• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    The present invention provides a system and method that includes a machine learning module which analyzes data collected from one or more sources such as UAVs, satellites, crop sensors mounted on the span (span), direct soil sensors and sensors climate change. According to another preferred modality, the machine learning module preferably creates sets of field objects from within a given field and uses the data received to create a predictive model for each field object defined based on characteristics detected from of each field object within the field.
    公开号:BR112019024937A2
    申请号:R112019024937-0
    申请日:2018-05-31
    公开日:2020-06-23
    发明作者:L. Larue Jacob；Jacob L. LaRue；Carritt Andrew；Andrew Carritt；M. Dixon Joshua；Joshua M. Dixon
    申请人:Valmont Industries, Inc.；
    IPC主号:
    专利说明:

    [001] [001] RELATED REQUESTS
    [002] [002] This application claims priority to US Provisional Application No. 62 / 513,479 filed on June 1, 2017.
    [003] [003] BACKGROUND AND FIELD OF THE PRESENT INVENTION
    [004] [004] Field of the present invention
    [005] [005] The present invention generally relates to a system and method for managing irrigation systems and, more particularly, to a system and method for using machine learning to model and design workflows for an irrigation system.
    [006] [006] Background of the Invention
    [007] [007] The ability to monitor and control the amount of water, chemicals and / or nutrients (applicators) applied to an agricultural field has increased the amount of cultivable acres in the world and increases the likelihood of profitable crop yield. Known irrigation systems typically include a control device with a user interface allowing the operator to monitor and control one or more functions or operations of the irrigation system. Through the use of the user interface, operators can control and monitor numerous aspects of the irrigation system and the growing environment. Additionally, operators can receive significant environmental and growth data from local and remote sensors.
    [008] [008] Despite the significant amounts of data and control available to operators, the systems present do not allow operators to model or otherwise use most of the data or control elements at their disposal. Instead, operators limit themselves to
    [009] [009] Outside the irrigation field, several machine learning methods have been developed that allow supervised and unsupervised learning models based on defined data sets. For example, support vector machines (SVMs) allow for a supervised learning model that uses associated learning algorithms that analyze data used for classification and regression analysis. Consequently, an SVM training algorithm is able to build a model using, for example, a linear classifier to generate an SVM model. When SVM and other types of models can be created, they can be used as predictive tools to guide future decision making.
    [010] [010] To overcome the limitations of the state of the art, a system that is capable of collecting and integrating data from a variety of sources is required. In addition, a system and method capable of using the data collected to model, predict and control irrigation and other results in the field are needed.
    [011] [011] Summary of the Present Invention
    [012] [012] To address the deficiencies presented in the state of the art, the present invention provides a system and method that includes a machine learning module that analyzes data collected from one or more sources, such as historical applications by the irrigation machine, UAVs, satellites , crop sensors mounted on the span (span), field-based sensors and weather sensors. According to another preferred modality, the machine learning module preferably creates sets of field objects (management zones) from within a given field and uses the data received to create a predictive model for each field object defined based on in the characteristic data of each field object within the field.
    [013] [013] The attached figures, which are incorporated and constitute part of the specifications, illustrate various modalities of the present invention and together with the specification, serve to explain the principles of the present invention.
    [014] [014] Brief description of the figures
    [015] [015] FIG. 1 shows an exemplary irrigation system for use with the present invention.
    [016] [016] FIG. 2 shows a block diagram illustrating the exemplary processing architecture of a control device according to a first preferred embodiment of the present invention.
    [017] [017] FIG. 3 shows an exemplary irrigation system with a number of exemplary energized elements included in accordance with another preferred embodiment of the present invention.
    [018] [018] FIG. 4 shows a block diagram illustrating a preferred method according to a preferred embodiment of the present invention.
    [019] [019] FIG. 4A shows a block diagram illustrating another preferred method according to a preferred embodiment of the present invention.
    [020] [020] FIGS. 5A-5C show diagrams illustrating examples of field object definitions according to a preferred embodiment of the present invention.
    [021] [021] FIG. 6 shows a block diagram illustrating additional aspects of an exemplary method and system of the present invention.
    [022] [022] Description of Preferred Arrangements
    [023] [023] Reference is now made in detail to the exemplary modalities of the invention, examples of which are illustrated in the attached figures. Whenever possible, the same reference numbers will be used in all figures to refer to the same or similar parts. Descriptions, modalities and figures should not be taken as limiting the scope of the claims. It should also be understood that, during this invention, unless logically required otherwise, where a process or method is presented or described, the steps of the method can be performed in any order, repetitively, iteratively or simultaneously. As used throughout this application, the word "can" is used in a permissive sense (that is, meaning "to have the potential for"), rather than the mandatory sense (that is, meaning "must").
