WO2025003409A1

WO2025003409A1 - Method for setting a threshold value for applying an agricultural product on a sub-area of an agricultural field

Info

Publication number: WO2025003409A1
Application number: PCT/EP2024/068259
Authority: WO
Inventors: Erik Hass; Hubert Schmeer; Dominic Sturm; Clemens Christian DELATREE; Carvin Guenther SCHEEL; Steffen TELGMANN; Marcel Enzo GAUER
Original assignee: Basf Agro Trademarks Gmbh
Priority date: 2023-06-29
Filing date: 2024-06-28
Publication date: 2025-01-02

Abstract

Computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field (120) in a spot spray application, comprising: providing weed coverage data for at least one measurement sub-area and a preceeding measurement subarea, wherein the weed coverage data are provided by at least one detection system, wherein the detection system is adapted to detect weed coverage at least in the at least one measurement sub-area while an application device (100) is moving through the agricultural field (120); providing a threshold model configured to provide a threshold value at least based on the provided weed coverage data in the at least one measurement sub-area; setting the threshold value for applying the agricultural product on the application sub-area based on the weed coverage data in the at least one measurement sub-area by utilizing the threshold model. The method applies aside of the uses case for an in-crop weed control also to the vegetation burndown and the use of defoliant and/or dessicants.

Description

METHOD FOR SETTING A THRESHOLD VALUE FOR APPLYING AN AGRICULTURAL PRODUCT ON A SUB-AREA OF AN AGRICULTURAL FIELD

TECHNICAL FIELD

The present disclosure relates to a computer-implemented method for setting a threshold value for applying an agricultural product on a sub-area of an agricultural field in a spot spray application, an apparatus for setting a threshold value for applying an agricultural product on a sub-area of an agricultural field in a spot spray application, and an application device for applying an agricultural product on a sub-area of an agricultural field in a spot spray application.

TECHNICAL BACKGROUND

The general background of the present disclosure is the treatment of plantation in an agricultural field. The treatment of plantation also comprises the treatment of weeds and crops in an agricultural field.

Agricultural machines get equipped with more and more sensors. Crop protection may be executed by detecting plantation, in particular weeds, crop, insects and/or pathogens in real time. In order to reduce the herbicide usage to benefit the environment and farm economy Smart Sprayers with spot spraying systems based on weed and crop recognition are presently used, in development or close to market launch. Therefore, a plurality of thresholds for the spraying decision for a spot spraying technology are defined. However, in common agricultural practice, the thresholds to trigger a spraying decision to apply a spot spray or not is so far agronomically optimized for the field level. This allows already considerable savings of the herbicides. Since, in arable fields, many weed species are not evenly distributed, but grow in patches, as for example the following weed species Abutilon theophrasti, Solanum nigrum, Chenopodium album , Echinochloa crus- gal li, Polygonum aviculare and Pa paver rhoeas, Alopecurus myosuroides, Avena sterilis etc., thresholds to trigger a spraying decision to apply a spot spray or not are optimized for the field level are too unprecise for applying an agricultural product for a field sub-area specific spot spray application. Therefore, there is a need to provide a method for providing optimized threshold values being accurate for applying an agricultural product on sub-areas of an agricultural field in a spot spray application.

SUMMARY OF THE INVENTION

The present invention provides a computer-implemented method, an apparatus, and an application device for setting threshold values for applying an agricultural product on a sub-areas of an agricultural field during a spot spray application according to the independent claims, which become apparent upon reading the following description. The dependent claims refer to further embodiments of the invention.

In one aspect of the present disclosure, a computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application is disclosed, the method is comprising: providing coverage data for at least one of weed coverage and crop coverage for at least one measurement sub-area, wherein the coverage data are provided by at least one detection system, wherein the detection system is adapted to detect coverage of at least one of weed and crop at least in the at least one measurement sub-area while an application device is moving through the agricultural field; providing a threshold model configured to provide a threshold value at least based on the provided coverage data in the at least one measurement sub-area; setting the threshold value for applying the agricultural product on the application sub-area based on the coverage data in the at least one measurement sub-area by utilizing the threshold model.

In further aspect of the present disclosure relates to a computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application is disclosed, the method is comprising: providing coverage data for at least one of weed coverage and crop coverage for at least one measurement sub-area, wherein the coverage data are provided by at least one detection system, wherein the detection system is adapted to detect coverage of at least one of weed coverage and crop coverage at least in the at least one measurement sub- area while an application device is moving through the agricultural field, wherein the detected coverage values are than averaged with at least the previous measurement, in particular previous 2-4 measurements in a kind of measurement cycle, providing a threshold model configured to provide a threshold value at least based on the provided averaged coverage data in at least two subsequent measurement subareas; setting a new threshold value for applying the agricultural product on the application sub-area based on the averaged coverage data in the at least two, in particular 3-4 measurement sub-areas by utilizing the threshold model.

Alternatively, in one aspect of the present disclosure, a computer-implemented method for setting a threshold value dynamically for applying an agricultural product on an application sub-area of an agricultural field is disclosed, the method is comprising: detecting a weed coverage in at least two subsequent measurement sub-areas by at least one detection system, e.g. a camera based sensor, while an application device is moving through the agricultural field; generating weed coverage data for the measurement sub-area from the detected weed coverage; providing the weed coverage data for at least two subsequent measurement subareas, providing a threshold model configured to generate a threshold value based on the provided averaged weed coverage data of at least two measurement sub-areas; utilizing the threshold model for generating the threshold value based on the provided averaged weed coverage data from at least two subsequent measurement subareas; setting the generated threshold values for applying the agricultural product on the application sub-area, in particular independent for each of the camera sensor positions.

A further aspect of the present disclosure relates to an apparatus for setting a threshold value for applying an agricultural product on application sub-areas of an agricultural field in a spot spray application, the apparatus comprising: a computing node; and a computer- readable media having thereon computer-executable instructions that are structured such that, when executed by the computing node, cause the apparatus to perform the following steps: providing weed coverage data for at least two subsequent measurement subareas, wherein the weed coverage data are provided by at least one detection system, e.g. corresponding to one camera sensor position, wherein the detection system is adapted to detect weed coverage at least in two subsequent measurement sub-areas while an application device (100) is moving through the agricultural field (120); providing a threshold model configured to provide a threshold value at least based on the provided averaged weed coverage data of at least two subsequent measurement sub-areas; setting the threshold value for applying the agricultural product for application subareas based on the averaged weed coverage data of at least two subsequent measurement sub-areas by utilizing the threshold model.

A further aspect of the present disclosure relates to an application device for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, wherein the threshold value is provided according to a computer- implemented method for setting a threshold value for applying an agricultural product on a sub-area of an agricultural field in a spot spray application as disclosed herein.

Another aspect of the present disclosure relates to a computer program element with instructions, which, when executed on computing devices of a computing environment, is configured to carry out the steps of the computer-implemented method for setting a threshold value for applying an agricultural product on a sub-area of an agricultural field in a spot spray application, in particular in a respective apparatus and/or system.

