learning algorithms.

[0079] To complete the heatmap, at least a portion of the remaining part of the map containing the colored nodes is colored. Specifically, the remaining part of the map is colored to generate a continuous map of pest pressure values. In an exemplary embodiment, the remaining part is colored by interpolating between pest pressure values ​​at multiple nodes.

[0080] In one embodiment, interpolation is performed using an inverse distance weighting (IDW) algorithm, where points on the rest of the map are colored based on their distance from known pest pressure values ​​at the nodes. For example, in such an embodiment, pest pressure values ​​for locations without nodes may be calculated based on a weighted average of inverse distances to nearby nodes. This embodiment operates under the assumption that pest pressure at a particular location will be more strongly influenced by nearby nodes (as opposed to more distant nodes). In other embodiments, interpolation may be performed based on other criteria in addition to, or instead of, distance from nodes.

[0081] Using the pest pressure values ​​generated for at least some of the remaining parts of the map (using interpolation as described above), those parts are colored based on the generated pest pressure values. Similar to the nodes, in one example, green indicates low pest pressure values, yellow indicates medium pest pressure values, and red indicates high pest pressure values. Thresholds for different colors may be set, for example, based on historical pest pressure and may be adjusted over time (automatically or based on user input). Those skilled in the art will understand that these three colors are merely examples and that any suitable coloring scheme may be used to generate the heatmap described herein.

[0082] In an exemplary embodiment, the first and second heatmaps are stored in a database, such as database 120 (shown in Figure 1). Therefore, in this embodiment, when a user views the heatmap on a user device (e.g., a mobile computing device), the heatmap has already been previously generated and stored by the heatmap generation computing device 112, as will be described later. Alternatively, the heatmap may be generated and displayed in real time based on the user's request.

[0083] Using the generated (610, 612) first and second heatmaps, in an exemplary embodiment, Method 600 further includes causing the time-lapse heatmap to be displayed on a user interface (614). The user interface may be, for example, a user interface displayed on a client device 114 (shown in Figures 1 and 2). The user interface may be implemented, for example, through an application installed on the client device 114 (e.g., an application provided by the entity operating the heat-generating computing device 112). In one or more exemplary methods, Method 600 further includes outputting control signals to control one or more additional systems, such as a system for monitoring pest pressure, a system for controlling pest pressure, and / or a pest treatment system, based on predicted future pest pressure.

[0084] The time-lapse heatmap displays an animation on the user interface. Specifically, in an exemplary embodiment, the time-lapse heatmap dynamically transitions between multiple previously generated heatmaps (e.g., the first and second heatmaps) over time, as described below. Therefore, by viewing the dynamic heatmap, the user can easily see and understand the changes in pest pressure over time for a geographical area. The time-lapse heatmap shows past, present, and / or future pest pressure for a geographical area. It can display force values.

[0085] In exemplary embodiments, a second heatmap for a second time point is generated using predicted pest pressure values, and it should be understood that this second time point refers to a point in time later than the time of the most recent current and historical pest pressure values ​​incorporated into the machine learning algorithm (e.g., included in the collection data). In other words, in such embodiments, the second time point refers to a future time point.

[0086] With respect to the first heatmap for the first time point, in an exemplary embodiment, it is generated using pest pressure values ​​for a time point earlier than the second time point. Therefore, the pest pressure values ​​used to generate the first heatmap are generally either current or historical pest pressure values. In another embodiment, the first time point is also a future time point, but it is a different time point from the second time point. Therefore, the pest pressure values ​​used to generate the first heatmap are similarly predicted pest pressure values.

[0087] Within the scope of this disclosure, references to the “first heatmap” and the “second heatmap,” as well as to the “first and second heatmaps,” made herein may imply that one or more (e.g., multiple) “intermediate heatmaps” are generated using pest pressure values ​​for various points in time between the first and second time points (e.g., current, historical, or predicted pest pressure values, as may be applicable). In such cases, the time-lapse heatmap displays the dynamic transition over time between the first heatmap, one or more intermediate heatmaps, and the second heatmap. In one embodiment, the intermediate heatmap includes one or more (e.g., multiple) intermediate heatmaps generated using predicted pest pressure values. In another embodiment, the intermediate heatmap includes one or more (e.g., multiple) intermediate heatmaps generated using current and / or historical pest pressure values. In yet another embodiment, the intermediate heatmap includes one or more (e.g., multiple) intermediate heatmaps generated using predicted pest pressure values, and one or more (e.g., multiple) intermediate heatmaps generated using current and / or historical pest pressure values.

