Method for providing herbicide application data to control herbicide product application equipment

Abstract

1. A computer-implemented method for providing control data for an application device to apply a herbicide product to a field, the method comprising the steps of: providing image data of the field; providing a weed classification model configured to provide weed data based on the image data of the field; providing weed data for the field based on the weed classification model and the image data; providing a weed growth model configured to provide weed inci- dence data and / or weed growth data for the field based on the weed data of the field; providing weed inci- dence data and / or weed growth data for the field based on the weed growth model and the weed data of the field; and providing herbicide application data based on the weed inci- dence data and / or weed growth data, the herbicide application data including at least application timing data for at least one herbicide product for application to the field.

Description

[Technical Field]

[0001] The present disclosure relates to computer-implemented methods for providing herbicide application data for applying a herbicide product to a field, application devices for applying a herbicide product to a field, systems for providing herbicide application data for applying a herbicide product to a field, and the use of image data, weed data, weed occurrence data, and / or weed growth data in such computer-implemented methods and respective computer program elements. [Background technology]

[0002] The general background of this disclosure is field management, which includes the management of fields, greenhouses, etc. with herbicides to control unwanted weed plants.

[0003] In typical agricultural practice, herbicide products are applied to agricultural fields based on the farmer's experience, expertise, and knowledge to interpret, for example, weed species, weed infestation, weather parameters, etc., to make a decision on whether to apply the herbicide product, where one of the key challenges is often determining the optimal time to apply the herbicide product. Summary of the Invention [Problem to be solved by the invention]

[0004] It has been recognized that there is a need to provide a method that provides robust and accurate information regarding the timing of application of herbicide products to a field.

[0005] In view of the above, it is an object of the present invention to provide a method for determining the optimal timing of herbicide application. In view of the above, it is an object of the present invention to provide a method for determining the optimal dosage of herbicide application. In view of the above, it is an object of the present invention to provide an optimal herbicide application map for use in a herbicide application device. In view of the above, it is an object of the present invention to provide an accurate and easy-to-use method for generating control data for a herbicide application device that has real-world effects, in particular based on existing image data and / or existing models. These and other objects will become apparent on reading the following description and are solved by the subject matter of the independent claims. The dependent claims refer to preferred embodiments of the invention. [Means for solving the problem]

[0006] Aspects of the present disclosure relate to a computer-implemented method for providing control data for an application device for applying a herbicide product to a field, the method comprising: providing image data of a field; providing a weed classification model configured to provide weed data based on image data of the field; providing weed data for the field based on the weed classification model and the image data; providing a weed growth model configured to provide weed occurrence data and / or weed growth data for the field based on the weed data for the field; providing weed occurrence data and / or weed growth data for the field based on a weed growth model and the weed data for the field; providing herbicide application data based on the weed occurrence data and / or weed growth data, the herbicide application data including at least application timing data for at least one herbicide product for application to the field.

[0007] A further aspect of the present disclosure relates to a computer-implemented method for generating and / or providing control data usable for controlling an application device for applying a herbicide product to a field, the method comprising: providing image data of a field; providing a weed classification model configured to provide weed data based on image data of the field; providing weed data for the field based on the weed classification model and the image data; providing a weed growth model configured to provide weed occurrence data and / or weed growth data for the field based on the weed data for the field; providing weed occurrence data and / or weed growth data for the field based on a weed growth model and the weed data for the field; providing herbicide application data based on the weed occurrence data and / or weed growth data, the herbicide application data including at least application timing data of at least one herbicide product for application to the field; Generating and / or providing control data usable for controlling a herbicide product application device based on the herbicide application data.

[0008] A further aspect of the present disclosure relates to an application device for applying a herbicide product to a field, wherein herbicide application data for the application device is provided by the methods disclosed herein.

[0009] A further aspect of the present disclosure relates to a system for providing control data for an application device for applying a herbicide product to a field, the system comprising: a first providing unit configured to provide image data of a field; a second providing unit configured to provide a weed classification model configured to provide weed data based on image data of the field; a third providing unit configured to provide weed data of the field based on the weed classification model and the image data; a fourth providing unit configured to provide a weed growth model configured to provide weed occurrence data and / or weed growth data of the field based on the weed data of the field; a fifth providing unit configured to provide weed occurrence data and / or weed growth data of the field based on the weed growth model and the weed data of the field; and a sixth providing unit configured to provide herbicide application data based on the weed occurrence data and / or weed growth data, the herbicide application data including at least application timing data of at least one herbicide product for application to the field.

[0010] A further aspect of the present disclosure relates to an apparatus for providing control data for an application device for applying a herbicide product to a field, the apparatus including one or more computing nodes and one or more computer readable media having computer executable instructions stored thereon that, when executed by the one or more computing nodes, cause the apparatus to perform the following steps: providing image data of a field; providing a weed classification model configured to provide weed data based on image data of the field; providing weed data for the field based on the weed classification model and the image data; providing a weed growth model configured to provide weed occurrence data and / or weed growth data for the field based on the weed data for the field; providing weed occurrence data and / or weed growth data for the field based on a weed growth model and the weed data for the field; Providing herbicide application data based on the weed occurrence data and / or weed growth data, the herbicide application data including at least application timing data of at least one herbicide product for application to the field.

[0011] Further aspects of the present disclosure relate to the use of image data, weed data, weed occurrence data and / or weed growth data in the computer-implemented methods disclosed herein, and / or the use of herbicide application data and / or control data usable to control herbicide application equipment.

[0012] A further aspect of the present disclosure relates to a computer program element having instructions configured, when executed on a computing device of a computing environment, to perform the steps of the computer-implemented methods disclosed herein in the systems and / or devices disclosed herein.

[0013] The embodiments described herein relate to the methods, systems, devices, application devices, and computer program elements outlined above, and vice versa. As an advantageous feature, the benefits provided by any of the embodiments and examples apply equally to all other embodiments and examples, and vice versa.