    [024] [024] Before discussing specific modalities, modalities of a hardware architecture to implement certain modalities are described here. One mode can include one or more computers communicatively connected to a network. As is known to those skilled in the art, the computer may include a central processing unit ("CPU"), at least one read-only memory ("ROM"), at least one random access memory ("RAM"), at least least one hard disk ("HD"), and one or more input / output devices ("I / O"). I / O devices may include a keyboard, monitor, printer, electronic pointing device (such as a mouse, trackball, stylist, etc.), or the like. In several ways, the computer has access to at least one database on the network.
    [025] [025] ROM, RAM and HD are computer memories to store instructions executable by computer, executable by the CPU. Within this invention, the term "computer-readable medium" is not limited to ROM, RAM and HD and can include any type of data storage medium that can be read by a processor. In some embodiments, a computer-readable medium may refer to a data cartridge, a magnetic data backup tape, a floppy disk, a flash memory drive, an optical data storage drive, a CD-ROM, ROM, RAM, HD or similar.
    [026] [026] At least portions of the features or processes described here can be implemented in appropriate computer executable instructions. Computer-executable instructions can be stored as software code components or modules on one or more computer-readable media (such as non-volatile memories, volatile memories, DASD arrays, magnetic tapes, floppy disks, hard drives, optical storage devices, etc. or any other computer-readable storage medium or suitable storage device). In one embodiment, computer executable instructions may include C ++, Java, HTML, compiled lines or any other programming or scripting code such as R, Python and / or Excel. In addition, the present invention teaches the use of processors to perform the features and processes described herein. As such, a processor is defined as the computer chip or processing element that executes the computer code necessary for the performance of a specific action.
    [027] [027] Additionally, the functions of the disclosed modalities can be implemented on a computer or shared / distributed between two or more computers within or through one or multiple networks or cloud. Communications between implementation modalities on computers can be carried out using any electronic, optical or radio frequency signals, transmitted via a power line carrier, cell phone, digital radio or other suitable methods and communication tools in accordance with known network protocols.
    [028] [028] Additionally, any illustrations or examples given in this document should in no way be considered as restrictions, limits or express definitions of any term or terms with which they are used. Instead, these examples or illustrations are to be considered as illustrative only. Those of ordinary skill in the art will appreciate that any term or terms used with which these examples or illustrations are used will encompass other modalities that may or may not be given together or elsewhere in the specifications and all of these modalities are intended to be included within the scope of that term or terms.
    [029] [029] FIGS 1 to 6 illustrate various modalities of irrigation systems that can be used with examples of implementations of the present invention. As will be understood, the irrigation systems shown in FIGS. 1 to 6 are exemplary systems in which the features of the present invention can be integrated. Consequently, FIGS. 1 to 6 are merely illustrative and any one of several systems (i.e., fixed systems as well as self-propelled central and linear pivot irrigation systems; stationary systems; corner systems) can be used with the present invention without limitation. For example, although FIG. 1 is shown as a center pivot irrigation system, the exemplary irrigation system 100 of the present invention can also be implemented as a linear irrigation system. The exemplary irrigation system 100 is not intended to limit or define the scope of the present invention in any way. According to later preferred embodiments, the present invention can be used with a variety of types of motors, such as gas powered, DC powered, switch reluctance, single-phase AC and the like. Still further, the exemplary embodiments of the present invention are discussed primarily in relation to direct spray irrigation methods. However, the methods and systems of the present invention can be used with any method of delivering applicants without limitation. For example, other delivery methods used by the present invention may include methods such as drip, spray gun, mobile gun, solid set, flood and other irrigation methods without limitation.
    [030] [030] With reference now to FIG. 1, extensions 102, 104, 106 are shown supported by the drive towers 108, 109, 110. Additionally, each drive tower 108, 109, 110 is shown with the respective motors 117, 119, 120 that supply torque to the drive wheels 115 , 116, 118. As shown further in FIG. 1, the irrigation machine 100 may preferably further include an extension / protrusion 121 which may include an end cannon (not shown).
