WO2025219787A1

WO2025219787A1 - Methods and systems for generating fertilizer prescription maps

Info

Publication number: WO2025219787A1
Application number: PCT/IB2025/053184
Authority: WO
Inventors: Kevin J Hamilton; James Kraus; Patrick Kendrick
Original assignee: AGCO Corp
Current assignee: AGCO Corp
Priority date: 2024-04-16
Filing date: 2025-03-26
Publication date: 2025-10-23
Anticipated expiration: 2026-10-16

Abstract

Technologies for generating fertilizer prescription maps (804). The technologies use a hyperspectral imaging camera (116) or a near-infrared (NIR) sensor (116) with a computing system (102) to determine the nutrient levels of a crop. The technologies can also geographically map the nutrient levels to use as a basis for generating a fertilizer prescription map (804). The computing system (102) can also use data from the mapping of nutrient levels and a corresponding yield map to generate an enhanced fertilizer prescription map (804). The system (102) can further use data from a mapping of machine operations in the field to generate the enhanced prescription map (804). Additionally, nutrient sampling data can be generated based on a chemical analysis of crop samples from different parts of the field and such data can be used by the system (102) as an input to generate the enhanced prescription map (804).

Description

METHODS AND SYSTEMS FOR GENERATING FERTILIZER PRESCRIPTION MAPS

TECHNICAL FIELD

[0001] The present disclosure relates to methods and systems for generating fertilizer prescription maps.

BACKGROUND

[0002] Precision agriculture or precision farming is a farming management model based on measuring and responding to inter and intra-field variability in crops and farming conditions. Also, tracking operational parameters of farming equipment can be applied to the farming management model. The goal of precision agriculture research is to define a decision support system (DSS) for farming management to enhance returns and increase the preservation of resources. Specifically, the precision in responses to variability in farming can be improved when known and predetermined farming information is processed and organized to enhance the information and then used to assist in the control and management of farming. Although precision farming can enhance returns and increase the preservation of resources, it can complicate farming information systems especially when tracking a great number of variables related to crop yields, crop varieties, crop quality, operational parameters of farming equipment, and farming conditions such as soil conditions and nutrient levels.

[0003] Currently, farming management information systems (FMISs) are pervasive in farming and a significant factor in furthering improvements to precision agriculture. Such information systems can track measuring and responding to inter and intra-field variability in crops, farming conditions, and farming equipment variables as well as enhance DDS for farming management. FMISs allow for new opportunities to improve farming and precision agriculture. However, even though FMISs are improving precision farming, present FMISs have limitations and can be dramatically improved upon considering relatively recent advancements in computer engineering and computer science as well as improvements in spectroscopy and sensor technology.

[0004] One significant problem with previous systems is that collecting nutrient information has relied on more traditional forms of nutrient detection and spectroscopy even though there have been many advances in sensor technology and spectroscopy in other industries. An example of advancement in spectroscopy is in the field of hyperspectral imaging. Although hyperspectral imaging has been applied in the agricultural industry, its application has been limited to a few things such as the detection of animal proteins in compound feeds to avoid disease as well as stress from heavy metals in plants.

[0005] Hyperspectral imaging advances spectroscopy by obtaining the spectrum for each pixel in an image. In general, devices that perform hyperspectral imaging include push broom scanners and whisk broom scanners that provide spatial scanning (which read images over time), band sequential scanners that provide spectral scanning (which includes capturing images of an area at different wavelengths), and snapshot hyperspectral imagers that use a staring array to generate an image immediately. Hyperspectral imaging can divide images into bands beyond the visible, and the recorded spectra can have fine wavelength resolution and cover a wide range of wavelengths such that hyperspectral imaging can measure continuous spectral bands instead of separate bands measured in more conventional forms of spectroscopy.

[0006] In general, hyperspectral sensors provide imaging using a greater portion of the electromagnetic spectrum and because of this advancement, certain objects leave unique fingerprints in the electromagnetic spectrum known as spectral signatures. The spectral signatures allow for the identification of the materials included in a scanned object and thus, specifically, could improve farming processes by facilitating the detection of materials and the extent of such materials within crops, soil, etc. Specifically, for example, improvements could be made in some of the inputs for farming management information systems and decision support systems.

SUMMARY

[0007] Described herein are systems and methods for generating fertilizer prescription maps and other types of maps related to nutrient levels and crop yield or health. In generating such maps and using hyperspectral sensors or other types of imaging to generate input for producing the maps, the disclosed systems and methods overcome some technical problems in farming. Also, the systems and methods (or techniques) disclosed herein provide specific technical solutions to at least overcome the technical problems mentioned in the background section and other parts of the application as well as other technical problems not described herein but recognized by those skilled in the art.

[0008] In providing technical solutions, in some embodiments, the systems and methods provide technologies for generating fertilizer prescription maps and other types of maps related to nutrient levels as well as crop yield or health. In generating such maps, the technologies can use hyperspectral sensors or other types of imaging to generate input for producing the maps along with geotagging the input. For example, the technologies can use a hyperspectral imaging camera or a near-infrared (NIR) sensor with a computing system to determine the nutrient levels of a crop in a crop field. The technologies can also geographically map the nutrient levels to use as a basis for generating a fertilizer prescription map. The computing system can also use data from the mapping of nutrient levels and a corresponding yield map to generate an enhanced fertilizer prescription map. The computing system can further use data from a mapping of farming machine operations in the field to generate the enhanced fertilizer prescription map. Additionally, a nutrient sampling map or nutrient sampling data can be generated based on a chemical analysis of crop samples from different parts of the field and such information can be used by the computing system as an input to generate the enhanced fertilizer prescription map.