[0014] As used herein, "determining" also includes "estimating," "calculating," and "initiating or performing a determination," "generating" also includes "initiating or performing a generation," and "providing" also includes "initiating or performing a determination, generation, selection, transmission, query, or reception."

[0015] The methods, devices, systems, application devices, apparatus, and computer program elements disclosed herein provide robust and accurate information regarding the timing of application of herbicide products to a field. It is an object of the present invention to provide an efficient, sustainable, and robust manner of providing herbicide application data, including at least timing data for applying herbicide products to a field, to avoid unnecessary and / or over-management of the field and improve the effectiveness of herbicide product application while saving the cost and amount of management product and reducing environmental impact.

[0016] These and other objects which will become apparent on reading the following description are solved by the subject matter of the independent claims. The dependent claims refer to preferred embodiments of the invention.

[0017] The term "field image data" as used herein should be understood broadly and is not limited to any particular data format. Furthermore, the images and / or image data may be provided by any means, for example, a remote camera unit and / or a camera unit mounted on an equipment / machine. The term "image data" may also include any processed image data, for example, where several images of a field / area are aggregated and processed.

[0018] The term "weed classification model" as used herein should be understood broadly and is not limited to any particular model. In this regard, the weed classification model is preferably configured to classify / identify weed plants, weed species, weed plant size, weed distribution, and / or weed associations (e.g., in terms of crop size and / or growth stage). In this regard, any known image recognition algorithm may be applied. The term "weed data" as used herein should be understood broadly and is not limited to any particular data format. The weed data includes at least output data of the weed classification model, such as information on classified weed plants, weed species, weed plant size, weed distribution, and / or weed associations in a crop. The term "weed growth model" as used herein should be understood broadly and is not limited to any particular model. The weed growth model may be applied to back-calculation to determine the historical timing of weed emergence and / or the historical optimal timing of herbicide application. This back-calculated data can then be used to determine the timing of herbicide application in the next season. However, the weed growth model may be applied to pre-calculation / prediction to determine herbicide application during the same period, for example, at a specific growth stage of a weed. The term "weed occurrence data" as used herein should be understood broadly in the present application and includes at least information about weeds and / or the occurrence of each weed. The term "weed growth data" as used herein should be understood broadly in the present application and includes at least information about one or more predetermined growth stages of a specific weed plant.

[0019] The term "field" as used herein should be understood broadly and refers to any area of ​​soil, i.e., surface and subsurface, to be managed with a herbicide product. A field may be a cultivated area of ​​any plant or crop, such as a farm, greenhouse, etc. The plants may be crops, weeds, volunteer plants, crops from a previous growing season, useful plants, or any other plants present in the field. A field may be identified via a geographic location or georeferenced location data. A field may be further specified using reference coordinates, size, and / or shape.

[0020] The term "herbicide application data" as used herein should be understood broadly and refers to any data providing information regarding the application of a herbicide product to a field, including at least a time and / or time window for applying the herbicide product to the field. In particular, the time and / or time window may be the current season and / or the next season (or later). Furthermore, the herbicide application data may include compatibility data providing information regarding at least one herbicide product suitable for application to the field based on at least the weed data / weed species. Furthermore, the herbicide application data may include dosage data. The dosage for applying the herbicide product to the field may be provided on or below the surface of the field. Furthermore, the herbicide application data may be provided by a herbicide application map. The herbicide application map may be a two-dimensional application map. The herbicide application data may include instructions, tasks, and / or instructions for an applicator to apply the herbicide product.

[0021] The term "herbicide product" as used herein should be understood broadly and refers to any herbicide material that is applied to a field. Herbicides may be specifically referred to as selective or non-selective herbicides. Selective herbicides suppress specific weed species while being relatively harmless to desired crops. In contrast, non-selective herbicides, such as total weed killers, kill all plant material they come into contact with. Herbicides may be at least one of, but are not limited to, the following: Acetamides, amides, aryloxyphenoxypropionates, benzamides, benzofuran, benzoic acids, benzothiadiazinones, bipyridylium, carbamic acids, chloroacetamides, chlorocarboxylic acids, cyclohexanediones, dinitroanilines, dinitrophenol, diphenyl ether, glycines, imidazolinones, isoxazoles, isoxazolidinones, nitriles, N-phenylphthalimides, oxadiazoles, oxazolidinediones, oxyacetamides, phenoxycarboxylic acids, phenylcarbamates, phenylpyrazoles, phenylpyrazolines amines, phenylpyridazines, phosphinic acids, phosphoramidates, dithiophosphates, phthalates, pyrazoles, pyridazinones, pyridines, pyridinecarboxylic acids, pyridinecarboxamides, pyrimidinediones, pyrimidinyl (thio)benzoates, quinolinecarboxylic acids, semicarbazones, sulfonylaminocarbonyltriazolinones, sulfonylureas, tetrazolinones, thiadiazoles, thiocarbamates, triazines, triazinones, triazoles, triazolinones, triazolocarboxamides, triazolopyrimidines, triketones, uracils, ureas.Additionally, the herbicide may be a lipid biosynthesis inhibitor, an acetolactate synthase inhibitor (ALS inhibitor), a photosynthesis inhibitor, a protoporphyrinogen-IX oxidase inhibitor, a bleach herbicide, an enolpyruvylshikimate 3-phosphate synthase inhibitor (EPSP inhibitor), a glutamine synthase inhibitor, a 7,8-dihydropteroate synthase inhibitor (DHP), a synthesis inhibitor, a Vactury inhibitor, and / or a bromobutide, chlorflurenol, chlorflurenol-methyl, cinmethylin. , cumyluron, dalapon, dazomet, difenzoquat, difenzoquat-methyl sulfate, dimethipine, DSMA, zimron, endothall and its salts, etobenzanide, flamprop, flamprop-isopropyl, flamprop-methyl, flamprop-M-isopropyl, flamprop-M-methyl, flurenol, flurenol-butyl, fluprimidol, fosamine, fosamine-ammonium, indanofan, indaziflam, maleimide carboxylic acid hydrazide, mefluidide, metam, methiozolin, methyl azide, methyl bromide, methyl-dimron, methyl iodide, MSMA, oleic acid, oxaziclomefone, pelargonic acid, pyributicarb, quinoclamine, tetflupyrolimet, triaziflam, tridiphane and its agriculturally acceptable salts, amide, isoxaflutole, flufenacet, aclonifen, atrazine, terbutylazine, S-metolachlor, metolachlor, metribuzin, S-methan The compound may be, but is not limited to, cyclohexyl benzoate ...