[0088] In one embodiment, to display a time-lapse heatmap, each previously generated heatmap is displayed for a short period (e.g., in a slideshow format) before the next heatmap is instantaneously transitioned. Alternatively, depending on the embodiment, the heatmap generation computing device 112 temporally interpolates between consecutive heatmaps and generates transition data between those heatmaps (e.g., using machine learning). In such embodiments, the time-lapse heatmap displays the smooth progression of pest pressure over time instead of a series of still images.

[0089] Figure 7 is a first screenshot 700 of a user interface that may be displayed on a computing device, such as a client system 114 (shown in Figures 1 and 2). The computing device may be, for example, a mobile computing device.

[0090] The first screenshot 700 includes a pest pressure heatmap 702 that displays pest pressure associated with specific pests and crops within an area 704, including farmland 706. In the example shown in the first screenshot 700, the pest is the boll weevil and the crop is cotton. Those skilled in the art will understand that the heatmaps described herein can display pest pressure information for any suitable pests and crops. Furthermore, depending on the embodiment, the heatmap may display pest pressure information for multiple pests in the same crop, one pest in multiple crops, or multiple crops. It can display pest pressure for multiple species of pests in a given area.

[0091] As shown in Figure 7, the farmland 706 is defined on the heatmap 702 by the farmland boundary 708. The farmland boundary 708 can be plotted on the heatmap 702 by the heatmap generation computing device 112 based on information provided by the grower associated with the farmland 706, for example. For example, the grower may provide information to the heatmap generation computing device 112 from a grower computing device, such as a grower data source 210 (shown in Figure 2).

[0092] The heatmap 702 includes three nodes 710 corresponding to three pest traps within the farmland 706. As shown in Figure 7, each node 710 has an associated color (here, two red nodes and one yellow node). Furthermore, within the heatmap 702, areas that do not contain a node 710 are colored by interpolating the pest pressure values ​​at the node 710, thereby generating a continuous map of pest pressure values. Although only three nodes 710 are shown in Figure 7, those skilled in the art will understand that additional pest traps may be used to color parts of the heatmap 702. In this example, the heatmap 702 is a static heatmap showing pest pressure at a specific point in time (e.g., one of the first and second heatmaps described above).

[0093] The first screenshot 700 further includes a time-lapse button 712 that, when selected by the user, displays a time-lapse heatmap as described herein.

[0094] Figure 8 is a second screenshot 800 of a user interface that may be displayed on a computing device, such as client system 114 (shown in Figures 1 and 2). Specifically, the second screenshot 800 shows a magnified view of heatmap 702. The magnified view may be generated, for example, in response to a user making a selection on the user interface and changing the zoom level.

[0095] As shown in Figure 8, additional information not shown in the first screenshot 700 is shown in the enlarged view. For example, an additional node 802 (representing an additional collector) is now visible. Furthermore, the associated collector name is displayed along with each node 710. In an exemplary embodiment, in the enlarged view, the user can select a specific node 710 and display pest pressure data for that node 710 in the user interface. This will be described in more detail below in relation to Figure 10.

[0096] Figure 9 is a third screenshot 900 of a user interface that may be displayed on a computing device, such as a client system 114 (shown in Figures 1 and 2). Specifically, the third screenshot 900 shows a time-lapse heatmap 902. The time-lapse heatmap 902 may be displayed, for example, in response to the user selecting the time-lapse button 712 (shown in Figures 7 and 8).

[0097] As shown in Figure 9, the timeline 904 is displayed in relation to the time-lapse heatmap 902. The timeline 904 allows the user to quickly determine for what time period the pest pressure is currently indicated. In exemplary embodiments, the timeline 904 shows a range of dates, including historical and future dates. Furthermore, the timeline 904 includes a current time indicator 906 indicating the present (i.e., current time) and a selected time indicator 908 indicating which time period is associated with the pest pressure shown on the time-lapse heatmap 902.