[0009] With respect to some embodiments, disclosed herein are computerized methods for generating fertilizer prescription maps and other types of maps related to nutrient levels and crop yield or health, as well as a non-transitory computer-readable storage medium for carrying out technical operations of the computerized methods. The non- transitory computer-readable storage medium has tangibly stored thereon, or tangibly encoded thereon, computer-readable instructions that when executed by one or more devices (e.g., one or more personal computers or servers) cause at least one processor to perform a method for generating fertilizer prescription maps and other types of maps related to nutrient levels and crop yield or health.

[0010] For example, in some embodiments, a system includes an image sensor (e.g., see image sensor 116 shown in FIG. 1). In some examples, the image sensor can be or include a hyperspectral imaging camera, a NIR sensor, or a combination thereof. The image sensor is configured to capture image data of a crop. The system also includes a computing system (e.g., see computing system 102), configured to determine nutrient levels of a crop in the crop based on the captured image data or to determine nutrient removal levels of the soil of the field of the crop based on the captured image data or the determined nutrient levels. The computing system can also be configured to generate a fertilizer prescription map (e.g., see map 804 shown in FIG. 8) based on the nutrient levels or the nutrient removal levels and geographic position information associated with the nutrient levels or the nutrient removal levels. Also, the computing system can be configured to generate one or more data logs based on the nutrient levels or the nutrient removal levels and geographic position information associated with the nutrient levels or the nutrient removal levels.

[0011] Also, for example, in some embodiments, a method of or related to the system includes capturing, by an image sensor (e.g., see image sensor 116 shown in FIG. 1), image data of a crop (e.g., see step 402 shown in FIG. 4). In some examples, the image sensor can be or include a hyperspectral imaging camera, a NIR sensor, or a combination thereof. The method can also include determining, by a computing system (e.g., see computing system 102), nutrient levels of the crop based on the captured image data (e.g., see step 404).

[0012] The method can also include generating, by the computing system, a data log including the nutrient levels of the crop and geographic position information associated with the nutrient levels (e.g., see step 406). In some embodiments, the method can further include determining, by the computing system, nutrient removal levels of the soil based on the captured image data or the nutrient levels (e.g., see step 502 shown in FIG. 5). And, the method can also include generating, by the computing system, a second data log including the nutrient removal levels and the geographic position information associated with the nutrient removal levels (e.g., see step 504). In some embodiments, the method can further include generating, by the computing system, a fertilizer prescription map (e.g., see map 804 shown in FIG. 8) based on the nutrient levels, the nutrient removal levels, or a combination thereof, and the geographic position information associated with the nutrient levels or nutrient removal levels (e.g., see step 602 shown in FIG. 6).

[0013] In some embodiments, the method can further include using crop yield data, moisture data, or a combination thereof associated with the geographic position information as an additional input in the generation of the fertilizer prescription map to enhance the accuracy of the fertilizer prescription map (e.g., see step 702 shown in FIG. 7). Also, the method can include using machine operations data associated with the geographic position information as an additional input in the generation of the fertilizer prescription map to enhance the accuracy of the fertilizer prescription map (e.g., see step 704). The machine operation data can include machine ground speed data, implement position data, or a combination thereof. Also, the method can include using nutrient sampling data from a nutrient sampling, which is associated with the geographic position information, as an additional input in the generation of the fertilizer prescription map to enhance the accuracy of the fertilizer prescription map (e.g., see step 706). The nutrient sampling data can be generated based on a chemical analysis of crop samples from different positions of a crop field associated with the geographic position information.

[0014] In some examples, the image sensor is part of a farming machine (e.g., see the farming machine 106 shown in FIG. 1) moving through a field of the crop. And, the farming machine can be a combine harvester (e.g., see harvester 300 shown in FIG. 3) or any other type of mobile farming machine. In such cases and others, the method can further include recording, by a location tracking system of the farming machine, geographic position information of the farming machine while the farming machine is moving through the field. Also, the method can include linking the captured image data to the recorded geographic position information. In some embodiments, the linking of the captured image data to the recorded geographic position information includes geotagging images of the captured image data.

[0015] These and other important aspects of the invention are described more fully in the detailed description below. The invention is not limited to the particular methods and systems described herein. Other embodiments can be used and changes to the described embodiments can be made without departing from the scope of the claims that follow the detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present disclosure will be understood more fully from the detailed description given below and from the accompanying drawings of various embodiments of the disclosure.

[0017] FIG. 1 illustrates an example network of farming machines with each farming machine having sensors that communicate with a local or a remote computing system through a communications network to provide input for FMIS map generation, in accordance with some embodiments of the present disclosure. [0018] FIG. 2 illustrates a block diagram of example aspects of the computing system shown in FIG. 1 , in accordance with some embodiments of the present disclosure.

[0019] FIGS. 3 illustrates a schematic side view of a farming machine, such as one of the farming machines shown in FIG. 1 , with some portions of the farming machine being broken away to reveal some internal details of construction, in accordance with some embodiments of the present disclosure.

[0020] FIGS. 4 to 7 illustrate example methods in accordance with some embodiments of the present disclosure.

[0021] FIG. 8 illustrates an example fertilizer prescription map, in accordance with some embodiments of the present disclosure.

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0022] Details of example embodiments of the invention are described in the following detailed description with reference to the drawings. Although the detailed description provides reference to example embodiments, it is to be understood that the invention disclosed herein is not limited to such example embodiments. But to the contrary, the invention disclosed herein includes numerous alternatives, modifications and equivalents as will become apparent from consideration of the following detailed description and other parts of this disclosure.

[0023] FIG. 1 illustrates network 100 including at least one computing system (e.g., see computing system 102), a communications network 104, and farming machines, e.g., see farming machines 106, 107, and 108. As shown, a farming machine of the network 100 includes sensors (e.g., see sensors 116, 117, and 118). A sensor of the network (e.g., see sensors 116, 117, and 118) is configured to communicate with a local or a remote computing system (e.g., see computing system 102) through a communications network (e.g., see communications network 104). Also, in some embodiments, the farming machines of the network 100 include a processor, memory, a communication interface, and one or more sensors that make the farming machines individual computing devices. In the case of the communications network 104 including the Internet, the farming machines 106, 107, and 108 are considered Internet of Things (loT) devices.