[0022] The term "weed distribution data" as used herein should be understood broadly in this context and refers to any data / information that defines or indicates the presence, distribution, and / or occurrence of weed plants in a field. Weed plants are undesirable plants, populations of which can be controlled by using herbicides. Weed distribution data may be depicted in two dimensions for one or more seasons. Weed distribution data may be historical data that indicates / delineates areas of high appearance / density of weeds, i.e., hotspots. Weed distribution data may be provided by scouting, camera, or sensor-based mapping analysis methods.

[0023] The term "crop data" as used herein should be understood broadly and refers to any data that defines, indicates, or provides relevant information about a crop planned to be planted in a field. The crop data may be data / information about the species of the crop plant, and may also include, if relevant, herbicide tolerance, trait conditions, and especially soil conditions that allow the fastest, most fruitful, and productive growth of the crop plant. The crop data may include information about the actual planned crop as well as information about subsequent crops to identify waiting periods. The crop data may be provided by a user via a user interface.

[0024] The term "historical management data" as used herein should be understood broadly and refers to any data / information that provides, defines, describes or indicates past treatments of a field. Specifically, historical management data may include information about managements performed on a field in prior periods. Historical management data may be provided as a two-dimensional map of the field showing either treatment information for one specific prior period / the sum of specific prior periods or the sum of all prior periods, depending on, for example, weather influences. Historical management data may be provided by a database and / or a data system.

[0025] The term "control data" as used herein should be understood broadly and refers to any data configured to operate and control the application device. The control data may be provided by a control unit and configured to control one or more technical means of the application device, such as, but not limited to, a drive control.

[0026] The term "application device" as used herein should be understood broadly and refers to any equipment configured to provide / spread seeds, plants and / or fertilizers to the soil of a field. The application device may be configured to traverse a field. The application device may be a ground or airborne vehicle, such as a tracked vehicle, a robot, an airplane, an unmanned aerial vehicle (UAV), a drone, etc. The application device may be an autonomous or non-autonomous application device.

[0027] The term "spot application" as used herein should be understood in a broad sense and refers to any data that provides information necessary or relevant for spot application of a second agricultural product in a field. Such spot application may be carried out as a so-called on / off application or variable application of the further agricultural product. The latter means that not all spots and / or the entire spot are provided with the same dosage, but rather variable dosages are provided.

[0028] The term "providing" as used herein should be understood broadly in this context and includes, but is not limited to, providing, receiving, querying, measuring, calculating, determining, and transmitting data. Data may be provided by a user via a user interface, rendered / displayed to a user by a display, and / or received from, queried by, measured by, calculated by, determined by, and / or transmitted by other devices.

[0029] The term "data" as used herein should be understood broadly and refers to any kind of data, which may be, but is not limited to, a single number / value, multiple numbers / values, multiple numbers / values ​​arranged in a list, a two-dimensional map, or a three-dimensional map.

[0030] In one embodiment of the method for providing herbicide application data, image data of the field may be provided by at least one remote camera unit and / or a camera unit mounted on equipment / machine, such as a spraying equipment.

[0031] In one embodiment of the method for providing herbicide application data, image data of a field may be provided over a period of time during which at least one weed species in the field has a growth stage between particular BBCH stages, for example, between BBCH6 and BBCH10, or between BBCH8 and BBCH12. In one embodiment of the method for providing herbicide application data, image data of a field may be provided over a period of time during which at least one weed species in the field has a particular size (e.g., a particular leaf size).

[0032] In one embodiment of the method for providing herbicide application data, the weed classification model may be configured to classify weed species and / or plants based on an analysis of the leaves of the weed plants, preferably based on the leaf size, leaf shape, leaf shape, and / or leaf color of the weed plants.

[0033] In one embodiment of the method for providing herbicide application data, the weed classification model may be configured to classify weed plants according to weed species, level of proliferation, size of weed plants, weed distribution and / or weed relatedness.

[0034] In one embodiment of the method for providing herbicide application data, the weed growth model may be configured to provide emergence data for at least one weed species in the field. These calculated estimated emergence data can be used to adjust herbicide application, for example, in the next planting season. For example, the emergence time of the weeds shown in the image can be determined. Based on this, it can be determined when is the best time to apply the herbicide, for example, starting from the time of sowing. This information can be used, for example, to apply the herbicide in the next planting season as close as possible to the emergence time of each weed, for example, before the weeds germinate.

[0035] In one embodiment of the method for providing herbicide application data, the weed growth model may be configured to provide growth stage timing data for at least one weed species, the growth stage timing data preferably referring to a growth stage of the weed species between BBCH11 and BBCH14, most preferably a growth stage of the weed species at BBCH12. The particular herbicide may be a so-called foliar herbicide that is more effective through the leaves, or a so-called soil herbicide that is more effective through the roots of the weed, and the appropriate herbicide may be applied at an optimal time based on the growth rate of the weed.

[0036] In one embodiment of the method for providing herbicide application data, the method further comprises: The method may include providing historical weather data, actual weather data, and / or predicted weather data, and the weed growth model is further configured to provide weed occurrence data and / or weed growth data for the field further based on the weather data. Because the effectiveness of some herbicides, such as soil herbicides, can depend on sufficient precipitation to transport the soil herbicide to plant roots, the weather data may be used to determine the selection of a particular herbicide product, such as a particular soil herbicide depending on the accumulated precipitation.

[0037] In one embodiment of the method for providing herbicide application data, the method further comprises: The method may include providing historical weed distribution data for the field, and the weed growth model is further configured to provide weed occurrence data and / or weed growth data for the field further based on the historical weed distribution data. Because weeds often occur in repetitive local distributions, such weed distribution data from previous seasons can improve herbicide application, for example.