    [031] [031] As shown, FIG. 1 provides an illustration of an irrigation machine 100 without any energized elements and sensors added. Referring now to FIG. 3, an exemplary system 300 is shown in which several examples of energized elements are included. As shown in FIG. 3, the present invention is preferably implemented by connecting elements of the present invention to one or more extensions 310 of an irrigation system that is connected to a water source or well 330. As shown further, the exemplary irrigation system still preferably includes 326 transducers , 328 which are provided to control and regulate water pressure, as well as drive units 316, 324 which are preferably programmed to monitor and control portions of the drive system of the irrigation unit.
    [032] [032] Additionally, the system of the present invention preferably further includes elements such as a GPS receiver 320 for receiving positional data and a flow meter 332 for monitoring the flow of water in the system. In addition, the system of the present invention preferably includes a range of sensors and can receive a range of sensor input data from a variety of sources, as further discussed here. As discussed with reference to FIG. 4 below, these sensors and inputs include any number of embedded sensors, sensors in situ, remote / offsite sensors and earth mapping data, as well as measurements or specifications provided by the manufacturer / producer and / or specialist.
    [033] [033] With reference again to FIG. 3, representative indirect crop sensors 314, 318 are shown that can collect a range of data (as discussed below), including soil moisture levels. Additionally, sensors 314, 318 can also include optics to allow detection of the type of crop, stage of growth, health, presence of disease, growth rate and the like. In addition, the system can preferably also include one or more 311 direct sensors that can be connected directly to a plant to provide direct readings of the plant's health and status. In addition, one or more direct soil sensors 313 can also be used to generate data on soil moisture, nutrient content or other data related to soil. For example, preferred soil sensors 313 can record data related to a variety of soil properties, including: soil texture, salinity, organic matter levels, nitrate levels, soil pH and clay levels. In addition, the detection system can also include a weather station 322 or similar that is capable of measuring climatic characteristics such as humidity, barometric pressure, precipitation, temperature, received solar radiation, wind speed and the like. In addition, the system may preferably include a 311 wireless transceiver / router and / or power line carrier-based communication systems (not shown) for receiving and transmitting signals between system elements.
    [034] [034] With reference now to FIG. 2, an exemplary control device 138 representing functionality for controlling one or more operational aspects of the irrigation system 100 will be discussed. As shown, exemplary control device 138 includes processor 140, memory 142 and network interface 144. Processor 140 provides processing functionality for control device 138 and can include any number of processors, microcontrollers or other control systems. processing. Processor 140 can run one or more software programs that implement techniques described here. Memory 142 is an example of tangible computer-readable media that provides storage functionality to store various data associated with the operation of control device 138, such as a software program and code segments mentioned above, or other data to instruct processor 140 and other elements of the control device 138 to perform the steps described here. Memory 142 may include, for example, removable and non-removable memory elements, such as RAM, ROM, flash (for example, SD card, mini-SD card, micro-SD card), magnetic, optical and USB memory devices, and so on. Network interface 144 provides functionality to enable control device 138 to communicate with one or more networks 146 through a variety of components such as wireless access points, power line carrier transceiver interfaces and so on, and any associated software employed by these components (for example, drivers, configuration software, and so on).
    [035] [035] In implementations, the irrigation position determination module 148 may include a global positioning system (GPS) receiver, a LORAN system or the like to calculate an irrigation system location 100. Additionally, the control device 138 can be coupled to a guide device or similar system 152 of the irrigation system 100 (for example, switchgear assembly or switching mechanism) to control the movement of the irrigation system 100. As shown, control device 138 may further include a positional terrain compensation module 151 to assist in controlling movement and location recognition of the system. In addition, control device 138 may preferably also include multiple inputs and outputs to receive data from sensors 154 and monitoring devices as discussed later below.
    [036] [036] With further reference to FIG. 3, according to a later preferred embodiment, the system of the present invention can also include distributed data collection and routing hubs 305, 307, 309 that can directly transmit and receive data from the various sensors in the extension to a machine learning module 306 supplied on a remote server 306 that receives a number of inputs from the irrigation system sensors 300. In this modality, the machine learning module 306 preferably includes software on the service side that can be accessed via the Internet or other architecture network. Alternatively, the machine learning module 306 and other aspects of the present invention may include client-side software residing on the main control panel 308 or elsewhere. Regardless, it should be understood that the system can be formed from any suitable software or hardware, or both configured to implement the features of the present invention.