[0024] The network 100 includes various types of sensors (e.g., see sensors 116, 117, and 118). The sensors can include hyperspectral imaging camera, a NIR sensor, or a combination thereof, for example. Also, the sensors can include any type of imaging sensor or camera — depending on the embodiment or situation. The sensors can also include position sensors, linear displacement sensors, angular displacement sensors, pressure sensors, load cells, or any sensor useable to sense a metric or force exerted by a farming machine. Also, the sensors can include various types of sensors for detecting moisture, weight, density, or flow rate of a crop or a bale.

[0025] The network 100 also includes farming machines which can be various types of farming machines (e.g., see farming machines 106, 107, and 108). In some embodiments, the farming machine (e.g., see farming machine 106, 108, or 110) includes a vehicle. In some embodiments, the farming machine is a combine harvester. In some embodiments, the farming machine is a tractor. In some embodiments, the farming machine is a planter. In some embodiments, the farming machine is a sprayer. In some embodiments, the farming machine is a baler. In some embodiments, the farming machine is or includes a harvester, a planter, a sprayer, a baler, any other type of farming implement, or any combination thereof. In such embodiments, the farming machine can be or include a vehicle in that it is self-propelling. Also, in some embodiments, the group of similar farming machines is a group of vehicles (e.g., see farming machines 106, 108, and 110). In some embodiments, the group of vehicles is a group of combine harvesters. And, in some embodiments, the group of vehicles is a group of combine harvesters, planters, sprayers, balers, another type of implement, or any combination thereof.

[0026] For example, in some embodiments, a system includes an image sensor (e.g., see image sensor 116 shown in FIG. 1 ). The image sensor can be or include a hyperspectral imaging camera, a NIR sensor, or a combination thereof. The image sensor is configured to capture image data of a crop. The system also includes a computing system (e.g., see computing system 102), configured to determine nutrient levels of a crop in the crop based on the captured image data or to determine nutrient removal levels of the soil of the field of the crop based on the captured image data or the determined nutrient levels. The computing system can also be configured to generate a fertilizer prescription map (e.g., see map 804 shown in FIG. 8) based on the nutrient levels or the nutrient removal levels and geographic position information associated with the nutrient levels or the nutrient removal levels. Also, the computing system can also be configured to generate one or more data logs based on the nutrient levels or the nutrient removal levels and geographic position information associated with the nutrient levels or the nutrient removal levels.

[0027] In some embodiments, the capturing of the inputs of the technical solutions (such as the capturing of the nutrient levels in crops or soil) is performed by various types of image sensors and cameras attached to farming machines. And, the mapping of various farming machine operations can also be included in the inputs of the technical solutions. For example, the inputs can include farming machine operations variables, attributes, and parameters. The farming machines can include harvesters (such as combine or forage harvesters) as well as any other types of farming machine including mobile farming machines such as tractors, planters, sprayers, balers, or any type of farming implement of a mobile machine, or any combination thereof.

[0028] Some embodiments include capturing the inputs while hay harvesting using a spectral camera, whereas in other examples a near-infrared (NIR) image sensor can be used and is usually attached to combine and forage harvesters. In some instances, a spectral camera generates an image where each pixel in the image has a reflectance or absorption value. In some other cases or in addition to spectral camera images, an NIR image sensor generates a single reflectance or absorption value. The image sensors of the technical solutions can look ahead at the crop or the field in general in front of the farming machine, and can also capture images after gathering or harvesting crop, such as during processing or holding of the crop within the farming machine.

[0029] In some embodiments, crop nutrient data is represented as a parts per million (PPM) value for each selected mineral that is tracked, and the computing system can use that value with a mass of crop being taken off the field to generate a mass of each selected nutrient or mineral for tracking and generation of FMIS maps. Also, yield sensors can be used to generate a dry yield, a wet yield and a moisture map. The dry yield can be determined by adjusting the wet yield according to the measured moisture level. The dry yield represents mass of harvested crop per area, so the amount of nutrients harvested from the field can be calculated using the PPM values determined from the captured inputs of the image sensors and the yield information from the yield sensor. This can be done readily with embodiments using image sensors of harvesters since harvesters usually have a yield sensor. Other types of farming machines that do not typically include a yield sensor can also be used using sensors to capture other operations parameters such as flow information. For example, harvested crop mass flow with moisture level and with dry mass flow rate can be used to determine nutrient levels. Also, dry mass flow rate with PPM nutrient values can be used as inputs to determine an amount of nutrients taken from the ground.

[0030] For example, yield sensors, already determining mass of harvested crop per area, can be used with an NIR sensor or a spectral camera to detect PPM values in the harvested crop. Also, dry mass flow can be determined by the yield sensor. And, using other operations attributes or parameters, such as using the ground speed of the farming machine or swath width to determine bushels per acre additional information can be determined such as the mass of a nutrient in the crop or taken out of the ground per acre or some other selected area of a crop field.

[0031] The communications network 104 includes one or more local area networks (LAN(s)) or one or more wide area networks (WAN(s)). In some embodiments, the communications network 104 includes the Internet or any other type of interconnected communications network. In some embodiments, the communications network 104 includes a single computer network or a telecommunications network. In some embodiments, the communications network 104 includes a local area network (LAN) such as a private computer network that connects computers in small physical areas, a wide area network (WAN) to connect computers located in different geographical locations, or a middle area network (MAN) to connect computers in a geographic area larger than that covered by a large LAN but smaller than the area covered by a WAN.