[0038] In one embodiment of the method for providing herbicide application data, the method further comprises: The method may further include providing past management data including information on management carried out on the field in a previous period, preferably information on modes of management operations in the past, and the weed growth model is further configured to provide weed occurrence data and / or weed growth data for the field further based on the past management data. For example, by taking the past management data into consideration, the risk of resistance development due to repeated use of pesticides can be reduced.

[0039] In one embodiment of the method for providing herbicide application data, the method further comprises: providing crop data including information regarding crops planted and / or planned to be planted in the field; The step of providing herbicide application data may further be based on crop data. For example, by taking into account the crop data, it may be possible to evaluate whether a particular weed is or is not harmful to a particular crop at all. The stage of growth of the crop may also be taken into account. For example, it may be possible to evaluate when a particular weed, e.g., at a particular size of the crop, is no longer harmful to a particular stage of the crop, and it may be determined that a particular smaller weed is no longer essentially harmful to the crop because the crop is able to suppress the weed itself.

[0040] In one embodiment of the method for providing herbicide application data, the herbicide application data may be spot application data for spot applying a herbicide product.

[0041] In one embodiment of the method for providing herbicide application data, the herbicide application data comprises: application timing data including at least one time window for applying the herbicide product to the field; suitability data for at least one herbicide product suitable for application to the field based at least on the weed data and / or the classified weed species; dosage data including at least one dosage for applying a herbicide product to the field, preferably a dosage to be provided to a sub-region of the field; dosage data including at least one threshold for applying a herbicide product, indicating at which threshold the application of the herbicide product is to be performed; Spatial variability data relating to subfield areas of the field; and / or At least one of the at least one herbicide application map may be included.

[0042] In one embodiment of the method for providing herbicide application data, the method may further include generating and / or providing control data usable for controlling a herbicide product application device based on the herbicide application data.

[0043] The present disclosure will now be described in detail with reference to the accompanying drawings. [Brief explanation of the drawings]

[0044] [Figure 1] 1 illustrates several exemplary embodiments of centralized and decentralized computing environments having computing nodes. [Figure 2] 1 illustrates several exemplary embodiments of centralized and decentralized computing environments having computing nodes. [Figure 3] 1 illustrates several exemplary embodiments of a distributed computing environment. [Figure 4] 1 shows a flow diagram of a computer-implemented method for providing herbicide application data. [Figure 5] FIG. 1 shows a schematic diagram of a system for providing combined application data. [Figure 6] 1 shows, by way of example, different possibilities for receiving and processing field data; DETAILED DESCRIPTION OF THE INVENTION

[0045] The following embodiments are merely examples for implementing the methods, systems, devices, or application devices disclosed herein and should not be construed as limiting the present invention thereto.

[0046] 1-3 illustrate different computing environments: centralized, decentralized, and distributed. The methods, devices, and computer elements of the present disclosure may be implemented in a decentralized or at least partially decentralized computing environment. In particular, different issues exist in data sharing or exchange in a multi-party ecosystem. Data sovereignty may be considered a core issue. Data sovereignty can be defined as the ability of natural or legal persons to exercise total self-determination regarding their own data. To enable this, specific capability-related aspects may be implemented across the chemical value chain, including requirements for secure and reliable data exchange in business ecosystems. In particular, the chemical industry requires tailored solutions to deliver chemical products more sustainably by using digital ecosystems. Data provision, determination, or processing can be realized by different computing nodes, which may be implemented in a centralized, decentralized, or distributed computing environment.

[0047] FIG. 1 illustrates an exemplary embodiment of a centralized computing system 20 including a central computing node 21 (the central solid circle) and several peripheral computing nodes 21.1-21.n (shown as peripheral solid filled circles). The term "computing system" is broadly defined herein to include one or more computing nodes, a system of multiple nodes, or a combination thereof. A "computing node" is broadly defined herein and may refer to any device or system that includes at least one physical, tangible processor and / or physical, tangible memory capable of storing computer-executable instructions executed by the processor. Computing nodes are now taking an increasingly diverse range of forms. Computing nodes may be devices not traditionally considered computing nodes, such as mobile devices, production equipment, sensors, monitoring systems, control systems, home appliances, laptop computers, desktop computers, mainframes, data centers, or wearables (e.g., eyeglasses, watches, etc.). Memory may be of any type, depending on the nature and type of the computing node.

[0048] In this example, the peripheral computing nodes 21.1-21.n may be connected to one central computing system (or server). In another example, the peripheral computing nodes 21.1-21.n may be attached to the central computing node, for example, via a terminal server (not shown). Most of the functionality may be performed by or obtained from the central computing node (also referred to as a remote centralized management location). One peripheral computing node 21.n is expanded to show the full range of elements present on the peripheral computing node. The centralized computing node 21 may include the same elements as described for the peripheral computing node 21.n.

[0049] Each computing node 21, 21.1-21.n may include at least one hardware processor 22 and memory 24. The term "processor" may refer to any logic circuitry configured to perform the basic operations of a computer or system, and / or generally to any device configured to perform calculations or logical operations. In particular, a processor, or computer processor, may be configured to process the basic instructions that run a computer or system. It may be a semiconductor-based processor, a quantum processor, or any other type of processor configured to process instructions. By way of example, a processor may include at least one arithmetic logic unit ("ALU"), at least one floating-point unit ("FPU"), such as a math coprocessor or numeric coprocessor, multiple registers, registers configured to supply operands to the ALU and store operation results, and memory, such as L1 and L2 cache memories. In particular, a processor may be a multi-core processor. Specifically, a processor may be or include a central processing unit ("CPU"). The processor may be a graphics processing unit ("GPU"), a tensor processing unit ("TPU"), a complex instruction set computing ("CISC") microprocessor, a reduced instruction set computing ("RISC") microprocessor, a very long instruction word ("VLIW") microprocessor, or a processor implementing other instruction sets or a combination of instruction sets. The processing means may also be one or more special-purpose processing devices, such as an application specific integrated circuit ("ASIC"), a field programmable gate array ("FPGA"), a complex programmable logic device ("CPLD"), a digital signal processor ("DSP"), a network processor, or the like. The methods, systems, and apparatus described herein may be implemented as software within a DSP, microcontroller, or any other co-processor, or as hardware circuitry within an ASIC, CPLD, or FPGA.It should be understood that the term "processor" may also refer to one or more processing devices, such as a distributed system of processing devices located across multiple computer systems (e.g., cloud computing), and is not limited to a single device unless otherwise specified.