    [037] [037] According to another preferred embodiment, the systems of the present invention preferably operate together to collect and analyze data. According to one aspect of the present invention, data is preferably collected from one or more sources, including image and moisture sensing data from UAVs 302, 304 satellites, crop sensors mounted on extension 318, 314, as well as the weather station 322, sensors in the soil 313, crop sensors 311, as well as data provided by the control / monitoring systems of the irrigation machine 100 itself (for example, amount applied, place and time of irrigation water application or other applicator, current status and position of the irrigation machine, machine failures, machine piping pressures, etc.) and other system elements. Preferably, the combination and analysis of data is processed and updated continuously.
    [038] [038] According to another preferred modality, satellite image data can be processed and used to generate vegetation index data, such as: EVI (enhanced vegetation index), NDVI (normalized difference vegetation index) , SAVI (vegetation index adjusted to soil), MASVI (modified vegetation index adjusted to soil) and PPR (vegetable pigment ratio) and the like. Other sensors can include any of a variety of electromagnetic, optical, mechanical, acoustic and chemical sensors. These may also include sensors that measure Frequency Domain Reflectometry (FDR),
    [039] [039] With reference now to FIGS. 3 to 7, a preferred method for using the machine learning module 306 of the present invention will now be discussed. Preferably, in preparation for processing, combining and evaluating the data collected from the sensor sources, as discussed below, the machine learning module 306 will preferably receive first measurements and field dimensions. According to a preferred modality, the dimensions of the field can be inserted from manual or third party mappings, from the length of the physical machine or from image recognition systems using satellite image history. Alternatively, data hubs 305, 307, 309 may preferably also include mapping sensors, such as GPS, visual measurement detectors and / or laser to determine the dimensions of the field.
    [040] [040] With reference now to FIG. 4, after entering field measurements and dimensions, machine learning module 306 in step 424 will preferably create subsections of the entire field and store the subsections created as field objects known as "management zones". As shown in FIG. 5A, according to a preferred embodiment, for a central pivot irrigation machine, the created field objects are preferably created as annular sectors 506 formed as subsections of rings defined by an inner and outer circle of arbitrary radii. These radii can be consistently increased or varied, depending on a variety of factors, including, but not limited to, sprinkler spacing along the machine, stored sprinkler groups or other factors. Circumferentially,
    [041] [041] As shown in FIG. 5B, the angle (ϴ) is preferably defined by an arc length 504 which can be an arbitrary length provided by the user, the projection radius of the last sprinkler, defined by the resolution of the irrigation machine's location recognition system or other factor . In addition, this arc length does not need to be consistent from segment to segment within the field area. However, all arc lengths must add to the circumference of the circle from which they have been subdivided and they cannot overlap. Similarly, the angles (ϴ) must add up to 360 and the location of these angles (ϴ) must be such that the areas covered by each angle do not overlap and are always adjacent to other angles (ϴ). As shown in FIG. 5C, field objects 508 can preferably be divided into data sets consisting of columns from C1 to Cn, where each C is defined as a collection of annular sectors (labeled Cn, 1, Cn, 2, .. Cn, x) and a circular sector (labeled Cn, z) that fit arbitrary arc length (s). Still further, as shown in FIGS. 5A to C, each annular sector can preferably be defined as having: where ϴ is the angle formed by adjacent rays separated by the outer length of the circumference S; Ru the radius of the outer arc; and Ri is the radius of the inner arc of the annular segment. According to alternative preferred modalities, field objects can alternatively be evaluated or gauged in a grid system, polar coordinate system or use any other spatial categorization system as needed.
    [042] [042] With reference again to FIG. 4, in step 426, the data for each defined field object is preferably collected and stored as discussed above.
    [043] [043] With reference again to FIG. 4, in step 428, each annular field / sector object is preferably defined as a discrete data point containing characteristics inherited from field-level data, as well as characteristics derived from its relationship with other data points (for example, types and elevations of neighboring soils). In one embodiment, as an example, the slopes of adjacent field objects can be used to calculate the flow of excessive rainfall into or out of a specific field object.
    [044] [044] In step 432, the discrete data points created are preferably used by the machine learning module 306 to create a predictive module for each discrete data point. According to a preferred modality, the machine learning module 306 performs the modeling function by pairing each data point with input / output data for the field object and evaluating the data over time or as a non-temporal set. According to another preferred modality, performance schedules / observations are then evaluated for a specific output, as part of the entire collection, with the evaluator machine learning how to categorize data points and building an algorithm that accurately reflects performance schedules. performance observed for the desired output. One or more of these algorithms are then preferably assembled in a solution model that can be used to evaluate new fields in real time with the aim of helping producers to optimize profitability, cash flow, regulatory compliance, application efficiency water, fertilizers or chemicals, or any other measurable or intangible benefit that may be needed or discovered.