[0032] At least each shown component of the network 100 (including computing system 102, communications network 104, and farming machines 106, 107, and 108) is or includes or is connected to a computing system that includes memory that includes media. The media includes volatile memory components, non-volatile memory components, or a combination thereof. In general, each of the computing systems includes a host system that uses memory. For example, the host system writes data to the memory and reads data from the memory. The host system is a computing device that includes a memory and a data processing device. The host system includes or is coupled to the memory so that the host system reads data from or writes data to the memory. The host system is coupled to the memory via a physical host interface. The physical host interface provides an interface for passing control, address, data, and other signals between the memory and the host system.

[0033] FIG. 2 shows a block diagram of example aspects of the computing system 102. FIG. 2 illustrates parts of the computing system 102 within which a set of instructions, for causing the machine to perform any one or more of the methodologies discussed herein, are executed. In some embodiments, the computing system 102 corresponds to a host system that includes, is coupled to, or utilizes memory or is used to perform the operations performed by any one of the computing devices, data processors, user interface devices, and sensors described herein. In alternative embodiments, the machine is connected (e.g., networked) to other machines in a LAN, an intranet, an extranet, or the Internet. In some embodiments, the machine operates in the capacity of a server or a client machine in a client-server network environment, as a peer machine in a peer-to-peer (or distributed) network environment, or as a server or a client machine in a cloud computing infrastructure or environment. In some embodiments, the machine is a personal computer (PC), a tablet PC, a set-top box (STB), a Personal Digital Assistant (PDA), a cellular telephone, a web appliance, a server, a network router, a switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while a single machine is illustrated, the term “machine” shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.

[0034] The computing system 102 includes a processing device 202, a main memory 204 (e.g., read-only memory (ROM), flash memory, dynamic random-access memory (DRAM), etc.), a static memory 206 (e.g., flash memory, static random-access memory (SRAM), etc.), and a data storage system 210, which communicate with each other via a bus 230.

[0035] The processing device 202 represents one or more general-purpose processing devices such as a microprocessor, a central processing unit, or the like. More particularly, the processing device is a microprocessor or a processor implementing other instruction sets, or processors implementing a combination of instruction sets. Or, the processing device 202 is one or more special-purpose processing devices such as an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), a network processor, or the like. The processing device 202 is configured to execute instructions 214 for performing the operations discussed herein. In some embodiments, the computing system 102 includes a network interface device 208 to communicate over the communications network 104 shown in FIG. 1.

[0036] The data storage system 210 includes a machine-readable storage medium 212 (also known as a computer-readable medium) on which is stored one or more sets of instructions 214 or software embodying any one or more of the methodologies or functions described herein. The instructions 214 also reside, completely or at least partially, within the main memory 204 or within the processing device 202 during execution thereof by the computing system 102, the main memory 204 and the processing device 202 also constituting machine-readable storage media.

[0037] In some embodiments, the instructions 214 include instructions to implement functionality corresponding to any one of the computing devices, data processors, user interface devices, I/O devices, and sensors described herein. While the machine- readable storage medium 212 is shown in an example embodiment to be a single medium, the term “machine-readable storage medium” should be taken to include a single medium or multiple media that store the one or more sets of instructions. The term “machine-readable storage medium” shall also be taken to include any medium that is capable of storing or encoding a set of instructions for execution by the machine and that causes the machine to perform any one or more of the methodologies of the present disclosure. The term “machine-readable storage medium” shall accordingly be taken to include, but not be limited to, solid-state memories, optical media, and magnetic media.

[0038] Also, as shown, computing system 102 includes user interface 220 that includes a display, in some embodiments, and, for example, implements functionality corresponding to any one of the user interface devices disclosed herein. A user interface, such as user interface 220, or a user interface device described herein includes any space or equipment where interactions between humans and machines occur. A user interface described herein allows operation and control of the machine from a human user, while the machine simultaneously provides feedback information to the user. Examples of a user interface (Ul), or user interface device include the interactive aspects of computer operating systems (such as graphical user interfaces), machinery operator controls, and process controls. A Ul described herein includes one or more layers, including a human-machine interface (HMI) that interfaces machines with physical input hardware. In some embodiments, such a Ul also includes a device that implements an HMI — also known as a human interface device (HID). In some examples, Ul described herein include tactile Ul (touch), visual Ul (sight), auditory Ul (sound), etc. In some embodiments, a graphical user interface (GUI), which is composed of a tactile Ul and a visual Ul capable of displaying graphics, or any other type of Ul presents information to a user of the system related to systems and methods for generating fertilizer prescription maps and other types of maps related to nutrient levels and crop yield or health.

[0039] FIG. 3 illustrates a schematic side view of a combine harvester 300 (which can be one of the farming machines shown in FIG. 1) with some portions of the harvester being broken away to reveal internal details of construction. Although FIG. 3 and some other parts of the disclosure describe the technologies disclosed herein as being a part of or connected to a combine harvester, it is to be understood that similar or analogous technologies can be a part of or connected to other types of harvesters (such as combine or forage harvesters) and other types of farming machines (such as tractors, planters, sprayers, balers, any type of farming implement of a mobile machine, or any combination thereof).

[0040] Some embodiments of a farming machine described herein include the combine harvester 300 or any other type of harvester. It is to be understood that, in general, any of the farming machines described herein can also include mechanical and operational parts to the level of specificity as provided herein for the harvester 300. However, for the sake of conciseness, such specificity may not be provided for all of the types of farming machines described herein. Further, it is to be understood that the sensed or captured parameters of crop fields, crops, and farming machines described herein with respect to the methods and systems disclosed herein can include the sensed and captured parameters of the harvester 300 or any other type of farming machine described herein.