[0050] Memory 24 may refer to physical system memory, which may be volatile, nonvolatile, or a combination thereof. Memory may include nonvolatile mass storage such as a physical storage medium. Memory may be a computer-readable storage medium such as RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic disk storage or other magnetic storage devices, non-magnetic disk storage such as solid-state disks, or any other physical and tangible storage medium usable for storing desired program code means in the form of computer-executable instructions or data structures and accessible by a computing system. Furthermore, memory may be a computer-readable medium (also called a transmission medium) that carries computer-executable instructions. Furthermore, program code means in the form of computer-executable instructions or data structures may be automatically transferred from a transmission medium to a storage medium (or vice versa) upon reaching various computing system elements. For example, computer-executable instructions or data structures received over a network or data link may be buffered in RAM in a network interface module (e.g., a "NIC") and then eventually transferred to the computing system's RAM and / or a less volatile storage medium. Thus, it should be understood that storage media may be included in computing elements that also (or even primarily) utilize transmission media.

[0051] A computing node 21, 21.1-21.n may include a plurality of structures 26, often referred to as "executable elements, executable instructions, computer-executable instructions, or instructions." For example, the memory 24 of a computing node 21, 21.1-21.n may be depicted as including executable elements 26. The term "executable element" or any equivalent thereof may refer to a structure that may be software, hardware, or a combination thereof, or that is well understood by those skilled in the computing arts as being implementable in software, hardware, or a combination thereof. For example, when implemented in software, those skilled in the art will understand that the executable element structure includes software objects, routines, methods, etc., that execute on the computing node 21, 21.1-21.n, regardless of whether such executable elements reside on the heap of the computing node 21, 21.1-21.n, or whether the executable elements reside on a computer-readable storage medium. In such cases, those skilled in the art will recognize that the structure of the executable element resides on a computer-readable medium, which, when interpreted by one or more processors (e.g., by processor threads) of computing nodes 21, 21.1-21.n, causes the computing nodes 21, 21.1-21.n to perform a function. Such structure may be directly computer-readable by a processor (as would be the case if the executable element were binary). Alternatively, the structure may be structured to be interpreted and / or compiled (whether in one or more stages) to generate binary directly translatable by a processor. Such understanding of an exemplary structure of an executable element is well within the understanding of those skilled in the computing arts when using the term "executable element." Examples of executable elements implemented in hardware include hard-coded or hard-wired logic gates implemented exclusively or nearly exclusively in hardware, such as in a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or any other dedicated circuitry.In this description, the terms "element," "agent," "manager," "service," "engine," "module," "virtual machine," etc. are used synonymously with the term "executable element."

[0052] The processor 22 of each computing node 21, 21.1-21.n may direct the operation of each computing node 21, 21.1-21.n in response to executing computer-executable instructions that constitute the executable elements. For example, such computer-executable instructions may be embodied on one or more computer-readable media forming a computer program product. The computer-executable instructions may be stored in the memory 24 of each computing node 21, 21.1-21.n. The computer-executable instructions include, for example, instructions and data that, when executed by the processor 21, cause a general-purpose computing node 21, 21.1-21.n, a special-purpose computing node 21, 21.1-21.n, or a special-purpose processing device to perform a particular function or group of functions. Alternatively or additionally, the computer-executable instructions may configure the computing node 21, 21.1-21.n to perform a particular function or group of functions. The computer-executable instructions may be, for example, binaries or instructions that undergo some interpretation (eg, compilation) before being executed directly by a processor, such as intermediate format instructions such as assembly language or even source code.

[0053] Each computing node 21, 21.1-21.n may include a communications channel 28, e.g., a network (shown as a solid line between the peripheral and central computing nodes in FIG. 1), that enables each computing node 21.1-21.n to communicate with the central computing node 21. A "network" may be defined as one or more data links that enable the transmission of electronic data between computing nodes 21, 21.1-21.n and / or modules and / or other electronic devices. When information is transferred or provided to a computing node 21, 21.1-21.n via a network or another communications connection (either wired, wireless, or a combination of wired and wireless), the computing node 21, 21.1-21.n properly considers the connection to be a transmission medium. A transmission medium may include a network and / or data link that may be used to carry desired program code means in the form of computer-executable instructions or data structures and that may be accessed by a general-purpose or special-purpose computing node 21, 21.1-21.n. Combinations of the above may also be included within the scope of computer-readable media.

[0054] Computing nodes 21, 21.1-21.n may further include a user interface system 25 for interfacing with a user. User interface system 25 may include output mechanism 25A as well as input mechanism 25B. The principles described herein are not limited to a strict output mechanism 25A or input mechanism 25B, as this depends on the nature of the device. However, output mechanism 25A may include, for example, a display, a speaker, a display, a tactile output, a hologram, etc. Examples of input mechanism 25B may include, for example, a microphone, a touchscreen, a hologram, a camera, a keyboard, a mouse or other pointer input, any type of sensor, etc.

[0055] FIG. 2 illustrates an exemplary embodiment of a decentralized computing environment 30 having several computing nodes 21.1-21.n, shown as solid circles. In contrast to the centralized computing environment 20 illustrated in FIG. 1, the computing nodes 21.1-21.n of the decentralized computing environment are not connected to, and therefore not under the control of, a central computing node 21. Instead, both hardware and software resources may be assigned to each individual computing node 21.1-21.n (local or remote computing system), and data may be distributed across the various computing nodes 21.1-21.n to perform tasks. Thus, in a decentralized system environment, program modules may be located in both local and remote memory storage devices. One computing node 21 is expanded to provide an overview of the elements present on the computing node 21. In this example, the computing node 21 includes the same elements as those described with respect to FIG. 1.