    [045] [045] According to a preferred modality, the solution model can preferably be created for each management zone (annular sector or other irrigable unit) for each field. In addition, solution models can preferably be created in whole or in part by any number or combination of human-provided heuristics and / or machine-created algorithms. In addition, the algorithms can be created by regressions, simulations or any other form of machine / deep learning. According to other preferred embodiments, the solution model of the present invention can be provided as neural networks, independent algorithms or any combination of learned or created code modules or independent programs. Additionally, the solution model can preferably incorporate current / cached data feed from local and remote sources.
    [046] [046] With reference now to FIG. 4, the solution model of the present invention can preferably be delivered to a producer via a push / pull request from the content delivery network, point-to-point connection or any other form of electronic or analog transport. In addition, the system will preferably allow an operator to accept, reject or modify a solution model after review.
    [047] [047] Once a model is delivered, in step 434, data entries are preferably received and provided to the model for evaluation. In step 436, the output values are generated as discussed below. Preferably, data entries preferably include acceptance, rejection or modification of the operator's solution model and any updated data from any of the data entry lists discussed above with respect to steps 424 to 432. Additionally, data entries may include additional data, such as data specified by the producer and / or desired data, such as: desired direction of travel; depth of application of base water; variable rate prescription for speed, zone or individual sprinkler; recommendation from producers for chemigation; chemigation material; amount of chemigation material ready for injection; basic amount of chemigation application per unit area; variable rate prescription for speed, zone or individual sprinkler; operation or repair status of the irrigation system and / or the sensor.
    [048] [048] With reference now to FIGS. 4 and 4A, an example method for inputting data and outputting modeled values should now be discussed in more detail. As shown in FIG. 4A, machine learning module 440 of the present invention can preferably be used to receive historical data 438 (step 428 in FIG. 4), which can include data recorded over a period of time (i.e., weeks, months, years) for each object within a given field. This historical data is preferably received by machine learning module 440 and used to create predictive models 450 from defined training sets 446 for selected desired outputs (step 432 in FIG. 4). To create the predictive models 450, machine learning module 440 preferably also includes sub modules for processing received data 442, including steps such as data cleaning, data transformation, normalization and resource extraction.
    [049] [049] Once extracted, the target characteristic vectors 444 are routed to a training module 446 which is used to train one or more machine learning algorithms 448 to create one or more predictive models 450. As shown, the model predictive 450 preferably receives input from current sensor 454 (step 434 in FIG. 4) and sends model 456 output / evaluation data (step 436 in FIG. 4) that is provided to a processing module 458 for create system inputs and changes based on the model 456 output. In step 452, output values 456 and current inputs 454 are preferably additionally fed back to machine learning module 440 through a feedback loop 452, so that module 440 can continuously learn and update predictive model 450.
    [050] [050] With reference now to FIG. 6, a further application example of the present invention will now be discussed further. As shown in FIG. 6, the example application refers to the adjustment of the drive and VRI systems based on the detected system data. As shown, the sample data fed into the system can include positional data 602 for a given time (P1). In addition, sample data can also include torque application data 604 from drive system 605 (D 1)
    [051] [051] According to a preferred embodiment of the present invention, the exemplary predictive model 624 shown in FIG. 6 is preferably created and updated by the methods described in relation to FIGS. 4, 4A and 5 discussed above. As shown in FIG. 6, the exemplary predictive model 624 can calculate moisture levels (that is, soil moisture levels) from a calculated slip ratio range. More specifically, the exemplary predictive model 624 can preferably calculate a modeled moisture level for a given annular region based on a measured slip ratio. In the next step, the estimated moisture level of the annular region provided can then be routed to a 625 processing module, which can then use the estimated moisture level to make selected adjustments to the irrigation system. For example, the processing module can calculate a speed correction based on the measured slip rate, which is then issued 622 to the 605 drive system. Speed corrections can also include a speed comparison between towers and an alignment calculation. between towers. In addition, the processing module can calculate a corrected watering rate 620 that can be issued to the VRI 608 controller. In addition, the processing module 625 can issue an updated moisture level 618 to be included in system notifications or other calculations .