[0098] For example, in Figure 9, the timeline 904 spans from January 5th to February 2nd, the current date is January 26th, and the time-lapse heatmap 902 shows the pest pressure for January 29th. In particular, since the selected time marker 908 is later than the current time marker 906, the pest pressure shown in Figure 9 is the predicted future pest pressure.

[0099] In one embodiment, the user can adjust the selected time indicator 908 (for example, by selecting and dragging the selected time indicator 908) to control which time periods are displayed by the time-lapse heatmap 902. Furthermore, in an exemplary embodiment, when the user selects the start icon 910, the time-lapse heatmap 902 is displayed as an animation, automatically transitioning between different static heatmaps to show the progression of pest pressure over time. A stop icon 912 is also shown in screenshot 900. If the user had previously selected the start icon 910, the user can select the stop icon 912 to stop the animation and freeze the time-lapse heatmap 902 at a desired point in time.

[0100] Figure 10 is a fourth screenshot 1000 of a user interface that may be displayed on a computing device, such as a client system 114 (shown in Figures 1 and 2). Specifically, the fourth screenshot 1000 shows pest pressure data 1002 for a particular collector. The pest pressure data 1002 may be displayed, for example, depending on whether the user has selected a particular node 710 (as described above with reference to Figure 8). In one embodiment, the pest pressure data 1002 includes graphical data 1004 that displays pest pressure over time (e.g., current and historical pest pressure), and text data 1006 that summarizes predicted future pest pressure.

[0101] Figure 11 shows a fifth screenshot 1100 of a user interface that may be displayed on a computing device, such as a client system 114 (shown in Figures 1 and 2). The fifth screenshot 1100 shows several user interface objects. User interface objects, as used herein, refer to graphical representations of objects displayed on the display of a computing device. User interface objects may be user-interactive or selectable by user input. For example, images (e.g., icons), buttons, and text (e.g., hyperlinks) each optionally constitute a user interface object. User interface objects may be displayed in any shape, any color, and / or any form. The fifth screenshot 1100 shows a user interface object 1101 representing a farmland boundary, and a user interface object 1104 representing a pest trap outside the farmland boundary. Specifically, the fifth screenshot 1100 shows a user interface object 1102 representing a heatmap indicating the current pest pressure value associated with a point in time within the current period (e.g., current month, current week, current period). The time point may be selected on screenshot 900 of Figure 9, and more specifically, by placing the time indicator 908 on a desired date indicated by 906. Specifically, the fifth screenshot 1100 shows a heatmap including a user interface object 1103 that represents historical pest pressure values ​​(or heatmaps indicating them) associated with a time point within a historical period (e.g., the month of the previous year corresponding to the current month (e.g., January 2020) (e.g., January 2019), the week of the previous year corresponding to the current week, the period of the previous year corresponding to the current period (e.g., winter 2020) (e.g., winter 2019)). The user interface object 1103 may be displayed according to a past time or past period, such as a corresponding past period selected by user input using the user interface object 1105.In one or more examples, the heatmap generating computing device and / or client device and / or mobile computing device. The vice may be configured to simultaneously display (e.g., superimpose and / or overlap) a user interface object 1102 representing a heatmap indicating the current pest pressure value associated with a point in time within the current period, together with a user interface object 1103 representing historical pest pressure values ​​associated with a point in time within a historical or past period (such as the same time in the previous year) corresponding to the current period. For example, the historical pest pressure values ​​include historical pest pressures for past growing seasons. For example, the fifth screenshot 1100 shows a user interface object 1105 that, when selected by the user, causes 1103 to display a selection of a period for historical pest pressure values.