[0056] FIG. 3 illustrates an exemplary embodiment of a distributed computing environment 40. In this description, "distributed computing" may refer to any computing that utilizes multiple computing resources. Such use may be achieved through virtualization of physical computing resources. One example of distributed computing is cloud computing. "Cloud computing" may refer to a model that enables on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services). When distributed, a cloud computing environment may be distributed internally within an organization and / or across multiple organizations. In this example, the distributed cloud computing environment 40 may include the following computing resources: mobile devices 42, applications 43, databases 44, and data storage and servers 46. The cloud computing environment 40 may be deployed as a public cloud 47, a private cloud 48, or a hybrid cloud 49. The private cloud 47 may be owned by the organization, and only members of the organization with appropriate access rights may use the private cloud 48, keeping data in the private cloud at least private. In contrast, data stored in a public cloud 48 may be open to anyone via the internet. A hybrid cloud 49 may be a combination of both private and public clouds 47, 48, where some data may be private while other data may be public.

[0057] FIG. 4 shows a flow diagram of a method for providing control data for an application device for applying a herbicide product to a field.

[0058] In a first step, image data of a field is provided, for example, by a camera unit mounted on a sprayer device. In a second step, a weed classification model is provided, configured to provide weed data based on the image data of the field. In a further step, the weed classification model is applied to process the provided image data to provide weed data as output data. The weed data may include information on weed plants, weed species, weed plant size, weed distribution, crop-weed associations, etc. In a further step, the provided weed data is used as input data to the above-mentioned provided weed growth model, which is configured to provide weed occurrence data and / or weed growth data for the field based on the weed data of the field. The weed occurrence data and / or weed growth data may then be used to provide herbicide application data including at least application timing data of at least one herbicide product, where the timing data may refer to the same and / or subsequent seasons. In other words, the weed growth model can be applied to back-calculation to determine the time of weed emergence and / or the optimal timing of herbicide application. This back-calculated data can then be used to determine the time of herbicide application in the next period. However, the weed growth model may also be applied to prior calculations / predictions to determine herbicide application in the same period, for example, at a particular growth stage of the weed.

[0059] FIG. 5 shows a schematic diagram of a system 10 for providing herbicide application data for applying herbicide products to a field. The system 10 for providing herbicide application data may include a first providing unit 11 configured to provide image data of a field, a second providing unit 12 configured to provide a weed classification model configured to provide weed data based on the image data of the field, a third providing unit 13 configured to provide weed data of the field based on the weed classification model and the image data, a fourth providing unit 14 configured to provide a weed growth model configured to provide weed infestation data and / or weed growth data of the field based on the weed data of the field, a fifth providing unit 15 configured to provide weed infestation data and / or weed growth data of the field based on the weed growth model and the weed data of the field, and a sixth providing unit 16 configured to provide herbicide application data based on the weed infestation data and / or weed growth data, wherein the herbicide application data includes at least application timing data of at least one herbicide product to apply to the field.

[0060] FIG. 6 shows, by way of example, different possibilities for receiving and processing field data.

[0061] For example, field data can be obtained by any type of agricultural equipment 300 (e.g., tractor 300) by recording application rates at the time of application, resulting in so-called time-of-application maps. Such agricultural equipment may also include sensors (e.g., optical sensors, cameras, infrared sensors, soil sensors, etc.) to provide, for example, weed distribution maps. Yields (e.g., in the form of biomass) can also be recorded by harvesting vehicles 310 during harvesting. Furthermore, corresponding maps / data can be provided by land-based and / or aerial drones 320 by taking images of the field or parts thereof. Finally, a georeferenced visual assessment 330 can also be performed to process the field data. The field data collected in this way can then be consolidated in computing device 340, and the data can be transmitted and calculated, for example, via any wireless link, cloud application 350, and / or work platform 360, and the field data can also be processed in whole or in part within cloud application 350 and / or work platform 360 (e.g., by cloud computing).

[0062] Aspects of the present disclosure relate to computer program elements configured to perform the steps of the above-described methods. The computer program elements may therefore be stored on a computing unit of a computing device, which may be part of one embodiment. The computing unit may be configured to perform or direct the execution of the steps of the above-described methods. Furthermore, the computing unit may be configured to operate the elements of the above-described systems. The computing unit may be configured to operate automatically and / or to execute user instructions. The computing unit may include a data processor. The computer program may be loaded into the working memory of the data processor. The data processor may therefore be equipped to perform the method according to one of the previous embodiments. This exemplary embodiment of the present disclosure encompasses both computer programs that initially employ the present disclosure and computer programs that convert existing programs into programs that employ the present disclosure by means of an update. Furthermore, the computer program elements may be capable of providing all steps necessary to execute the procedures of the above-described exemplary method embodiments. According to further exemplary embodiments of the present disclosure, a computer-readable medium such as a CD-ROM, a USB stick, a downloadable executable file, etc. is presented, on which computer-readable medium are stored computer program elements, which computer program elements are described in the previous sections. The computer program may be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. However, the computer program may also be provided over a network, such as the World Wide Web, from which it can be downloaded into the working memory of a data processor.According to a further exemplary embodiment of the present disclosure, a medium is provided on which a computer program element can be downloaded, the computer program element being configured to perform a method according to one of the above-described embodiments of the present disclosure.

[0063] The following embodiments 1 to 20 are preferred embodiments of the present invention.

[0064] Embodiments of the present invention: Embodiment 1: 1. A computer-implemented method for providing control data for an application device for applying a herbicide product to a field, the method comprising: providing image data of a field; providing a weed classification model configured to provide weed data based on image data of the field; providing weed data for the field based on the weed classification model and the image data; providing a weed growth model configured to provide weed occurrence data and / or weed growth data for the field based on the weed data for the field; providing weed occurrence data and / or weed growth data for the field based on the weed growth model and the weed data for the field; providing herbicide application data based on the weed occurrence data and / or weed growth data, the herbicide application data including at least application timing data for at least one herbicide product for application to the field.