    [052] [052] It should be understood that the present invention can analyze and model a range of irrigation systems and subsystems and provide customized models for execution based on any data received. The modeling discussed in relation to FIG. 6 is just a single example. Other modeling outputs may include instructions and / or recommendations for each subsystem, including changes in: direction of travel; depth of application of base water; variable rate prescription for speed, zone or individual sprinkler; recommendation of chemigation for producers; quantity and type of chemigation material; required amount of chemigation material ready for injection; basic amount of chemigation application per unit area; maintenance and / or repair of the central pivot; sensor maintenance and / or repair status and the like, without limitation. Where desired, each modeled output can be automatically routed and executed by the irrigation system or sent for acceptance / input from the producer in preparation for execution.
    [053] [053] Although the above descriptions of the present invention contain a lot of specificity, these should not be interpreted as limitations in scope, but rather as examples. Many other variations are possible. For example, the processing elements of the present invention by the present invention can operate on a number of frequencies. In addition, the communications provided with the present invention can be designed to be duplex or simplex in nature. In addition, as required, the processes for transmitting data to and from the present invention can be designed to be push or pull in nature. In addition, each feature of the present invention can be made to be activated and accessed remotely from distant monitoring stations. Consequently, the data can preferably be loaded and downloaded of the present invention, as needed.
    [054] [054] Consequently, the scope should not be determined by the illustrated modalities, but by the attached claims and their legal equivalents.
    权利要求:
    Claims (23)
    [1]
    1. A system for use with a self-propelled irrigation system having at least one extension and a drive system for moving the extension through a field to be irrigated, the system comprising: sensors mounted on the extension, where at least a sensor mounted on the extension comprises at least one sensor configured to allow the detection of a crop aspect; in which the crop aspect is also selected from the group of crop aspects comprising: type of crop, stage of growth, health, presence of disease and growth rate; climatic sensors, in which at least one climatic sensor is configured to detect at least one climatic condition, in which the climatic condition is selected from the group of climatic conditions comprising: humidity, pressure, precipitation and temperature; air sensors, where air sensors include at least one sensor located on an unmanned aerial vehicle, plane or satellite; and a machine learning module, in which the machine learning module is configured to receive characteristic data for the field; where the machine learning module is configured to create a set of field objects for the field and use the characteristic data to create a predictive model for each field object defined based on the characteristic data detected for each field object within the field. field;
    [2]
    The system of claim 1, wherein the machine learning module receives measurements and field dimensions determined by mapping sensors.
    [3]
    3. The system of claim 1, in which the set of field objects are stored as ring sectors; in which the annular sectors are formed as subsections of rings defined by an inner and outer circle with the shape preferably limited by the difference in radial length, and an angle (ϴ) derived from two radii that connect to the ends of an outer length L determined by the selected angle (ϴ).
    [4]
    The system of claim 3, wherein each annular sector is defined as having an area = (Ru2 - Ri2) / 2ϴ; where ϴ = L / r, Ru is the radius of the outer arc, Ri is the radius of the inner arc, r is the radius of the irrigable field and L is the arc length of the outer circumference for the selected angle (ϴ).
    [5]
    5. The system of claim 4, in which the characteristic data for each defined field object is preferably collected and stored in a query table.
    [6]
    The system of claim 5, wherein the characteristic data comprises data received from embedded sensor arrays.
    [7]
    7. The system of claim 6, wherein the characteristic data comprises data selected from the data group comprising: direct soil moisture, plant status, crop cover temperature, ambient air temperature, relative humidity, barometric pressure, radiation from long and short waves, photosynthetically active radiation, rainfall, wind speed and spectral bands outside the soil and crop coverage.
    [8]
    The system of claim 5, wherein the characteristic data is acquired from systems not attached to the irrigation system.
    [9]
    The system of claim 8, wherein the characteristic data comprises data selected from the data group comprising: Geotiff, RGBNRGB, NDVI, NIRNRGB and individual spectral bands.
    [10]
    The system of claim 9, wherein the characteristic data comprises evapotranspiration data from satellite heat balance models including infrared heat signatures and data from a crop stress index model.
    [11]
    The system of claim 5, wherein the characteristic data comprises data from weather stations to compute evapotranspiration.
    [12]
    The system of claim 11, wherein the characteristic data comprises: temperature, relative humidity, precipitation, solar radiation, wind speed, runoff, climatic data and projected conditions.
    [13]
    13. The system of claim 5, wherein the characteristic data comprises data relating to the irrigation machine, wherein the data is selected from the data group comprising: flow, pressure, voltage, error messages, setting of the percentage timer, direction , fertigation / chemigation status, water chemical information and operational information.
    [14]
    14. The system of claim 5, wherein the system comprises data referring to the specifications of the irrigation system and its subcomponents.