[0102] User interface objects 1102 and 1103 may be displayed in any shape or form, and are not limited to the shapes shown in Figure 11. For example, user interface objects 1102 and 1103 may be displayed as two user interface objects (shaped, for example, as a disc or ring) that are superimposed or overlapped on each other and have a color and / or texture indicating the corresponding pest pressure value. It may be understood that in some areas, and for some crops, a calendar year may actually have two (or more) growing seasons. Using the techniques of this disclosure, growers are provided with information that can be used to compare the actual pest pressure value for the current season with historical pest pressure values ​​for past seasons. The same techniques may be applied to compare predicted future pest pressure values ​​for the current season or period with historical pest pressure values ​​for corresponding past seasons. The user interface may include a user interface object configured to accept user input to toggle or switch between displaying a user interface object representing historical pest pressure values ​​and displaying a user interface object representing current pest pressure values.

[0103] The user interface may include a user interface object configured to accept user input to toggle or switch between displaying a user interface object representing the pest pressure value for a first period (e.g., for the current period) and displaying a user interface object representing the pest pressure value for a second period (e.g., a historical period).

[0104] Figure 12 is a sixth screenshot 1200 of a user interface that may be displayed on a computing device, such as a client system 114 (shown in Figures 1 and 2). Specifically, the sixth screenshot 1200 shows pest pressure data 1202 for a particular collector. The pest pressure data 1202 may be displayed depending on whether the user has selected a particular node 710, for example (as described above with reference to Figure 8). In one embodiment, the pest pressure data 1202 includes graphical data 1204 displaying pest pressure values ​​over time (e.g., pest pressure values ​​for the current period), graphical data 1208 displaying historical pest pressure values ​​over time for a historical or past period corresponding to the current period (e.g., July 21 to August 10 of last year or another previous year), and optionally, text data 1206 summarizing predicted future pest pressure. The historical or past period for displaying 1208, such as a particular past time or a particular past year, may be selected by the user using a user interface object 1210. Screenshot 1200 may also be displayed depending on whether the user has selected a collector in Screenshot 1100 of Figure 11, where a past period has already been selected.

[0105] Furthermore, depending on the embodiment, the generated heatmap facilitates the control of additional systems. In one embodiment, a system for monitoring pest pressure (e.g., a system including a pest trap) uses the heatmap to predict pest pressure (e.g., a pest prediction system). This can be controlled by computing devices and / or heatmap generating computing devices. For example, the frequency and / or type of collection data reported by one or more pest traps may be changed based on the heatmap. In another example, spraying equipment (for example, for spraying insecticides) or other agricultural equipment may be controlled based on the heatmap.

[0106] At least one of the technical problems addressed by this system includes: i) the inability to accurately monitor pest pressure; ii) the inability to accurately predict future pest pressure; and iii) the inability to communicate pest pressure information to users in a comprehensive and direct manner.

[0107] The technical effects brought about by the embodiments described herein include, at a minimum, i) monitoring pest pressure in real time, ii) accurately predicting future pest pressure using machine learning, iii) controlling other systems or devices based on the predicted future pest pressure, iv) generating a comprehensive heat map showing pest pressure, v) generating a time-lapse heat map that dynamically displays changes in pest pressure over time, and vi) controlling other systems or devices based on the generated heat map.

[0108] Furthermore, the technical effects of the systems and processes described herein are achieved by performing at least one of the following steps: (i) receiving collection data for a plurality of pest traps within a geographic location, wherein the collection data includes at least current and historical pest pressures at each of the plurality of pest traps; (ii) receiving meteorological data for the geographic location, wherein the meteorological data includes at least current and historical meteorological conditions for the geographic location; (iii) receiving image data for the geographic location; (iv) identifying at least one geospatial feature within or near the geographic location; (v) applying a machine learning algorithm to the collection data, meteorological data, image data, and at least one identified geospatial feature to identify a correlation between pest pressure and at least one geospatial feature; and (vi) generating a predicted future pest pressure for the geographic location based at least the identified correlation between pest pressure and at least one geospatial feature.

[0109] The processor or processing element in the embodiments described herein may employ artificial intelligence and / or be trained using supervised or unsupervised machine learning, and the machine learning program may employ a neural network, which may be a convolutional neural network, a deep learning neural network, or a composite learning module or program that learns in two or more fields or areas of interest. Machine learning may include identifying and recognizing patterns in existing data to facilitate making predictions for subsequent data. The model may be constructed based on example inputs to make reasonable and reliable predictions for new inputs.