[0065] Embodiment 2: In the computer-implemented method according to embodiment 1, image data of the field is provided by at least one remote camera unit and / or a camera unit mounted on the equipment / machine.

[0066] Embodiment 3: In the computer-implemented method according to embodiment 1 or embodiment 2, image data of a field is provided when at least one weed species in the field has a growth stage between BBCH6 and BBCH10, or between BBCH8 and BBCH12.

[0067] Embodiment 4: In the computer-implemented method according to any one of embodiments 1 to 3, the weed classification model is configured to classify weed species and / or plants based on an analysis of the leaves of the weed plants, preferably based on the leaf size, leaf geometry, leaf shape, and / or leaf color of the weed plants.

[0068] Embodiment 5: In the computer-implemented method according to any one of embodiments 1 to 4, the weed classification model is configured to classify weed plants according to weed species, degree of proliferation, size of weed plants, weed distribution, and / or weed relatedness.

[0069] Embodiment 6: In the computer-implemented method according to any one of the first to fifth embodiments, the weed growth model is configured to provide emergence time data for at least one weed species in the field.

[0070] Embodiment 7: In the computer-implemented method according to any one of embodiments 1 to 6, the weed growth model is configured to provide growth stage timing data of at least one weed species, and the growth stage timing data preferably refers to a growth stage of the weed species between BBCH11 and BBCH14, most preferably a growth stage of the weed species of BBCH12.

[0071] Embodiment 8: 8. A computer-implemented method according to any one of embodiments 1 to 7, comprising: The method further includes providing historical weather data, actual weather data, and / or predicted weather data, and the weed growth model is further configured to provide weed occurrence data and / or weed growth data for the field further based on the weather data.

[0072] Embodiment 9: 9. A computer-implemented method according to any one of embodiments 1 to 8, comprising: The method further includes a step of providing historical weed distribution data for the field, wherein the weed growth model is further configured to provide weed occurrence data and / or weed growth data for the field further based on the historical weed distribution data.

[0073] Embodiment 10: 10. A computer-implemented method according to any one of embodiments 1 to 9, comprising: The method may further include a step of providing historical management data including information regarding management carried out on the field in a previous period, preferably information regarding the mode of management action in the past, and the weed growth model is further configured to provide weed occurrence data and / or weed growth data for the field further based on the historical management data.

[0074] Embodiment 11: A computer-implemented method according to any one of embodiments 1 to 10, wherein the method is applied to back-calculation to determine the past timing of weed emergence and / or the past optimal timing of herbicide application, and optionally these back-calculated data are used to determine the timing of herbicide application in the next season, or optionally these back-calculated data are applied to pre-calculation / prediction to determine herbicide application in the same season, particularly at a particular growth stage of the weeds.

[0075] Embodiment 12: 12. A computer-implemented method according to any one of embodiments 1 to 11, comprising: providing crop data including information regarding crops planted and / or to be planted in the field; The step of providing herbicide application data is further based on crop data.

[0076] Embodiment 13: In the computer-implemented method according to any one of embodiments 1-12, the herbicide application data is spot application data for spot applying a herbicide product.

[0077] Embodiment 14: In a computer-implemented method according to any one of embodiments 1 to 13, the herbicide application data comprises: application timing data including at least one time window for applying the herbicide product to the field; - compatibility data for at least one herbicide product suitable for application to the field, based at least on the weed data and / or the classified weed species; - dosage data comprising at least one dosage for applying a herbicide product to the field, preferably a dosage to be provided to a sub-area of ​​the field; - dosage data including at least one threshold value for applying a herbicide product, indicating at which threshold value application of the herbicide product is performed; - spatial variability data relating to subfield areas of the field; and / or - at least one herbicide application map It includes at least one of the following:

[0078] Embodiment 15: 15. The computer-implemented method according to any one of embodiments 1-14, further comprising generating and / or providing control data usable for controlling a herbicide product application device based on the herbicide application data.

[0079] Embodiment 16: An application device for applying a herbicide product to a field, wherein herbicide application data is provided by a method according to any one of embodiments 1-15.

[0080] Embodiment 17: 1. A system for providing herbicide application data for applying a herbicide product to a field, comprising: a first providing unit configured to provide image data of a field; a second providing unit configured to provide a weed classification model configured to provide weed data based on the image data of the field; a third providing unit configured to provide weed data of the field based on the weed classification model and the image data; a fourth providing unit configured to provide a weed growth model configured to provide weed occurrence data and / or weed growth data of the field based on the weed data of the field; a fifth providing unit configured to provide weed occurrence data and / or weed growth data of the field based on the weed growth model and the weed data of the field; and a sixth providing unit configured to provide herbicide application data based on the weed occurrence data and / or weed growth data, the herbicide application data including at least application timing data of at least one herbicide product for application to the field.

[0081] Embodiment 18: 1. An apparatus for providing control data for an application device for applying a herbicide product to a field, the apparatus comprising one or more computing nodes and one or more computer readable media having computer executable instructions stored thereon, the instructions, when executed by the one or more computing nodes, causing the apparatus to perform the following steps: providing image data of a field; providing a weed classification model configured to provide weed data based on image data of the field; providing weed data for the field based on the weed classification model and the image data; providing a weed growth model configured to provide weed occurrence data and / or weed growth data for the field based on the weed data for the field; providing weed occurrence data and / or weed growth data for the field based on the weed growth model and the weed data for the field; Providing herbicide application data based on the weed occurrence data and / or weed growth data, the herbicide application data including at least application timing data for at least one herbicide product for application to the field.

[0082] Embodiment 19: 16. Use of image data, weed data, weed occurrence data, and / or weed growth data in a computer-implemented method according to any one of embodiments 1 to 15, and / or use of herbicide application data and / or control data for controlling a herbicide application device.