A further aspect of the present disclosure relates to a system for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, comprising: a weed coverage data providing unit configured to provide providing weed coverage data for at least two subsequent measurement sub-areas, wherein the weed coverage data are provided by at least one detection system, wherein the detection system is adapted to detect weed coverage at least in two subsequent measurement sub-areas and averaged while an application device is moving through the agricultural field; a threshold model providing unit configured to provide a threshold model configured to provide a threshold value at least based on the provided averaged weed coverage data from at least two, in particular 3-4 measurement sub-areas; a threshold value setting unit configured to set the threshold value for applying the agricultural product on the application sub-area based on the averaged weed coverage data from at least two, in particular 3-4 measurement sub-areas by utilizing the threshold model.

A further aspect of the present disclosure relates to a use of weed coverage data, crop coverage data, relative weed coverage data, one or more threshold models, one or more lookup tables, one or more detection systems, red green blue images and/or near Infrared Images and/or Red Edge Images in a computer-implemented method, a system and/or an apparatus for setting a threshold value for applying an agricultural product on a subarea of an agricultural field in a spot spray application.

A further aspect of the present disclosure relates to a use of control data for controlling at least one application sub-devices of an application device at least based on the set threshold value for applying the agricultural product on the sub-area of the agricultural field.

The present invention allows for adapting decision thresholds for each sensor/ camera position of a spot sprayer while the sprayer passes through the field. An initial single threshold for the whole field which is specific for the crop and the field history may be herewith modulated and optimized on each detection position, e.g. camera position based on large in-field differentiations of the detected weed coverages when passing across weed patches.

Any disclosure and embodiments described herein relate to the methods, the system, the apparatus, the device or the computer program product lined out above. Advantageously, the benefits provided by any of the embodiments and examples equally apply to all other embodiments and examples and vice versa. As used herein “determining" also includes “estimating, calculating, initiating or causing to determine", “generating" also includes “initiating or causing to generate", and “providing” also includes “initiating or causing to determine, generate, select, send, query or receive”.

The method, device, apparatus, system and/or computer program element, disclosed herein provide a method by which threshold values for applying an agricultural product on an agricultural field is determined in an objective manner not only on a field-level.

In particular, the present disclosure may allow an automation of determ ining/providing an optimized, dynamic threshold setting for spot spraying systems on-the-go during spraying on a high resolution level, e.g., for each nozzle of a sprayer and/or for a predetermined/chosen section of a spray boom of a sprayer. This means ideally that the threshold values used for spot applications, e.g., on/off mode or variable mode, may be adapted independently across a sprayer boom width on each nozzle or section level while driving forward when spraying. In other words, threshold values may be determined in an objective manner on a detailed field sub-area level, virtually for every square meter of an agricultural field. Thus, the present disclosure may provide an economically optimal intrafield threshold adjustment (“teilflachenspezische Schadschwellenanpassung”) as reaction to inhomogen crop canopies and variable, patchy weed densities. It may allow the best, i.e., an optimal, crop performance with the lowest possible input on an agricultural product, e.g., an herbicide product. This may allow the use of more optimal thresholds and also doses for an agricultural product avoiding unnecessary treating and/or over treatment of the agricultural field, and saving amounts of agricultural products.

The invention also covers the use of total herbicides in bumdown applications as vegetation management in plantations, in fallow areas or intermediate cover crops etc. before the planting/drilling of the next crop. Further, it also covers the end of season use of defoliants, also in a burn down mode, in various crops as cotton, soybeans etc. and desiccants in crops as potatoes, cotton etc.

Further, as the weed coverages are different inside weed patches than the rest of the field and vary across a field, it makes sense to adjust the thresholds to trigger spot sprays on an intra-field, site specific level respectively sub-area level (teilflachen-spezifisch), ideally on a hyberlocal level for each nozzle position along the sprayer boom during the spraying operation. This will improve the targeting and minimize the herbicide use further while maintaining sufficient weed control and reducing stress to the crop.

It delivers further financial savings and less herbicidal stress on the crop, which may lead to higher yields. Further it delivers environmental benefits as the exposure of non-target organisms is significantly reduced.

A threshold in this case is the level of weed coverage or relative weed coverage at the time of the application (e.g., BBCH 14 or V4 stage of corn) which triggers a spot spray and which leads to an acceptable level of final weed infestation some weeks after the crop canopy has closed (e.g., BBCH 30 or V10 stage). This can be related to farmer acceptance and/or to yield damage estimated in trials comparing a range of thresholds. These thresholds are specific to every crop species, crop growth stage and varies depending various factors in the field history (e.g., cultivation technique, use of organic fertilizers, intermediate crops etc.). If the weed coverage (or the relative weed coverage) measured by the camera system below the set threshold there is no spray triggered. Opposite, if the weed coverage (or relative weed coverage) is above the set threshold value the spot spray is initiated.

In other words, the term “threshold value” as used herein is to be understood broadly in the present case and includes any value that may be used to control an application of the agricultural product. For example, such a threshold value may refer to weed coverage, weed coverage and crop coverage or relative weed coverage. The threshold value may also be based on respectively affected by the weed growth stage data, weed size data, weed density data, weed number data, comprising information about the weeds on a predefined surface data e.g., per ha, weed location data e.g., GPS-positions and distance of the weeds to a row, crop growth stage data, crop size data, crop density data, number of crop plants on a predefined surface data e.g., per ha, and/or weed species data; biomass per unit area, plants per unit area, relative weed coverage data, etc. Within the scope of the present disclosure, the threshold may be determined in a single-stage or two-stage setting. A single-stage setting within the context of the present disclosure is to be understood to mean that the threshold value is only determined in real time in the field, i.e., during the application of the agricultural product. A two-stage setting within the context of the present disclosure is to be understood to mean that in a first step a predefined threshold value is specified for an agricultural field or for an area of an agricultural field and in a second step, this initial threshold value is adjusted/changed for sub-areas of a field during the application of the agricultural product. In an example the threshold value for a nozzle is set based on the detected averaged weed coverage data of at least two subsequent measurement sub-areas while the application device used for generating the application sub-area substantially corresponds to the measurement subarea. The application sub-area may be seen as footprint and/or spot on the field ground generated by applying the spraying operation of the nozzle. The threshold value is provided by a threshold model based on the weed coverage, the crop coverage, the relative weed coverage, the averaged weed coverage, the averaged crop coverage and/or the averaged relative weed coverage. A threshold may be the level of weed coverage or relative weed coverage at the time of the application (e.g., 2-4-leaf stage of the crop) used as trigger of a spot spray and which leads to an acceptable level of final weed infestation some weeks after the crop canopy has closed (e.g., from the beginning of stem elongation) in terms of farmer acceptance and/or influence on the crop yield.

The term “threshold model” used herein is to be understood broadly in the present case and represents any model capable of determining the threshold value. The threshold model uses the weed coverage, the crop coverage, the relative weed coverage, the averaged weed coverage, the averaged crop coverage and/or the averaged relative weed coverage for providing, in particular determining, the threshold value for single images. The threshold model is included in the detection system or delivered on-line from a field manager platform. The threshold model may include at least one lookup table in which the relationship between a weed coverage and a threshold value is provided or determined by an algorithm; the relationship between an averaged weed coverage and a threshold value is provided or determined by an algorithm; the relationship between a weed coverage, a crop coverage and a threshold value is provided or determined by an algorithm; or the relationship between an averaged weed coverage, an averaged crop coverage and a threshold value is provided or determined by an algorithm; or the relationship between a relative weed coverage and a threshold value is provided or determined by an algorithm; the relationship between an averaged relative weed coverage and a threshold value is provided or determined by an algorithm. The threshold model may be a machine learning model or a machine learning algorithm but is not limited thereto. Threshold models may be provided by results of hundreds of large scale field trials carried out in a range of crops in various geographic regions. Alternatively, the threshold model may be a multifactorial regression analysis, but is not limited thereto.