[0041] As shown in FIG. 3, the combine harvester 300 includes at least two image sensors (e.g., see sensors 390 and 392). The at least two image sensors can include one or more hyperspectral imaging cameras or one or more near-infrared (NIR) sensors, or any other combination thereof. The at least two image sensors include a first image sensor 390 mounted to the harvester 300 at a front end of the harvester. The first image sensor 390 is configured to capture images of the crop while the crop is being harvested or just before the crop is harvested. The at least two image sensors also include a second image sensor 392 mounted to the combine harvester 300 in a crop processing section of the harvester. For example, the second image sensor 392 is mounted near the clean grain auger 332 that delivers the clean grain to an elevator (not shown) that elevates the grain to a storage bin 334 on top of the combine harvester 300, from which it is ultimately unloaded via an unloading spout 336. The second image sensor 392 is configured to capture images of the crop after the crop has been harvested. Also, in some instances, such as the one shown in FIG. 3, the second image sensor 392 is configured to capture images of the crop after the crop has been processed to at least some extent by the combine harvester 300.

[0042] It is to be understood that the image sensors of the harvester 300 (e.g., see image sensors 390 and 392) are positioned near various parts of the harvester (whether it is a combine harvester or a forage harvester) to capture images of the crop as it is harvested or processed or to capture images of operating parts of the harvester. And, it is to be further understood that the captured images described with respect to the methods and systems described herein can include such images. Also, although the description of FIG. 3 and some other parts of the disclosure describe the image sensors of a harvester and the images they capture, it is to be understood that similar or analogous sensors can be a part of or connected to other types of farming machines (such as tractors, planters, sprayers, balers, etc.) and can capture similar or analogous images. And, it is to be further understood that the captured images described with respect to the methods and systems described herein can include such similar or analogous images captured by images sensors that are a part of or connected to other types of farming machines besides harvesters.

[0043] Also, the combine harvester 300 has processing system 312 that extends generally parallel with the path of travel of the harvester. It is to be understood that such a harvester is being used to illustrate principals herein and the subject matter described herein is not limited to harvesters with processing systems designed for axial flow, nor to axial flow harvesters having only a single processing system. The combine harvester 300 also includes a harvesting header (not shown) at the front of the machine that delivers collected crop materials to the front end of a feeder house 314. Such materials are moved upwardly and rearwardly within feeder house 314 by a conveyor 316 until reaching a beater 318 that rotates about a transverse axis. Beater 318 feeds the material upwardly and rearwardly to a rotary processing device, in the illustrated instance to a rotor 322 having an infeed auger 320 on the front end thereof. Infeed auger 320, in turn, advances the materials axially into the processing system 312 for threshing and separating. The processing system 312 is housed by processing system housing 313. In other types of systems, conveyor 316 may deliver the crop directly to a threshing cylinder. The crop materials entering processing system 312 can move axially and helically therethrough during threshing and separating. During such travel, the crop materials are threshed and separated by rotor 322 operating in chamber 323 which concentrically receives the rotor 322. The lower part of the chamber 323 contains concave assembly 324 and a separator grate assembly 326. Rotation of the rotor 322 impels the crop material rearwardly in a generally helical direction about the rotor 322. A plurality of rasp bars and separator bars (not shown) mounted on the cylindrical surface of the rotor 322 cooperate with the concave assembly 324 and separator grate assembly 326 to thresh and separate the crop material, with the grain escaping laterally through concave assembly 324 and separator grate assembly 326 into cleaning mechanism 328. Bulkier stalk and leaf materials are retained by the concave assembly 324 and the separator grate assembly 326 and are impelled out the rear of processing system 312 and ultimately out of the rear of the combine harvester 300. A blower 330 forms part of the cleaning mechanism 328 and provides a stream of air throughout the cleaning region below processing system 312 and directed out the rear of the combine harvester 300 so as to carry lighter chaff particles away from the grain as it migrates downwardly toward the bottom of the machine to a clean grain auger 332. Since the grain is cleaned by the blower 330 by the time it reaches the auger 332, in some embodiments the image sensor for capturing images of the crop is mounted near the auger 332 facing a section that conveys the cleaned grain (e.g. , see image sensor 304). Clean grain auger 332 delivers the clean grain to an elevator (not shown) that elevates the grain to a storage bin 334 on top of the combine harvester 300, from which it is ultimately unloaded via an unloading spout 336. A returns auger 337 at the bottom of the cleaning region is operable in cooperation with other mechanism (not shown) to reintroduce partially threshed crop materials into the front of processing system 312 for an additional pass through the processing system 312. It is to be understood that the image sensors of the harvester 300 (e.g., see image sensors 390 and 392) are positioned near such parts of the harvester (such as near parts of the processing system 312) to capture images of the crop as it is harvested or processed or to capture images of such parts of the harvester. And, it is to be further understood that the captured images described with respect to the methods and systems described herein can include such images.

[0044] Also, in some embodiments, the sensed or captured parameters of crop fields, crops, and farming machines described herein with respect to the methods and systems described herein, such as the sensed parameters and data captured by the sensors of the harvester 300, are stored via an on-board memory or the like for later transmission to a farm management information system (FMIS) or similar software package. In other embodiments, the data or information is wirelessly transmitted to a remote personal computer, server, or other suitable device for later review and use by the grower using the FMIS or similar. For example, the sensor data is used to create a fertilizer prescription map or other graphical display, providing the grower with agronomic data for making future planting or treatment decisions for a given field (e.g., see FIG. 8). As mentioned, in some examples, the informational output is displayed to a user via a Ul to enhance farming operations manually or is used as feedback information to the controller so that the controller automatically enhances farming operations with or without manual input depending on the embodiment.