[0083] Embodiment 20: A computer program element having instructions configured to, when executed on a computing device in a computing environment, perform steps of a computer-implemented method according to any one of embodiments 1 to 15 in a system according to embodiment 17 or an apparatus according to embodiment 18.

[0084] The present disclosure has been described in conjunction with preferred embodiments, which are also examples. However, from a study of the drawings, the disclosure, and the claims, other variations can be understood and implemented by those skilled in the art by applying the claimed invention. It is particularly noteworthy that any steps presented may be performed in any order, i.e., the present invention is not limited to a particular order of these steps. Furthermore, the different steps may not be performed at a particular location or node of a distributed system, i.e., each step may be performed at a different node using different equipment / data processing devices.

[0085] In the description as well as in the claims, the term "comprises" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items referred to in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage in an implementation manner.

Claims

1. A computer-implemented method for generating and / or providing control data usable for controlling an application device for applying herbicides to a field, The steps include providing field image data and The steps include providing a weed classification model configured to provide weed data based on the image data of the field, The steps include providing field weed data based on the aforementioned weed classification model and the aforementioned image data, The steps include providing a weed growth model configured to provide weed occurrence data and / or weed growth data for a field based on the weed data for the field, The steps include providing weed occurrence data and / or weed growth data for the field based on the weed growth model and the weed data for the field, The steps include providing herbicide application data based on the aforementioned weed emergence data and / or weed growth data, which includes at least application timing data for at least one herbicide product to be applied to the field, A method comprising the step of generating and / or providing control data usable for controlling a herbicide product application device based on the herbicide application data.

2. A computer-implemented method according to claim 1, wherein the image data of the field is provided by at least one remote camera unit and / or a camera unit mounted on equipment / machinery.

3. A computer-implemented method according to claim 1, wherein the image data of the field is provided when at least one weed species in the field is in a growth stage between BBCH6 and BBCH10, or between BBCH8 and BBCH12.

4. In the computer-implemented method described in claim 1, The aforementioned weed classification model is configured to classify weed species and / or plants based on an analysis of the leaves of weed plants, preferably based on the size of the leaves, the geometric shape of the leaves, the shape of the leaves, and / or the color of the leaves. Alternatively, the weed classification model is configured to classify weed plants according to weed species, degree of reproduction, size of the weed plant, weed distribution, and / or weed relatedness.

5. In the computer-implemented method described in claim 1, The aforementioned weed growth model is configured to provide emergence timing data for at least one weed species in the field. Alternatively, the weed growth model is configured to provide growth stage timing data for at least one weed species, wherein the growth stage timing data preferably refers to a growth stage of a weed species between BBCH11 and BBCH14, and most preferably to a growth stage of a weed species BBCH12.

6. A computer-implemented method according to claim 1, A method further comprising the step of providing historical weather data, actual weather data and / or predicted weather data, wherein the weed growth model is further configured to provide weed emergence data and / or weed growth data for the field based on the weather data.

7. A computer-implemented method according to claim 1, A method further comprising the step of providing past weed distribution data for the field, wherein the weed growth model is further configured to provide weed emergence data and / or weed growth data for the field based on the past weed distribution data.

8. A computer-implemented method according to claim 1, A method further comprising the step of providing historical management data, which includes information on management performed on the field in a preceding period, preferably information on the mode of the past management operation, wherein the weed growth model is further configured to provide weed emergence data and / or weed growth data of the field based on the historical management data.

9. A computer-implemented method according to claim 1, wherein the herbicide application data is spot application data for spot application of the herbicide product.

10. In the computer-implemented method according to claim 1, the herbicide application data is - Application timing data including at least one time window for applying the herbicide product to the field, - Suitability data relating to at least one herbicide product suitable for application to the field, based at least on the aforementioned weed data and / or the aforementioned classified weed species, - Dosage data including at least one dosage for applying a herbicide product to the field, preferably a dosage provided to a portion of the field, - Dosage data including at least one threshold for applying the herbicide product, indicating at which threshold the herbicide product should be applied. - Spatial variation data related to the aforementioned sub-field area of ​​the field, and / or - At least one herbicide application map A method that includes at least one of the following.

11. An application device for applying a herbicide product to a field, wherein herbicide application data is provided by the method described in claim 1.

12. A system that provides herbicide application data for applying herbicide products to fields, A first provisioning unit configured to provide field image data, A second providing unit configured to provide a weed classification model configured to provide weed data based on the image data of the field, A third providing unit configured to provide the weed data of the field based on the weed classification model and the image data, A fourth providing unit configured to provide a weed growth model configured to provide weed occurrence data and / or weed growth data for the field based on the weed data for the field, A fifth providing unit configured to provide weed occurrence data and / or weed growth data for the field based on the weed growth model and the weed data for the field, A system comprising a sixth providing unit configured to provide herbicide application data, which includes at least timing data for the application of at least one herbicide product for application to the field, based on the aforementioned weed emergence data and / or the aforementioned weed growth data.

13. A device that provides control data for an application device for applying herbicide products to a field, wherein the device includes one or more computing nodes and one or more computer-readable media storing computer executable instructions, and if an instruction is executed by the one or more computing nodes, the device performs the following steps, i.e. The steps include providing field image data and The steps include providing a weed classification model configured to provide weed data based on the image data of the field, The steps include providing the weed data for the field based on the weed classification model and the image data, The steps include providing a weed growth model configured to provide weed occurrence data and / or weed growth data for the field based on the weed data for the field, The steps include providing weed occurrence data and / or weed growth data for the field based on the weed growth model and the weed data for the field, An apparatus for performing the step of providing herbicide application data, which includes at least timing data for the application of at least one herbicide product to be applied to the field, based on the aforementioned weed emergence data and / or the aforementioned weed growth data.

14. The use of image data, weed data, weed emergence data, and / or weed growth data in the computer-implemented method according to claim 1, and / or the use of herbicide application data and / or control data for controlling a herbicide application device.

15. A computer program element having instructions configured to perform steps of the computer-implemented method described in claim 1 in the system described in claim 12 or the device described in claim 13, when executed on a computing device of a computing environment.

Images