The term “agricultural product” as used herein is to be understood broadly in the present case and comprises any product and/or object and/or material which may be applied on an agricultural field. In the context of the present disclosure, the term “agricultural product” may comprise: chemical products such as fungicide, herbicide, insecticide, acaricide, molluscicide, nematicide, avicide, rodenticide, repellant, bactericide, biocide, safener, plant growth regulator, urease inhibitor, nitrification inhibitor, denitrification inhibitor, or any combination thereof; biological products such as microorganisms useful as fungicide (biofungicide), herbicide (bioherbicide), insecticide (bioinsecticide), acaricide (bioacaricide), molluscicide (biomolluscicide), nematicide (bionematicide), avicide, piscicide, rodenticide, repellant, bactericide, biocide, safener, plant growth regulator, total herbicide and/or bumdown herbicide, defoliant, desiccant, urease inhibitor, nitrification inhibitor, denitrification inhibitor, or any combination thereof; fertilizers and/or nutrients; seeds and seedlings; water. In particular, the term agricultural product comprises crop protection products, like herbicide products, and in particular foliar active herbicide products (e.g., of the chemical classes of the Sulfonylureas, the HPPD's, the Auxins, FOP's and DIMs (but not limited to) in various crops as com, soy beans etc.), total herbicide products and other products used for bumdown (e.g., Glyphosate, Glufosinate, Auxins etc.), but also defoliants and dessicants (as Thiadizuron, Carfentrazone, PPO- herbicides as Saflufenacil or Pyraflufen and bio herbicides (e.g., pelargonic acid etc.).

The term “conversion into binary images” used herein is to be understood broadly in the present case and represents a method or a process by which red-green-blue (RGB) images and/or the Near Infrared Images and/or the Red Edge Images and/or multi- spectral images are converted into binary images. This conversion may be provided by using the BW= im2bw() function of MATLAB®, or the sequences of cv2.cvtColor() and cv2.threshold(9) in Python®, but is not limited thereto. In this context, the conversion of the red-green-blue (RGB)-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images may be converted into binary images by determining the Normalized Difference Vegetation Index, NDVI, and by setting threshold levels for the intensity level of the pixels. In other words, all pixels are replaced according to the specified luminance with either white (logical 1 ), if the pixel is equal or greater than the chosen luminance level, or black (logical 0), if lower.

As a result, the binary image shows any green plant material in white and the background of the soil or dead plant material, having a same or almost same luminance of the soil, in black. Therefore, the binary image can be separated into white areas and black areas. Both the white areas and the black areas may be provided in the unit percent of all pixels of the binary image or in the unit percent of the soil surface depicted in the red-green- blue (RGB)-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images. Alternatively, the white areas and the black areas may be provided in the unit square meters or square millimeters of the soil surface depicted in the red- green-blue (RGB)-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images. In other words, the binary image presents the area ratio between green plant material and the background of the soil with respect to the soil surface depicted in the red-green-blue (RGB)-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images. The soil surface depicted in the red-green-blue (RGB)-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images may have the unit square meters or square millimeters and may be pre-defined and/or defined surface. Additionally, the conversion into binary images may include a distinguishing of crop plants and weed plants by algorithms based on the shape of the crop plants or weed plants and/or the position of the plants in rows. The crop coverage and/or the weed coverage are expressed as a value either as the percentage value or as an absolute surface value.

The term “agricultural field” as used herein is to be understood broadly in the present case and presents any area, i.e. , surface and subsurface, of a soil to be treated by e.g., seeding, planting and/or fertilizing. The agricultural field may be any plant or crop cultivation area, such as a farming field, a plantation, a greenhouse, or the like. A plant may be a crop, a weed, a volunteer plant, a crop from a previous growing season, a beneficial plant or any other plant present on the agricultural field. The agricultural field may be identified through its geographical location or geo-referenced location data. A reference coordinate, a size and/or a shape may be used to further specify the agricultural field. The crop to be grown onto the agricultural field can be arranged in crop rows or in non-crop rows. The arrangement of crop plants into crop rows has the advantage that a growth of the crop plants can be significantly increased because needs (e.g., water amount, sun irradiation and/or nutritional requirement) of the crop plants for an increased grow can be applied to each crop plants in the desired manner. In particular, distributing influences from other crop plants can be significantly reduced such that the growth of the crop plants is increased.

The term “substantially corresponds” as used herein is to be understood broadly in the present case and represents that the at least two, in particular 3-4 subsequent measurement sub-areas (= a measurement cycle) and the application sub-area, in particular the spatially dimension of the at least one measurement sub-are and the application sub-area, correlates with a value of 0.7 to 1 .0, in particular 0.9 to 1 .0.

The term “detection system” as used herein is to be understood broadly in the present case and refers to any system configured to capture and/or determine the threshold value, i.e., the detection system is configured to detect and/or to determine weed coverage, crop coverage, relative weed coverage, averaged weed coverage, averaged crop coverage and/or averaged relative weed coverage at least in the measurement sub-area of the agricultural field. The detection system may, for example, comprise at least one camera unit that takes a, i.e., one, snapshot respectively picture of the ground in front of the application device or the application sub-device like a sprayer or spreader boom at regular time intervals while the applications device is moving, in particular moving through the agricultural field. Alternatively, the detection system may, for example, comprise at least one camera unit that takes at least two snapshots respectively pictures (e.g., 5 or 15 images) of the ground in front of the application device or the application sub-device at the regular time interval while the applications device is moving, in particular moving through the agricultural field. In this context, from each single image of the at least two snapshots, the weed coverage, crop coverage and/or relative weed coverage is determined, respectively analyzed. The at least two determined weed coverages, crop coverages and/or relative weed coverages of the at least two single images, respectively, will be averaged. Based on the weed coverage, crop coverage and/or relative weed coverage of the one snapshot or the averaged weed coverage, the averaged crop coverage and/or averaged relative weed coverage of the at least two snapshots, a decision on the used threshold value is taken. The images can show overlapping areas of the ground or showing non-overlapping areas of the ground. In addition, within the context of the present disclosure, it is also possible that a video stream may be continuously analyzed. The present disclosure is not limited to a particular detection system. For example, camera units may be used that may be arranged near an application sub-device, e.g., the camera units may be mounted on a sprayer boom. Moreover, camera units may be also arranged on separate drone units that fly in front of an application sub-devices and/or device and capture the ground or using a two stage system with drones analyzing in a first flight and spraying in a second flight or eventually in a one-pass drone operation with detection and spot spray during the flight. This may be particular of interest in paddy rice, but not limited to it.