[0045] FIGS. 4 to 7 illustrate methods 400, 500, 600, and 700, respectively, in accordance with some embodiments of the present disclosure. [0046] Method 400 starts with step 402, which includes capturing, by an image sensor (e.g., see sensors 116, 117, and 118 shown in FIG. 1 and image sensors 390 and 392 shown in FIG. 3), image data of a crop. The crop can be harvested crop, processed crop, or crop in a crop field, for example. In some embodiments, the image sensor is part of a farming machine (e.g., see machine 106 depicted in FIG. 1 or harvester 300 shown in FIG. 3) moving through a field where the crop is harvested. In some embodiments, such as when forage crops are being harvested, a remote system separate from the harvester itself can provide the spectral data and estimations of PPM nutrient concentrations to be combined with farming machine yield data. In some embodiments, the image sensor includes a hyperspectral imaging camera. In some embodiments, the image sensor includes a near-infrared (NIR) sensor. In some cases, the image sensor includes both a hyperspectral imaging camera and a NIR sensor.

[0047] At step 404, the method 400 continues with determining, by a computing system (e.g., see computing system 102 shown in FIGS. 1 and 2), nutrient levels of the crop based on the captured image data. In some embodiments, the capturing of the image data includes capturing, by the NIR sensor, NIR image data of the crop field and capturing, by the hyperspectral imaging camera, spectral image data of the crop field. And, in such examples, the determining of the nutrient levels of the crop is based on the NIR image data and the spectral image data.

[0048] Although not depicted, the method 400 and other methods described herein can include recording, by a location tracking system of the farming machine, geographic position information of the farming machine while the farming machine is moving through the field as well as linking the captured image data to the recorded geographic position information.

[0049] At step 406, the method continues with generating, by the computing system, a data log including the nutrient levels of the crop and geographic position information associated with the nutrient levels. Not shown, the method can also include the capturing of geographic position information by a corresponding geographic positioning system of the harvester and then associating the geographic position information with the captured image data (such as via geotagging of images). And, subsequently, the method can include associating the nutrient levels, derived from the captured image data, with the geographic position information. Further, the method 400 and other methods described herein can include recording, by a location tracking system of the farming machine, geographic position information of the farming machine while the farming machine is moving through the field as well as linking the captured image data to the recorded geographic position information. In some embodiments, the linking of the captured image data to the recorded geographic position information includes geotagging images of the captured image data.

[0050] In some embodiments, the method 400 can include capturing, by a hyperspectral imaging camera, image data of a crop field (at step 402). And, the method 400 can include determining, by a computing system, nutrient levels of a crop in the crop field based on the captured image data captured by the hyperspectral imaging camera (at step 404). Furthermore, the method 400 can include generating, by the computing system, a fertilizer prescription map based on the nutrient levels of a crop in the crop field and geographic position information associated with the nutrient levels that were derived from the images captured by the hyperspectral imaging camera (at step 406).

[0051] Method 500 starts with step 402 too, which includes capturing, by an image sensor (e.g., see sensors 116, 117, and 118 shown in FIG. 1 and image sensors 390 and 392 shown in FIG. 3), image data of a crop. Also, method 500 can include steps 404 and 406 or not, depending on the embodiment. FIG. 5 shows the embodiment where steps 404 and 406 are included in the method 500, which includes determining, by a computing system (e.g., see computing system 102 shown in FIGS. 1 and 2), nutrient levels of the crop based on the captured image data and generating, by the computing system, a data log including the nutrient levels of the crop and geographic position information associated with the nutrient levels, respectively. Method 500 also continues with step 502, which includes determining, by the computing system, nutrient removal levels of soil based on the captured image data or the determined nutrient levels. And, at step 504, the method 500 also includes generating, by the computing system, a second data log including the nutrient removal levels and the geographic position information associated with the nutrient removal levels. Similarly, and not shown, the method can also include the capturing of geographic position information by a corresponding geographic positioning system of the harvester and then associating the geographic position information with the captured image data (such as via geotagging of images). And, subsequently, the method can include associating the nutrient removal levels, derived from the captured image data or the determined nutrient levels, with the geographic position information.

[0052] Method 600 starts with step 402 too, which includes capturing, by an image sensor (e.g., see sensors 116, 117, and 118 shown in FIG. 1 and image sensors 390 and 392 shown in FIG. 3), image data of a crop. Also, method 600 can include steps 404 and 406 or not, depending on the embodiment. FIG. 6 shows the embodiment where steps 404 and 406 are included in the method 600, which includes determining, by a computing system (e.g., see computing system 102 shown in FIGS. 1 and 2), nutrient levels of the crop based on the captured image data and generating, by the computing system, a data log including the nutrient levels of the crop and geographic position information associated with the nutrient levels, respectively. Also, method 600 can continue with step 502, which includes determining, by the computing system, nutrient removal levels of the soil based on the captured image data or the determined nutrient levels. And, the method 600 can include step 504 that includes generating, by the computing system, a second data log including the nutrient removal levels and the geographic position information associated with the nutrient removal levels. Additionally, method 600 includes, at step 602, generating, by the computing system, a fertilizer prescription map based on the nutrient levels of the crop, the nutrient removal levels, or a combination thereof and the geographic position information associated with the determined nutrient levels or the nutrient removal levels.

[0053] Method 700 starts with step 402 as well, which includes capturing, by an image sensor (e.g., see sensors 116, 117, and 118 shown in FIG. 1 and image sensors 390 and 392 shown in FIG. 3), image data of a crop. Also, method 700 can include steps 404 and 406 or not, depending on the embodiment. FIG. 7 shows the embodiment where steps 404 and 406 are included in the method 700, which includes determining, by a computing system (e.g., see computing system 102 shown in FIGS. 1 and 2), nutrient levels of the crop based on the captured image data and generating, by the computing system, a data log including the nutrient levels of the crop and geographic position information associated with the nutrient levels, respectively. Also, method 700 includes step 502 where the computing system determines nutrient removal levels of the soil based on the captured image data or the determined nutrient levels. And, the method 700 includes step 504 that includes generating, by the computing system, a second data log including the nutrient removal levels and the geographic position information associated with the nutrient removal levels. The first and second logs can be part of the same master data log.