    [15]
    15. The system of claim 5, in which the machine learning module VRl further analyzes the data referring to the specifications entered by the producer; where specifications are selected from the group of specifications comprising: soil analysis, soil chemistry, water chemistry, geographic analysis, meteorological analysis, irrigation schedules and yield data
    [16]
    16. The system of claim 5, in which the characteristic data comprises data referring to the specifications entered by the producer, in which the specifications are selected from the group of specifications comprising: calculations of the soil water balance; soil moisture in the root zone; soil moisture by depth; prediction of soil moisture in the root zone; and prediction of soil moisture by depth.
    [17]
    17. The system of claim 5, wherein the annular sector is defined as a discrete data point that is linked to characteristic data.
    [18]
    The system of claim 17, wherein the VRI machine learning module creates a predictive module for each discrete data point.
    [19]
    19. The system of claim 18, wherein the VRI machine learning module evaluates each discrete data point over time.
    [20]
    20. The system of claim 19, in which the assessed data is categorized to build a solution model to maximize profitability for a given field.
    [21]
    21. The system of claim 20, in which individual solution models are created for each ring sector.
    [22]
    22. The system of claim 21, wherein the system allows an operator to accept, reject or modify a solution model after review.
    [23]
    23. The system of claim 22, wherein the additional data entries comprise data specified by the producer, comprising: desired direction of travel, depth of application of the base water, prescription of variable rate for speed, zone or individual sprinkler, recommendation of producer chemigation, chemigation material, amount of chemigation material ready for injection, basic amount of chemigation application per unit area, variable rate prescription for speed, and system repair status.
    类似技术:
    公开号 | 公开日 | 专利标题
    BR112019024937A2|2020-06-23|SYSTEM FOR USE WITH A SELF-PULSED IRRIGATION SYSTEM AND A DRIVE SYSTEM
    US10728336B2|2020-07-28|Integrated IoT | system solution for smart agriculture management
    US20180263171A1|2018-09-20|Generating an agriculture prescription
    US9886016B2|2018-02-06|Automated irrigation control system
    US20200060106A1|2020-02-27|Crop-specific automated irrigation and nutrient management
    US20160314542A1|2016-10-27|Automated agricultural activity determination system and method
    US20200320647A1|2020-10-08|Generating digital models of relative yield of a crop based on nitrate values in the soil
    US20150272017A1|2015-10-01|Method and system for automated differential irrigation
    Phillips et al.2014|Integrated sensing of soil moisture at the field-scale: Measuring, modeling and sharing for improved agricultural decision support
    US10853377B2|2020-12-01|Sequential data assimilation to improve agricultural modeling
    US20170336533A1|2017-11-23|Radar based precipitation estimates using spatiotemporal interpolation
    US20170351005A1|2017-12-07|Computing radar based precipitation estimate errors based on precipitation gauge measurements
    US10359514B2|2019-07-23|Generating estimates of uncertainty for radar based precipitation estimates
    Almalki et al.2021|A low-cost platform for environmental smart farming monitoring system based on IoT and UAVs
    Li et al.2020|Review of sensor network-based irrigation systems using IoT and remote sensing
    Rabadiya Kinjal et al.2018|Smart irrigation: Towards next generation agriculture
    MAKARIO et al.2019|Long Range Low Power Sensor Networks for Agricultural Monitoring-A Case Study in Kenya
    Kovalchuk et al.2020|Development of Low-Cost Internet-of-Things | Networks for Field Air and Soil Monitoring Within the Irrigation Control System
    Chiu et al.2020|Development of a wireless sensor network for tracking flood irrigation management in production-sized rice fields in the mid-south
    US11176117B2|2021-11-16|Automated detection of errors in location data in agricultural operations
    US20200302555A1|2020-09-24|Crop seeding recommendations
    US20210302973A1|2021-09-30|Horticulture aided by autonomous systems
    US20210298244A1|2021-09-30|Horticulture aided by autonomous systems
    Anand et al.2019|Soil moisture and atmosphere components detection system using IoT and machine learning
    Kelley2016|Addressing Data Resolution in Precision Agriculture