The detection system may also comprise one or more LED lightning/illumination units, wherein the LED lightning/illumination units are, e.g., provided as a flash unit that is directed towards the ground. Such a setup is particularly advantageous since an image may be captured synchronized with a flash triggering. In this way, the ground or the plants may be illuminated sufficiently so that shadowing by plants or parts of plants may be avoided as far as possible. Shadowing, also by sunlight, is often problematic, since such shadows are often wrongly interpreted as green leaf area by image recognition software, e.g., in mobile phone or drone camera applications. Another advantage may be that the agricultural device, a sprayer or spreader can operate with the camera sensors day and night due to the LED lightning/illumination. Further, the detection system may comprise a system for converting red green blue-images and/or the Near Infrared Images and/or the Red Edge Images into binary images as described below in further detail. Furthermore, the detection system may comprise a conversion model.

The term “application sub-area” is to be understood broadly in the present case and refers to the sub-area of the agricultural field on which the agricultural product is to be applied based on the threshold value. In this context, the application sub-area is the area of the agricultural field on which currently, i.e., in a given moment, the agricultural product is to be applied. Therefore, the application sub-area is fully or at least partially below the boom of the application sub-device. The application sub-area may substantially correspond to the at least one measurement sub-area. In this context, the application sub-area and the at least one measurement sub-area may fully or at least partially overlap. A length of the application sub-area is defined by the orientation and/or inclination of one or a plurality of nozzles and the spray diameter of one or a plurality of nozzles being arranged at the boom of the application sub-device but is not limited thereto. The length of the application sub-area is measured parallel to the moving direction of the application device. For instance, the length of the application sub-area may be between 1.0 and 3.0 m, particularly between 1.0 and 2.0 m, but is not limited thereto. A width of the application sub-area is defined by the orientation and/or inclination of one or a plurality of nozzles and the spray diameter of one or a plurality of nozzles being arranged at the boom of the application sub-device but is not limited thereto. Therefore, the width of the application sub-area may be between the spray diameters of only one nozzle up to the sum of the spray diameter of a plurality of nozzles. For instance, the width of the application subarea may be between 0.25 m and 6.0 m but is not limited thereto. The width of the application sub-area is measured perpendicular to the moving direction of the application device.

The term “measurement sub-area” is to be understood broadly in the present case and represent an area, in particular sub-area, on which the weed coverage, the crop coverage and/or the relative weed coverage is provided by or derived from at least one detection system, i.e. , a camera sensor. The measurement sub-area may be defined respectively provided by the shooting range of the camera of the detection system. As already mentioned above, the detection system may, for example, comprise at least one camera unit that takes a, i.e., one, snapshot respectively picture of the ground in front of the application device or the application sub-device at regular time intervals while the applications device is moving, in particular moving through the agricultural field. In this case, the measurement sub-area is defined by the shooting range of the at least one camera taking solely the one snapshot.

As also already mentioned above, alternatively, the detection system may, for example, comprise at least one camera unit that takes at least two snapshots respectively pictures (e.g., 5 or 15 images) of the ground in front of the application device or the application sub-device at the regular time interval while the applications device is moving, in particular moving through the agricultural field. In this case, from each single image of the at least two snapshots, the weed coverage, the crop coverage and/or the relative weed coverage is determined respectively analyzed. The at least two determined weed coverages, crop coverages and/or the relative weed coverages of the at least two single images, respectively, will be averaged. Based on the weed coverage, the crop coverage and/or the relative weed coverage of the one snapshot or the averaged weed coverage, the averaged crop coverage and/or the averaged relative weed coverage of the at least two snapshots, a decision on the used threshold value is taken.

In other words, when the measurement sub-areas are provided by a pre-defined sequence, i.e., a particular number of single images which is used as measurement cycle, e.g., 5 or 15 or 2-5 images, the determined respectively detected weed coverage, crop coverage and/or relative weed coverage provided by the detection system is averaged, wherein the averaged weed coverage, the averaged crop coverage and/or the averaged relative weed coverage are used to take a decision, if the threshold value for applying the agricultural product on the application sub-area need to be changed or not. In other words, each of the images of the pre-selected and/or pre-defined measurement cycle, i.e., 5 or 15 images, is individually analyzed with respect to the weed coverage, crop coverage and/or the relative weed coverage. The weed coverage, the crop coverage and/or the relative weed coverage are averaged.

The threshold is only adapted, if the result in the measurement cycle of a sequence of at least two measurement sub-areas is below or above a pre-set threshold value being provided by the threshold model, which was developed in field trials. Otherwise, the threshold in the following application sub-area remains the same. The actual or current measurement sub-area refers to the measurement sub-area which is currently measured, i.e., the at least one camera takes at least one image. The previous measurement sub- are refers to a measurement sub-area which have been already measured, i.e., the at least one camera has already taken at least one image. In this case, the measurement sub-area is defined by the shooting range of the at least one camera taking the at least two snapshots. The shooting range of the at least one camera of the detection system may be affected by the orientation and/or inclination of the at least one camera. Therefore, the length and/or width of the measurement sub-area are defined by the width of the application sub-device, the shooting range, the measuring rate of the one or more cameras, the sampling rate of the one or more cameras, the cycle duration of the measurements of the one or more cameras but is not limited thereto. Dependent on the timing of the sampling rate in relation to a driving speed of the application device different images may overlap. The sampling rate may be provided as a timing for the number of images taken per time unit. The time unit may correspond to the time period of the sequence of the images. In order to form a measurement sub-area an actual/current and/or one or more previous measurement sub-area(s) and/or their value(s) are to be considered. In an example an average value for the sequence of measurement sub-areas may be taken in order to determine an adapted threshold if the present threshold needs to be changed. For instance, the measurement sub-area may have a width between 0.25 m and 6.0 m and a length between 1 .0 and 3 m, particularly between 1 .0 and 2.0 m, but is not limited thereto. The width is perpendicular to the moving direction of the application device. The length is parallel to the moving direction of the application device.

Alternatively, or additionally, the measurement sub-area may be a region of interest (ROI), i.e. , a section or part of the shooting range one camera or a plurality of cameras. The term “Region of interest (ROI)” refers to an area in the camera image for which the weed coverage and/or the crop coverage is detected, measured and processed. The “region of interest” may be a rectangular area in the single image of the camera of the detection system but is not limited thereto.

In each measurement cycle the camera is continuously switched on and off order to sample the field. Dependent on the sample frequency or the angle of the camera, the measurement sub areas may overlap and/or substantially seamlessly are joint together. Application sub-areas may be former measurement sub-areas.

The term “weed” as used herein is to be understood broadly in the present case and refers to any harmful or considered harmful plant. Notably, in a bumdown modus, e.g., when clearing the agricultural field for the growing season, also volunteer plants emerging from previous crop seasons may be also considered as weed plants. As a result, in such burndown modus all plants may be considered as weed plants. During the burndown modus, a total herbicide, in particular a so-called bumdown herbicide, is applied on all plants regardless of whether it is a crop plant or a weed. Therefore, by a burndown modus all plants on the agricultural field are controlled respectively killed.

The term “weed coverage data” as used herein is to be understood broadly in the present case and represents any data indicating the weed coverage of an agricultural field. The weed coverage represents the area of the agricultural field which is covered by the leaves of weed plants. The weed coverage may be the percentage value on a soil surface related to a defined soil surface. For instance, the weed coverage may be 2.0 percent of one square meter soil surface. Alternatively, the weed coverage may be the proportion in square millimeter per square meter of the soil surface covered by weeds. Weed leaves of the weed plants may be distinguished from the crop plants by algorithms via a row identification and/or shape recognition. The weed coverage may be measured by converting a red green blue-image and/or the Near Infrared Image and/or the Red Edge Image and/or multi-spectral images into binary images as mentioned above.