[0110] In addition, or alternatively, machine learning programs can be trained by inputting sample datasets or specific data, such as image data, text data, report data, and / or numerical analysis data. Machine learning programs may utilize deep learning algorithms that are primarily specialized in pattern recognition and may be trained after processing multiple cases. Machine learning programs may include—individually or in combination—Bayesian program learning (BPL), speech recognition and synthesis, image or object recognition, optical character recognition, and / or natural language processing. Machine learning programs may also include natural language processing, semantic analysis, automated reasoning, and / or machine learning. This may include learning.

[0111] In supervised machine learning, a processing element may be provided with example inputs and their associated outputs, and may strive to discover general rules that map inputs to outputs, so that when new inputs are subsequently provided, the processing element can accurately predict the correct output based on the discovered rules. In unsupervised machine learning, the processing element may be required to find its own structure in unlabeled example inputs. In one embodiment, machine learning techniques may be used to extract data about computer devices, users of computer devices, computer networks hosting computer devices, services running on computer devices, and / or other data.

[0112] Based on these analyses, processing elements can learn how to identify features and patterns that can then be applied to analyzing collection data, meteorological data, image data, and geospatial data (for example, using one or more models) to predict future pest pressures.

[0113] As used herein, the term “non-temporary computer-readable medium” is intended to represent any tangible computer-based device implemented in any way or technique for short-term and long-term storage of information, such as computer-readable instructions, data structures, program modules and submodules, or other data within any device. Therefore, the methods described herein, though not limited to, may be encoded as executable instructions embedded within tangible non-temporary computer-readable medium, including storage devices and / or memory devices. Such instructions, when executed by a processor, cause the processor to perform at least a portion of the methods described herein. Furthermore, as used herein, the term “non-temporary computer-readable medium” includes, but is not limited to, volatile and non-volatile media, as well as non-temporary computer storage devices, including, but not limited to, removable and non-removable media such as firmware, physical and virtual storage devices, CD-ROMs, DVDs, and any other digital sources such as networks or the internet, and all tangible computer-readable media, including, but not limited to, undeveloped digital means, with the sole exception of temporary propagation signals.

[0114] This specification, using examples, discloses the best mode of disclosure and further enables any person skilled in the art to carry out the embodiments, including, but not limited to, fabricating and using any device or system and performing any incorporated method. The patentable scope of this disclosure is defined by the claims and may include other examples that a person skilled in the art could conceive. Such other examples are intended to fall within the scope of the claims if they have structural elements that are identical to the language of the claims, or if they include equivalent structural elements that differ only slightly from the language of the claims.

Claims

1. Memory and A processor connected to the aforementioned memory in a communicative manner, A harmful organism pressure prediction computing device comprising the processor, Receiving collection data for multiple pest traps within a geographical location, wherein the collection data includes at least current and historical pest pressure in each of the multiple pest traps. Receiving meteorological data for the aforementioned geographical location, wherein the meteorological data includes at least current and historical meteorological conditions for the aforementioned geographical location. Receiving image data for the aforementioned geographical location, Identifying at least one geospatial feature within or near the aforementioned geographical location, The machine learning algorithm is applied to the collected data, the weather data, the image data, and the at least one identified geospatial feature to identify the correlation between the pest pressure and the at least one geospatial feature. At a minimum, generating predicted future pest pressure for the geographic location based on the identified correlation between pest pressure and the at least one geospatial feature, A computing device programmed to predict pest pressure.

2. The pest pressure prediction computing device according to claim 1, wherein the at least one geospatial feature includes at least one of elevation features, bodies of water, transport routes, and factories.

3. The pest pressure prediction computing device according to claim 1 or 2, wherein the processor is further programmed to generate action recommendations for the geographic location based on the predicted future pest pressure.

4. The pest pressure prediction computing device according to any one of claims 1 to 3, wherein the processor is further programmed to transmit the predicted future pest pressure of the pest to a mobile computing device and to display the predicted pest pressure on the mobile computing device, the predicted pest pressure being displayed via an application installed on the mobile computing device.