    同族专利:
    公开号 | 公开日
    ZA201907448B|2020-11-25|
    CN110708948A|2020-01-17|
    US20180348714A1|2018-12-06|
    EP3629695A1|2020-04-08|
    CA3064038A1|2018-12-06|
    AU2018275673A1|2019-12-05|
    WO2018222875A1|2018-12-06|
    EP3629695A4|2021-03-03|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    US5927603A|1997-09-30|1999-07-27|J. R. Simplot Company|Closed loop control system, sensing apparatus and fluid application system for a precision irrigation device|
    AR021219A1|1998-09-15|2002-07-03|Secretary Of Agriculture The Us|IRRIGATION SYSTEM HAVING A SENSOR NETWORK FOR FIELD REPRESENTATION|
    AUPR339501A0|2001-02-27|2001-03-22|Computronics Corporation Limited|Control apparatus for a boom irrigator, and a method and system relating thereto|
    US6889620B2|2001-02-28|2005-05-10|The Mosaic Company|Method for prescribing site-specific fertilizer application in agricultural fields|
    US7584053B2|2004-08-05|2009-09-01|Reintech, Llc|Universal remote terminal unit and method for tracking the position of self-propelled irrigation systems|
    US20080046130A1|2006-08-03|2008-02-21|Deere & Company, A Delaware Corporation|Agricultural automation system with field robot|
    US20100032495A1|2008-08-06|2010-02-11|Kevin Abts|Environmental and biotic-based speed management and control of mechanized irrigation systems|
    US9894849B2|2015-01-15|2018-02-20|Trimble Inc.|Prescribing a drip line for use in a field|
    US10467351B2|2015-03-13|2019-11-05|Valmont Industries, Inc.|Systems, methods and user interface for graphical configuration for field irrigation systems|
    CN105052336A|2015-07-14|2015-11-18|天津工业大学|Intelligent control system for water and fertilizer integrated drip irrigation|
    US9880537B2|2015-08-05|2018-01-30|Clearag, Inc.|Customized land surface modeling for irrigation decision support in a crop and agronomic advisory service in precision agriculture|
    WO2017085557A1|2015-11-20|2017-05-26|Societal Innovations Ipco Limited|System and method for monitoring and controlling components in an agricultural environment using configurable software platforms|CA3068773A1|2017-07-20|2019-01-24|Valmont Industries, Inc.|System and method for solid state tower control|
    US11251725B2|2017-07-20|2022-02-15|Valmont Industries, Inc.|Electronic braking system for an irrigation machine|
    US10631477B2|2017-10-30|2020-04-28|Valmont Industries, Inc.|System and method for irrigation management|
    US10827693B2|2018-02-14|2020-11-10|Deere & Company|Sprayers in a temperature inversion|
    WO2020014773A1|2018-07-16|2020-01-23|Vineland Research And Innovation Centre|Automated monitoring and irrigation of plants in a controlled growing environment|
    CN112672638A|2018-08-28|2021-04-16|瓦尔蒙特工业股份有限公司|System and method for position correction using power line carrier communication|
    US10939627B2|2018-10-11|2021-03-09|Valmont Industries, Inc.|System and method for cascading alignment of independent drive systems|
    CN109872060B|2019-02-01|2020-05-22|中国地质大学（武汉）|Method for selecting multi-satellite sensor combined observation scheme|
    EP3945784A1|2019-04-04|2022-02-09|Valmont Industries, Inc.|System and method for latching solenoid activation detection for vri and other irrigation uses|
    CN113923980A|2019-06-07|2022-01-11|瓦尔蒙特工业股份有限公司|System and method for integrated use predictive and machine learning analysis of center-pivoted irrigation systems|
    BR112021025127A2|2019-06-27|2022-01-25|Valmont Industries|System to provide variable rate application and irrigation system to provide irrigation solutions to discrete field locations|
    WO2021007363A1|2019-07-09|2021-01-14|The Texas A&M University System|Irrigation control with deep reinforcement learning and smart scheduling|
    WO2021050341A1|2019-09-12|2021-03-18|Valmont Industries, Inc.|System and method for analysis of current and voltage levels within a center pivot irrigation system|
    US20210204496A1|2020-01-08|2021-07-08|The United States Of America, As Represented By The Secretary Of Agriculture|System and method of watering crops with a variable rate irrigation system|
    CN112385524A|2020-11-17|2021-02-23|温州职业技术学院|Networking communication agricultural management system|
    法律状态:
    2021-11-03| B350| Update of information on the portal [chapter 15.35 patent gazette]|
    优先权:
    申请号 | 申请日 | 专利标题
    US201762513479P| true| 2017-06-01|2017-06-01|
    US62/513,479|2017-06-01|
    PCT/US2018/035400|WO2018222875A1|2017-06-01|2018-05-31|System and method for irrigation management using machine learning workflows|
    [返回顶部]