The term “crop coverage data” as used herein is to be understood broadly in the present case and represents any data indicating the crop coverage of an agricultural field. The crop coverage represents the area of the agricultural field which is covered by the leaves of crop plants. The crop coverage may be the percentage value on a soil surface related to a defined soil surface. For instance, the crop coverage may be 2.0 percent of one square meter soil surface. Alternatively, the crop coverage may be the proportion of square millimeter per square meter of the soil surface covered by the crops. Crop leaves of the crop plants may be distinguished from the weed plants by algorithms via a row identification and/or shape recognition. The crop coverage may be measured by converting a red green blue-image and/or the Near Infrared Image and/or the Red Edge Image and/or multi-spectral images into binary images as mentioned above.

The term “relative weed coverage” as used herein is to be understood broadly and represents a quotient of the weed coverage and the sum of the weed coverage and the crop coverage. The relative weed coverage may be used to determine the threshold values. The relative weed coverage may be used for setting a threshold value, because it has been found that there is an interaction of a crop growth stage, respectively crop size or crop coverage, and weed growth and herewith the weed coverage due to an effect of competition for space, nutrients, light and water. If the ratio between the crop coverage and the weed coverage is more on the site of the crop coverage, it may compete better with growing weeds and therefore the threshold value, e.g., with respect to herbicide product applications, may be higher. The relative weed coverage may be provided according to the following formula:

wherein Lw is the relative weed coverage, Lweed is the weed coverage and L_crop is the crop coverage. As mentioned above, the crop coverage and/or the weed coverage are expressed as a value either as the percentage value or as an absolute value but is not limited thereto.

The term “application device” as used herein is to be understood broadly in the present case and represents any device being configured to apply an agricultural product onto the soil of an agricultural field using respective application sub-devices. The application device may be configured to traverse the agricultural field. The application device may be a ground or an air vehicle, e.g., a rail vehicle, a robot, an aircraft, an unmanned aerial vehicle (UAV), a drone, or the like. The application device can be an autonomous or a non-autonomous application device.

The term “application sub-devices” used herein is to be understood broadly in the present case and comprises any sub-devices configured to be controlled by respective control data when applying the agricultural product on the agricultural field. The application subdevice may be sprayer, in particular a smart sprayer, comprising a boom and a plurality of pulse width modulation (PWM) nozzles and/or electronically controlled multi nozzle heads or other variable rate application (VRA) devices, for example Vortex nozzles, but is not limited thereto. The application sub-device is able to operate on/off spraying with single fixed rate but also with variable rates (e.g., when additional parameters, as the weed size, are used additionally aside of the weed coverage indicated threshold to trigger the spot application). In an example, the application sub-device is a smart sprayer comprising a boom and a plurality of spray nozzles mounted in a distance of 25 or 50 cm on a sprayer boom, e.g., most common in the US are 15, 20 or 30 inch spacing. Additionally, or alternatively, the application sub-device may be a spreader with single nozzle or section-outlet control but is not limited thereto.

In case the sprayer has a two or more tank system and is equipped with two or more spray lines on the boom, the camera systems and/or detection system could be used at the same time to run (a) the spot spraying based on weed coverage thresholds with the first spray line and (b) the VRA spraying on the second spray line based green area index (GAI) driven rates, but is not limited thereto.

The term “spot application/spot spray” used herein is to be understood broadly in the present case and refers to any a method for punctual and/or targeted treating, in particular applying an agricultural product on a hyperlocal level in an agricultural field.

The term “control data” as used herein is to be understood broadly in the present case and presents any data being configured to operate and control an application device or application sub-device. The control data are provided by a control unit and may be configured to control one or more technical means of the application device, e.g., the drive control, but is not limited thereto.

The term “machine learning algorithm” may comprise decision trees, naive bayes classifications, nearest neighbors, neural networks, convolutional or recurrent neural networks, generative adversarial networks, support vector machines, linear regression, logistic regression, random forest and/or gradient boosting algorithms. Particularly, the result of a machine learning algorithm is used to adjust a threshold adapting and/or setting logic. Particularly, the machine learning algorithm is organized to process an input having a high dimensionality into an output of a much lower dimensionality. Such a machine learning algorithm is termed “intelligent” because it is capable of being “trained.” The algorithm may be trained using records of training data. A record of training data comprises training input data and corresponding training output data. The training output data of a record of training data is the result that is expected to be produced by the machine learning algorithm when being given the training input data of the same record of training data as input. For instance, the training data for the machine learning algorithm may be historical weed distribution data. The deviation between this expected result and the actual result produced by the algorithm is observed and rated by means of a “loss function”. This loss function is used as feedback for adjusting the parameters of the internal processing chain of the machine learning algorithm. For example, the parameters may be adjusted with the optimization goal of minimizing the values of the loss function that result when all training input data is fed into the machine learning algorithm and the outcome is compared with the corresponding training output data. The result of this training is that given a relatively small number of records of training data as “ground truth”, the machine learning algorithm is enabled to perform its job well for a number of records of input data that higher by many orders of magnitude. Records of weed coverage maps, weed patch distributions etc. during crop rotations can also be also an important factor to influence threshold settings.

The term “providing” as used herein is to be understood broadly in the present case and represents any providing, receiving, querying, measuring, calculating, determining, transmitting of data, but is not limited thereto. Data may be provided by a user via a user interface, depicted and/or shown to a user by a display, and/or received from other devices, queried from other devices, measured other devices, calculated by other device, determined by other devices and/or transmitted by other devices.

The term “data” as used herein is to be understood broadly in the present case and represents any kind of data. Data may be single numbers and/or numerical values, a plurality of a numbers and/or numerical values, a plurality of a numbers and/or numerical values being arranged within a list, 2 dimensional maps or 3 dimensional maps, but are not limited thereto.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the method further comprising providing a base threshold value representing a base threshold, wherein setting the threshold value for applying the agricultural product comprises setting the threshold value based on the base threshold value and the coverage data in the measurement sub-areas by utilizing the threshold model, in particular setting the threshold value by adapting the base threshold value based on the threshold value provided by the threshold model to obtain an adapted threshold value.

The term “base threshold” may be understood as a threshold which is provided for the entire agricultural field or at least for an entire boom width. The base threshold may be determined based on historical data, satellite data other data sources providing a data for an agricultural field or the parts of an agricultural field which underlies an application by an application boom.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the threshold model is adapted to provide an adapted threshold value for a respective application sub-area if the coverage data for the measurement subareas has a predetermined relation.