[0054] Additionally, method 700 includes, at step 702, using, by the computing system, crop yield data, moisture data, or a combination thereof associated with the geographic position information as an additional input in the generation of the fertilizer prescription map to enhance the accuracy of the fertilizer prescription map. In some embodiments, the crop yield data includes mass flow data of harvested grain or includes or is derived from a yield map. Also, the moisture data can be used to determine dry mass information and the dry mass information can be used, by the computing system, as an additional input in the generation of the fertilizer prescription map to enhance the accuracy of the fertilizer prescription map. Additionally, method 700 includes, at step 704, using, by the computing system, machine operations data associated with the geographic position information as an additional input in the generation of the fertilizer prescription map to enhance the accuracy of the fertilizer prescription map. In some embodiments, the machine operation data includes machine ground speed data. In some embodiments, the machine operation data includes implement position data. Additionally, method 700 includes, at step 706, using, by the computing system, nutrient sampling data from a nutrient sampling, which is associated with the geographic position information, as an additional input in the generation of the fertilizer prescription map to enhance the accuracy of the fertilizer prescription map, wherein the nutrient sampling data is generated based on a chemical analysis of crop samples from different parts of the field. Also, method 700 includes, at step 708, generating, by the computing system, a fertilizer prescription map based on the determined nutrient levels of the crop or the nutrient removal levels of the soil and the crop yield data, the moisture data, the machine operations data, the nutrient sampling data, or any combination thereof and the geographic position information associated with the determined nutrient levels or the nutrient removal levels. In some embodiments, the sampling data can include tissue test data that can be processed via a computing system within the corresponding sensor package. And, in some examples, the computing system can combine other data layers from other sources of related agricultural and farming information. Example data layers can include information from soil samples, historical yields, yield goals, soil texture, cation exchange capacity (CEC), etc. Also, in some examples, the data and information used as a basis for generating the map can be used, by the computing system, to directly display the data or information to an operator of a farming machine (e.g., see machine 106 depicted in FIG. 1 or harvester 300 shown in FIG. 3) via a Ul or recorded to a task controller, such as recorded to a master log on a controller (e.g., see the user interface 220 shown in FIG. 2).

[0055] In some embodiments, the capturing of the inputs of the technical solutions (such as the capturing of the nutrient levels in crops or soil) is performed by various types of image sensors and cameras attached to farming machines. And, the mapping of various farming machine operations can also be included in the inputs of the technical solutions. For example, the inputs can include farming machine operations variables, attributes, and parameters. The farming machines can include harvesters (such as combine or forage harvesters) as well as any other types of farming machines including mobile farming machines such as tractors, planters, sprayers, balers, etc. Some embodiments include capturing the inputs while hay harvesting using a spectral camera, whereas in other examples a near-infrared (NIR) image sensor can be used and is usually attached to combine and forage harvesters. In some instances, a spectral camera generates an image where each pixel in the image has a reflectance or absorption value. In some other cases or in addition to spectral camera images, an NIR image sensor generates a single reflectance or absorption value. The image sensors of the technical solutions can look ahead at the crop or the field in general in front of the farming machine, and can also capture images after gathering or harvesting crop, such as during processing or holding of the crop within the farming machine.

[0056] In some embodiments, crop nutrient data is represented as a parts per million (PPM) value for each selected mineral that is tracked, and the computing system can use that value with a mass of crop being taken off the field to generate a mass of each selected nutrient or mineral for tracking and generation of FMIS maps. Also, yield sensors can be used to generate a dry yield, a wet yield and a moisture map. The dry yield can be determined by adjusting the wet yield according to the measured moisture level. The dry yield represents mass of harvested crop per area, so the amount of nutrients harvested from the field can be calculated using the PPM values determined from the captured inputs of the image sensors and the yield information from the yield sensor. This can be done readily with embodiments using image sensors of harvesters since harvesters usually have a yield sensor. Other types of farming machines that do not typically include a yield sensor can also be used using sensors to capture other operations parameters such as flow information. For example, harvested crop mass flow with moisture level and with dry mass flow rate can be used to determine nutrient levels. Also, dry mass flow rate with PPM nutrient values can be used as inputs to determine an amount of nutrients taken from the ground.

[0057] For example, yield sensors, already determining mass of harvested crop per area, can be used with an NIR sensor or a spectral camera to detect PPM values in the harvested crop. Also, dry mass flow can be determined by the yield sensor. And, using other operations attributes or parameters, such as using the ground speed of the farming machine or swath width to determine bushels per acre additional information can be determined such as the mass of a nutrient in the crop or taken out of the ground per acre or some other selected area of a crop field. [0058] FIG. 8 illustrates an example fertilizer prescription map 804, in accordance with some embodiments of the present disclosure. As shown in FIG. 8, fertilizer prescription map 804 shows various levels of fertilizer to apply to a crop field for respective locations within the field, which are defined by sectors and labeled with sector identification numbers in the map 804. Each respective labeled location or sector in the map is associated with a corresponding sector identification (e.g., see sectors 806 and 808 which are identified as having “SECTOR ID 111540” and “SECTOR ID 111562” respectively). This is important because being able to identify a fertilizer prescription level per sector or area of a crop field provides a significant agronomic value. In some embodiments, although not depicted, the map 804 is combined with another type of FMIS map, such as a soil moisture map, a yield map from a previous date, or a map showing depletion of nutrients from the ground. The advantage of such a combination is that it provides additional information on the possible factors for the determined fertilizer prescription level. In some examples, the prescription map 804 is combined with one or more different types of agriculture informational maps such as an average ground speed map, a plunger load map, a stuffer geometry map, or a mapping of another operations parameter, or a topographical map, a soil quality map, a soil moisture map, a soil pH-level map, or a crop or carbon density map, just a name some examples. Such combined maps are then useable to analyze a crop, bales, and a field and possibly improve farming practices.