5. The pest pressure prediction computing device according to any one of claims 1 to 4, wherein the weather data includes predicted future weather conditions for the geographic location.

6. The pest pressure prediction computing device according to any one of claims 1 to 5, wherein the identified correlation is a correlation between pest pressure and the distance from at least one geospatial feature.

7. The pest pressure prediction computing device according to any one of claims 1 to 6, wherein the processor is further programmed to control at least one of a pest monitoring system and agricultural equipment based on the predicted future pest pressure.

8. A method for generating pest pressure description data, wherein the method is carried out using a pest pressure prediction computing device including a memory communicably coupled to a processor, and the method is Receiving collection data for multiple pest traps within a geographical location, wherein the collection data includes at least current and historical pest pressure in each of the multiple pest traps. Receiving meteorological data for the aforementioned geographical location, wherein the meteorological data includes at least current and historical meteorological conditions for the aforementioned geographical location. Receiving image data for the aforementioned geographical location, Identifying at least one geospatial feature within or near the aforementioned geographical location, The machine learning algorithm is applied to the collected data, the weather data, the image data, and the at least one identified geospatial feature to identify the correlation between the pest pressure and the at least one geospatial feature. At a minimum, generating predicted future pest pressure for the geographic location based on the identified correlation between pest pressure and the at least one geospatial feature, A method that includes this.

9. The method according to claim 8, wherein the at least one geospatial feature includes at least one of an elevation feature, a body of water, a transport route, and a factory.

10. The method according to claim 8 or 9, further comprising generating a remedial recommendation for the geographical location based on the predicted future pest pressure.

11. The method according to any one of claims 8 to 10, comprising transmitting the predicted future pest pressure of the pest to a mobile computing device and displaying the predicted pest pressure on the mobile computing device, further comprising displaying the predicted pest pressure via an application installed on the mobile computing device.

12. The method according to any one of claims 8 to 11, wherein the weather data includes predicted future weather conditions for the geographic location.

13. The method according to any one of claims 8 to 12, wherein the identified correlation is a correlation between pest pressure and the distance from at least one geospatial feature.

14. The method according to any one of claims 8 to 13, further comprising controlling at least one of a pest monitoring system and agricultural equipment based on the predicted future pest pressure.

15. A computer-readable storage medium containing computer-executable instructions, when executed by a pest pressure prediction computing device including at least one processor that communicates with memory, the computer-readable instructions are transmitted to the pest pressure prediction computing device. Receiving collection data for multiple pest traps within a geographical location, wherein the collection data includes at least current and historical pest pressure in each of the multiple pest traps. Receiving meteorological data for the aforementioned geographical location, wherein the meteorological data includes at least current and historical meteorological conditions for the aforementioned geographical location. Receiving image data for the aforementioned geographical location, Identifying at least one geospatial feature within or near the aforementioned geographical location, The machine learning algorithm is applied to the collected data, the weather data, the image data, and the at least one identified geospatial feature to identify the correlation between the pest pressure and the at least one geospatial feature. At a minimum, generating predicted future pest pressure for the geographic location based on the identified correlation between pest pressure and the at least one geospatial feature, A computer-readable storage medium that enables the following process.

16. The computer-readable storage medium according to claim 15, wherein the at least one geospatial feature includes at least one of an elevation feature, a body of water, a transport route, and a factory.

17. The aforementioned instruction further provides the pest pressure prediction computing device, A computer-readable storage medium according to claim 15 or 16, which generates treatment recommendations for the geographical location based on the predicted future pest pressure.

18. The computer-readable storage medium according to any one of claims 15 to 17, wherein the instruction further causes the pest pressure prediction computing device to transmit the predicted future pest pressure of the pest to a mobile computing device and to display the predicted pest pressure on the mobile computing device, the predicted pest pressure being displayed via an application installed on the mobile computing device.

19. A computer-readable storage medium according to any one of claims 15 to 18, wherein the weather data includes predicted future weather conditions for the geographic location.

20. The computer-readable storage medium according to any one of claims 15 to 19, wherein the identified correlation is a correlation between pest pressure and the distance from at least one geospatial feature.

Images