A predetermined relation may be seen as a particular pattern or tendency of the coverage of within the measurement sub-areas. The predetermined relation may be a deviation from a predetermined value, a predetermined strong change of the coverage or a predetermined deviation from a floating average but is not limited thereto. The predetermined relation may also be threshold of an average of coverage in the measurement sub-areas and/or a predetermined gradient in the coverage in the measurement sub-areas.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the predetermined relation is a relative coverage in the preceding numbers of measurement sub-areas. In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the predetermined relation is a predetermined gradient of coverage in the preceding numbers of measurement sub-areas.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, providing coverage data comprises coverage data selectively for a plurality of sections of an application boom, providing coverage data comprises providing coverage data for measurement sub-areas for each of said sections of the application boom, wherein the detection system is adapted to detect coverage in the measurement sub-areas for each of said sections of the application boom while an application device is moving through the agricultural field; wherein the threshold model is configured to provide a threshold value for a respective application sub-area in each of said sections of the application boom based on the provided coverage data in the measurement sub-areas of the respective one of said sections of the application boom; wherein setting the threshold value for applying the agricultural product on a respective application sub-area in each of said sections of the application boom is based on the coverage data in the measurement sub-areas in the respective one of said sections of the application boom by utilizing the threshold model.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the threshold model is configured to provide a threshold value for a respective application sub-area in each of said sections of the application boom based on the provided coverage data in the measurement sub-areas of the respective one of said sections of the application boom and the provided coverage data in the measurement sub-areas of adjacent sections of the application boom; wherein setting the threshold value for applying the agricultural product on a respective application sub-area in each of said sections of the application boom is based on the coverage data in the measurement sub-areas in the respective one of said sections of the application boom and coverage data in the measurement sub-areas in the adjacent sections of the application boom by utilizing the threshold model. Adjacent sections of an application boom are those sections which lay in the beside the section in question. When considering the relative coverage between a section and an adjacent section thereto, a relation ma be determined between the coverage in one section and a coverage in the adjacent section, i.e. , the section beside the one section. This may apply also to both sides. Upon the relative coverage or extension of the relative coverage over a predetermined threshold, the application threshold may be adapted.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the at least one measurement sub-area substantially corresponds to the application sub-area. In other words, the application sub-area substantially corresponds to the measurement sub-area. This means that the coverage data of the current sub-area, i.e. the current detection area, e.g. in a camera's field of view is used to determine the threshold for the current sub-area.

In an embodiment of the computer-implemented method for dynamically adapting and/or setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the at least one measurement sub-area comprises at least one previous measurement sub-area (averaged for decision) , wherein the at least one previous measurement sub-area and the application sub-area are located at different positions in the agricultural field. In other words, the application sub-area is spatially subsequent in a moving direction of the application device moving through the agricultural field, in particular direct subsequent to the at least one measurement subarea, wherein in particular the at least one measurement sub-area is spatially continuous. In other words, the averaged values of a measurement sub-area comprises at least one previous measurement sub-area, wherein the weed coverage data take into account weed coverage data for the at least one previous measurement sub-area for a decision to change the actual/current threshold on a given camera sensor unit. This means that not only the coverage data of the current detection area, e.g. a camera's field of view, is used to determine the threshold value, but also the coverage data of the previous subarea, which may be held available in a memory, as it has already been sprayed at the time of the decision for the current sub-area. Further, also the coverage data of the sub- area or a plurality of sub-areas before the previous sub-area used, which also may be held available in a memory, to determine the application threshold. The coverage data of the different sub-areas may be averaged to compare to the preset threshold for a decision.

In an embodiment of the computer-implemented method for dynamically setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the at least one measurement sub-area comprises an actual/current measurement sub-area and at least one previous measurement sub-area (a measurement cycle), wherein the at least one measurement sub-area and the application sub-area at least partially overlap. In other words, one of the at least one measurement sub-areas and the application sub-area substantially spatially corresponds to each other and the rest of the at least one measurement sub-areas are spatially different to each other and different to the application sub-area. The application sub-area is spatially subsequent in a moving direction of the application device moving through the agricultural field, in particular direct subsequent to the rest of the at least one measurement sub-area. The at least one measurement sub-area is spatially continuous. In other words, the measurement sub-area comprises one actual/current measurement sub-area and at least one previous measurement sub-area, wherein the weed coverage data take into account weed coverage data for the actual/current measurement sub-area and weed coverage data for the at least one previous measurement sub-area for a decision to change the actual/current threshold on a given camera sensor unit.

In an embodiment of the computer-implemented method for dynamically adapting and/or setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the method may further comprise: providing weed growth stage data, weed size data, weed density data, weed number data comprising information about the weeds on a predefined surface data e.g., per ha, weed location data e.g., GPS-positions, GNSS-positions and distance of the weeds to a crop row, crop growth stage data, crop size data, crop density data, number of crop plants on a predefined surface data e.g., per ha, and/or weed species data; wherein the provided threshold model may be further configured to provide a threshold value further based on weed growth stage data, weed size data, weed density data, weed number data comprising information about the weeds on a predefined surface data e.g., per ha, weed location data e.g., GPS-positions, GNSS-positions and distance of the weeds to a row, crop growth stage data, crop size data, crop density data, number of crop plants on a predefined surface data e.g., per ha, crop stage and/or weed species data; setting and/or adapting the threshold value for applying the agricultural product on the application sub-area may be further based on weed growth stage data, weed size data, weed density data, weed number data comprising information about the weeds on a predefined surface data e.g., per ha, weed location data e.g., GPS-positions and distance of the weeds to a row, crop growth stage data, crop size data, crop density data, number of crop plants on a predefined surface data e.g., per ha, crop stage and/or weed species data.

In other words, the method further comprises the steps of: detecting a crop coverage in the measurement sub-area by the at least one detection system while the application device is moving through the agricultural field; generating crop coverage data for the measurement sub-area from the detected weed coverage; providing the crop coverage data for the measurement sub-area, wherein the threshold model is further configured to generate a threshold value based on the provided averaged weed coverage data and the provided averaged crop coverage data from at least two, in particular 3-4 subsequent measurement sub-areas; utilizing the threshold model for generating the adapted threshold value based on the provided averaged weed coverage data and the provided averaged crop coverage data from the at least two, in particular 3-4 subsequent measurement sub-areas.

In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the method may further comprise: providing identification sub-devices configured for identifying problem weeds, providing a threshold model configured to provide a threshold value at least based on the provided weed coverage data and the identified problem weeds in the at least two subsequent measurement sub-areas; setting and adapting the threshold value for applying the agricultural product on the application sub-area based on the averaged weed coverage data and the identified problem weeds in the at least two subsequent measurement sub-areas by utilizing the threshold model.

In this context, the problem weeds may be identified by image recognition, in particular by a shape based identification. The problem weeds may be any weeds with a high seed potential and herbicide resistance issues. For instance, problem weeds may be Amaranthus spp., but is not limited thereto. The identification of problem weeds may trigger spot sprays independent from the set threshold value. In other words, as soon as a problem weed is detected, the set threshold value e.g., based on the weed coverage is practically overwritten and a spraying operation is initiated. Exemplary, the application rate in a case when a problem weed is identified may be pre-determined respectively preset. The pre-determined or pre-set application rates may consider the size of the problem weeds but is not limited thereto.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the method may further comprise: providing crop coverage data for the at least measurement sub-area wherein the crop coverage data are provided by the at least one detection system, wherein the detection system is further adapted to detect crop coverage in the at least two subsequent measurement sub-areas while the application device is moving through the agricultural field; wherein the provided threshold model is further configured to provide an adapted threshold value at least based on the provided averaged weed coverage data and the provided averaged crop coverage data from at least two subsequent measurement subareas; setting the threshold value for applying the agricultural product on the application sub-area based on the weed coverage data and the crop coverage data by utilizing the threshold model.