[0059] FIG. 8 illustrates display 802 of user interface device 800 (e.g., see the user interface 220 shown in FIG. 2). The display 802 is shown displaying the prescription map 804. The map 804 provides determined fertilizer prescription levels associated with different locations or sectors of a crop field. As shown in FIG. 8, each sector of the prescription map 804 includes a respective sector identification number and a fertilizer prescription level. The values and ranges of a level can vary greatly depending on the embodiment and the type of field and other conditions. For example, the “LEVEL F1”, as shown in sector 806, can represent a prescription level of 250 N kg/ha. In such an example, the “LEVEL F2” can represent a prescription level of 500 N kg/ha, and the “LEVEL F3” can represent a prescription level of 750 N kg/ha. And, the “LEVEL F4”, as shown in sector 808, can represent a prescription level of 1000 N kg/ha.

[0060] Some portions of the preceding detailed descriptions have been presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the ways used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of operations leading to a predetermined result. The operations are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like. It should be borne in mind, however, that these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. The present disclosure can refer to the action and processes of a computing system, or similar electronic computing device, which manipulates and transforms data represented as physical (electronic) quantities within the computing system's registers and memories into other data similarly represented as physical quantities within the computing system memories or registers or other such information storage systems.

[0061] While the invention has been described in conjunction with the specific embodiments described herein, it is evident that many alternatives, combinations, modifications, and variations are apparent to those skilled in the art. Accordingly, the example embodiments of the invention, as set forth herein are intended to be illustrative only, and not in a limiting sense. Various changes can be made without departing from the spirit and scope of the invention.

Claims

CLAIMS What is claimed is:

1. A method, comprising: capturing, by an image sensor (116), image data of a crop (step 402); determining, by a computing system (102), nutrient levels of the crop based on the captured image data (step 404); and generating, by the computing system (102), a data log including the nutrient levels of the crop and geographic position information associated with the nutrient levels (step 406).

2. The method of claim 1 , further comprising: determining, by the computing system (102), nutrient removal levels of the soil based on the captured image data or the nutrient levels (step 502); and generating, by the computing system (102), a second data log including the nutrient removal levels and the geographic position information associated with the nutrient removal levels (step 504).

3. The method of claim 2, further comprising generating, by the computing system (102), a fertilizer prescription map (804) based on the nutrient levels, the nutrient removal levels, or a combination thereof, and the geographic position information associated with the nutrient levels or nutrient removal levels (step 602).

4. The method of claim 3, further comprising using crop yield data, moisture data, or a combination thereof associated with the geographic position information as an additional input in the generation of the fertilizer prescription map (804) to enhance the accuracy of the fertilizer prescription map (step 702).

5. The method of claim 3, further comprising using machine operations data associated with the geographic position information as an additional input in the generation of the fertilizer prescription map (804) to enhance the accuracy of the fertilizer prescription map (step 704).

6. The method of claim 3, further comprising using nutrient sampling data from a nutrient sampling, which is associated with the geographic position information, as an additional input in the generation of the fertilizer prescription map (804) to enhance the accuracy of the fertilizer prescription map (step 706), wherein the nutrient sampling data is generated based on a chemical analysis of crop samples from different positions of a crop field associated with the geographic position information.

7. The method of claim 1 , further comprising generating, by the computing system (102), a fertilizer prescription map (804) based on the nutrient levels of the crop and the geographic position information associated with the nutrient levels (step 602).

8. The method of claim 7, further comprising using crop yield data, moisture data, or a combination thereof associated with the geographic position information as an additional input in the generation of the fertilizer prescription map (804) to enhance the accuracy of the fertilizer prescription map (step 702).

9. The method of claim 7, further comprising using machine operations data associated with the geographic position information as an additional input in the generation of the fertilizer prescription map (804) to enhance the accuracy of the fertilizer prescription map (step 704).

10. The method of claim 5 or 9, wherein the machine operation data comprises machine ground speed data, implement position data, or a combination thereof.

11. The method of claim 7, further comprising using nutrient sampling data from a nutrient sampling, which is associated with the geographic position information, as an additional input in the generation of the fertilizer prescription map (804) to enhance the accuracy of the fertilizer prescription map (step 706), wherein the nutrient sampling data is generated based on a chemical analysis of crop samples from different positions of a crop field associated with the geographic position information.

12. The method of claim 1 , wherein the image sensor (116) comprises a hyperspectral imaging camera.

13. The method of claim 1 or 12, wherein the image sensor (116) comprises a nearinfrared (NIR) sensor.

14. The method of claim 1 , wherein the image sensor (116) is part of a farming machine (106) moving through a field of the crop.

15. The method of claim 14, wherein the farming machine is a combine harvester (300).

16. The method of claim 14, further comprising: recording, by a location tracking system of the farming machine (106), geographic position information of the farming machine while the farming machine is moving through the field; and linking the captured image data to the recorded geographic position information.

17. The method of claim 16, wherein the linking of the captured image data to the recorded geographic position information comprises geotagging images of the captured image data.

18. A method, comprising: capturing, by a hyperspectral imaging camera (116), image data of a crop; determining, by a computing system (102), nutrient levels of a crop in the crop based on the captured image data; and generating, by the computing system (102), a fertilizer prescription map (804) based on the nutrient levels and geographic position information associated with the nutrient levels.

19. The method of claim 18, further comprising using crop yield data associated with the geographic position information as an additional input in the generation of the fertilizer prescription map (804) to enhance the accuracy of the fertilizer prescription map.

20. A system, comprising: a hyperspectral imaging camera (116) configured to capture image data of a crop; and a computing system (102), configured to: determine nutrient levels of a crop in the crop based on the captured image data; and generate a fertilizer prescription map (804) based on the nutrient levels and geographic position information associated with the nutrient levels.