In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the method may further comprise: providing crop coverage data for the at least measurement sub-area wherein the crop coverage data are provided by the at least one detection system, wherein the detection system is further adapted to detect crop coverage in the at least two subsequent measurement sub-areas while the application device is moving through the agricultural field; wherein relative weed coverage data are derived from the weed coverage data and the crop coverage data by the at least one detection system; wherein the provided threshold model is further configured to provide a threshold value at least based on the derived relative weed coverage data; setting the threshold value for applying the agricultural product on the application sub-area based on the relative weed coverage data by utilizing the threshold model.

In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the method may further comprise: averaging of the provided weed coverage data of at least two measurement subareas, the provided crop coverage data of at least two measurement sub-areas and/or the relative weed coverage data of at least two measurement sub-areas, setting the threshold value for applying the agricultural product on the application sub-area based on the averaged weed coverage data, the averaged crop coverage data and/or the averaged relative weed coverage data by utilizing the threshold model.

In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the threshold model comprises at least one lookup table in which the relationship between a weed coverage and a threshold value is provided or determined by an algorithm; the relationship between an averaged weed coverage and a threshold value is provided or determined by an algorithm; the relationship between a weed coverage, a crop coverage and a threshold value is provided or determined by an algorithm; or the relationship between an averaged weed coverage, an averaged crop coverage and a threshold value is provided or determined by an algorithm; or the relationship between a relative weed coverage and a threshold value is provided or determined by an algorithm; the relationship between an averaged relative weed coverage and a threshold value is provided or determined by an algorithm.

Such lookup tables may be based on the results of a number of large scale field trials, which may allow for specific crops, for certain growth stages to read out the best threshold value. Therefore, a lookup table for the purpose of a field sub-area specific threshold setting on nozzle level or section level or whole boom level may comprise:

• for a certain crop and crop growth stage, an optimal weed coverage, e.g., in percent or square millimeter, per sub-area, e.g., per m²; and/or

• for a certain crop and crop growth stage, an optimal relative value of crop and weed coverage; and/or

• in case of the bumdown modus for a certain weed and/or vegetation coverage and weed size an optimal threshold based on weed and/or vegetation coverage value. The camera sensor system is than capturing any green surface of any vegetation on a field. Therefore often the term “vegetation management” is used. A vegetation coverage, in particular a vegetation coverage value, may comprise at least one of a weed coverage and crop coverage. In other words, any device adapted to distinguish between weed and/or crop may be switched off and/or may not be present.

The use of defoliants or desiccants in crops, as for example cotton, can be seen as a special case of the bumdown mode.

In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the step of setting and/or adapting the threshold value while applying the agricultural product on the application sub-area comprises: providing a base threshold value for the application sub-area for the agricultural field; setting and/or adapting the threshold value for applying the agricultural product on the application sub-area based on the base threshold value and the weed coverage data, crop coverage data, relative weed coverage data, averaged weed coverage data, averaged crop coverage data and/or averaged relative weed coverage data by utilizing the threshold model, wherein the threshold model is configured to provide a threshold value at least based on the provided base threshold value and the weed coverage data, crop coverage data, relative weed coverage data, averaged weed coverage data, averaged crop coverage data and/or averaged relative weed coverage data for the measurement sub-area. Such a base threshold value may be provided field-specific or also field sub-area-specific.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the base threshold value for a given field may be determined based on one or more of the following parameters and made available to the sprayer system either via an algorithm or a look-up table crop species; crop growth stage; planting row width; precipitation within a predefined time window before applying the agricultural product; weed species; weed growth stage; resistances of weed species; biomass distribution;

- crop/weed competitiveness;

- intermediate cover crop;

- cultivation method;

- use of slurry, farmyard manure or biogas substrate; and/or

- previous herbicide use in the crop concerned, particularly of a residual herbicide in spray programs as important modulator of the weed coverage.

In this context, the base threshold value is a threshold being pre-set, pre-determined and/or determined for the whole agricultural field, i.e. , field-level, or for the application sub-areas, the base threshold value is adapted during the application of the agricultural product to the weed and crop heterogeneity on a single nozzle or boom section level. In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the at least one detection system comprises at least one camera unit for capturing image data of the at least two subsequent measurement sub-areas of the agricultural field. Such a camera may be assigned to one or more application sub-devices. In an example, an application device may comprise multiple cameras, wherein a camera is assigned to a specific application sub-devices, e.g., one nozzle or a specific section of a sprayer boom.

In an embodiment of the computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the at least one camera unit is configured to provide red green blue-images and/or Near Infrared Images and/or Red Edge Images and/or multi-spectral images, and the at least one detection system is adapted to detect or calculate weed coverage or crop and weed coverage based on the red green blue-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images.

In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the red green blue-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images are converted into binary images, and the at least one detection system is configured to detect weed coverage or crop and weed coverage based on the binary images. Optionally, the detection system may additionally detect certain problem weeds based on the shapes of the binary or multispectral images.

In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the at least one detection system may be assigned to one or more application sub-devices configured to apply the agricultural product on the sub-area, wherein the application sub-devices may be nozzle units and/or boom sections of a sprayer boom of a sprayer allowing an application sub-area specific setting of thresholds. In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the agricultural product may be a crop protection product, particularly an herbicide product, a foliar herbicide product, a total herbicide, a herbicide with soil and leaf activity and/or a biological herbicide, a burndown herbicide, defoliant, desiccants and/or another pesticide product etc.

In an embodiment of the computer-implemented method for setting and/or adapting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application, the method may further comprise: providing control data for controlling at least one application sub-devices of an application device at least based on the set threshold value for applying the agricultural product on the sub-area of the agricultural field. In an example, control data for all application sub-devices of an application device are provided such that threshold values may be adapted across a sprayer boom on a nozzle or boom section level while driving through the agricultural field when spraying.

The process can be exemplarily described as follows: A field to be treated is first registered in an on-line data base with the details of the location, the crop and the field history. This delivers an optimized single base threshold for the whole field for on/off decisions of a spot sprayer. Optimize e.g. means to get the highest savings of herbicides while maintaining a farmer accepted weed control. The crop species (e.g. sugar beet or corn) defines the value range of useable weed thresholds. The range of useful threshold values differs by crop due to the crop specific competitiveness to weed infestations e.g. for sugar beet the useable range of thresholds is much lower than in corn. Other parameters as the previous crop, the cultivation technique, the use organic fertilizers, intermediate crops etc. and the especially the precipitation in the weeks before a given crop was drilled, define the optimum weed threshold value which is based on an algorithm forecasted weed cover. When the sprayer enters first the field specific base threshold is used on all camera I sensor positions. While passing through the field on each camera sensor position the measured weed cover values are constantly compared with the base threshold. If the camera sensors detect a bigger differentiation from the initially forecasted weed coverage an adjustment of the threshold for the on/off decision for e.g. the herbicide spot spray is done. Afterwards the system compares the detected coverage with the last threshold used on each camera sensor position (a measurement cycle) for possible larger discrepancies to check if the threshold needs to be adapted.

For example the coverage of e.g. weeds in a region of interest (ROI) the camera sensor (mounted on the sprayer boom looking forward) enters (i.e. before the boom) is determined and averaged with the values of the last, e.g. the last 2 or 3 measurements. If this value differs significantly from the previously used threshold an adjustment is done. It is to be noted that the detected cover, e.g. weed cover can be quite different on each camera sensor position mounted on the spray boom. This means the applicator or sprayer reacts to subarea specific weed cover differences caused by e.g. weed patches due to an adaptation of the threshold which is an improvement of the basis for e.g. an on/off decisions on each camera sensor position.

One use case of the invention are row crops which are usually drilled with 25-75 cm row distance such as corn, soy, sunflowers, sugar beet, potatoes etc. The basis of the threshold variation for whole fields may be a look up table or an algorithm developed in hundreds of field trials for row crops. The development showed that certain field histories ‘produce’ a certain e.g. weed coverage requiring a certain threshold for a spray decision. For the present invention the observation that there is a direct link of the optimum threshold for e.g. a weed coverage found in a field can be used, even if the field history parameters are not known. This fact is now used to vary and adapt the thresholds on each camera sensor position independently.

This invention delivers a unique, sub-area specific weed threshold optimization (high resolution) independently for each camera sensor and nozzle position to further optimize e.g. herbicide savings over single thresholds used for the whole field. Different threshold in sub-areas in driving direction as well transversally to it (along the spray boom) are possible.

BRIEF DESCRIPTION OF THE DRAWINGS

In the following, the present disclosure is further described with reference to the enclosed figures: Figure 1 illustrates example embodiments of a centralized and a decentralized computing environment with computing nodes;

Figure 2 illustrates example embodiments of a centralized and a decentralized computing environment with computing nodes;

Figure 3 illustrates an example embodiment of a distributed computing environment;

Figure 4 illustrates a flow diagram of a computer-implemented method for providing a threshold value for applying an agricultural product on an agricultural field e.g. based on averaged weed coverage data of at least two measurement sub areas;

Figure 5 illustrates a system for providing a threshold value for applying an agricultural product on an agricultural field;

Figure 6 illustrates another flow diagram of a computer-implemented method for providing a threshold value for applying an agricultural product on an agricultural field, e.g., based on averaged weed and crop coverage data of at least two measurement sub areas;

Figure 7 illustrates another system for providing a threshold value for applying an agricultural product on an agricultural field;

Figure 8 illustrates an application device for applying an agricultural product on a sub-area of an agricultural field in a spot spray application, e.g., using adapted, optimized thresholds based on measurements of at least two measurement sub-areas, independent for each camera sensor and nozzle on the sprayer boom; Figure 9 illustrates exemplarily the different possibilities to receive and process field data, in particular weed coverage data.

DETAILED DESCRIPTION OF EMBODIMENT

The following embodiments are mere examples for implementing the method, the system, the apparatus, or application device disclosed herein and shall not be considered limiting.

Figures 1 to 3 illustrate different computing environments, central, decentral, and distributed. The methods, apparatuses, computer elements etc. of this disclosure may be implemented in decentral or at least partially decentral computing environments. In particular, for data sharing or exchange in ecosystems of multiple players different challenges exist. Data sovereignty may be viewed as a core challenge. It can be defined as a natural person’s or corporate entity’s capability of being entirely self-determined with regard to its data. To enable this particular capability, related aspects, including requirements for secure and trusted data exchange in business ecosystems, may be implemented across the chemical value chain. In particular, chemical industry requires tailored solutions to deliver chemical products in a more sustainable way by using digital ecosystems. Providing, determining, or processing of data may be realized by different computing nodes, which may be implemented in a centralized, a decentralized or a distributed computing environment.

Figure 1 illustrates an example embodiment of a centralized computing system 20 comprising a central computing node 21 (filled circle in the middle) and several peripheral computing nodes 21.1 to 21. n (denoted as filled circles in the periphery). The term “computing system” is defined herein broadly as including one or more computing nodes, a system of nodes or combinations thereof. The term “computing node” is defined herein broadly and may refer to any device or system that includes at least one physical and tangible processor, and/or a physical and tangible memory capable of having thereon computer-executable instructions that are executed by a processor. Computing nodes are now increasingly taking a wide variety of forms. Computing nodes may, for example, be handheld devices, production facilities, sensors, monitoring systems, control systems, appliances, laptop computers, desktop computers, mainframes, data centers, or even devices that have not conventionally been considered a computing node, such as wearables (e.g., glasses, watches, or the like). The memory may take any form and depends on the nature and form of the computing node.

In this example, the peripheral computing nodes 21.1 to 21 .n may be connected to one central computing system (or server). In another example, the peripheral computing nodes 21.1 to 21. n may be attached to the central computing node via, e.g., a terminal server (not shown). The majority of functions may be carried out by or obtained from the central computing node (also called remote centralized location). One peripheral computing node 21. n has been expanded to provide an overview of the components present in the peripheral computing node. The central computing node 21 may comprise the same components as described in relation to the peripheral computing node 21 .n.

Each computing node 21 , 21.1 to 21. n may include at least one hardware processor 22 and memory 24. The term “processor” may refer to an arbitrary logic circuitry configured to perform basic operations of a computer or system, and/or, generally, to a device which is configured for performing calculations or logic operations. In particular, the processor, or computer processor may be configured for processing basic instructions that drive the computer or system. It may be a semiconductor based processor, a quantum processor, or any other type of processor configures for processing instructions. As an example, the processor may comprise at least one arithmetic logic unit ("ALU"), at least one floatingpoint unit ("FPU)", such as a math coprocessor or a numeric coprocessor, a plurality of registers, specifically registers configured for supplying operands to the ALU and storing results of operations, and a memory, such as an L1 and L2 cache memory. In particular, the processor may be a multicore processor. Specifically, the processor may be or may comprise a Central Processing Unit ("CPU"). The processor may be a (“GPU”) graphics processing unit, (“TPU”) tensor processing unit, ("CISC") Complex Instruction Set Computing microprocessor, Reduced Instruction Set Computing ("RISC") microprocessor, Very Long Instruction Word ("VLIW') microprocessor, or a processor implementing other instruction sets or processors implementing 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 devices described herein may be implemented as software in a DSP, in a micro-controller, or in any other side-processor or as hardware circuit within an ASIC, CPLD, or FPGA. It is to 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.

The memory 24 may refer to a physical system memory, which may be volatile, nonvolatile, or a combination thereof. The memory may include non-volatile mass storage such as physical storage media. The memory may be a computer-readable storage media 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 disk or any other physical and tangible storage medium which can be used to store desired program code means in the form of computer-executable instructions or data structures and which can be accessed by the computing system. Moreover, the memory may be a computer-readable media that carries computer-executable instructions (also called transmission media). Further, upon reaching various computing system components, program code means in the form of computer-executable instructions or data structures can be transferred automatically from transmission media to storage media (or vice versa). For example, computer-executable instructions or data structures received over a network or data link can be buffered in RAM within a network interface module (e.g., a “NIC”), and then eventually transferred to computing system RAM and/or to less volatile storage media at a computing system. Thus, it should be understood that storage media can be included in computing components that also (or even primarily) utilize transmission media.

The computing nodes 21 , 21.1 to 21. n may include multiple structures 26 often referred to as “executable component”, “executable instructions”, “computer-executable instructions” or “instructions”. For instance, memory 24 of the computing nodes 21 , 21.1 to 21. n may be illustrated as including executable component 26. The term “executable component” or any equivalent thereof may be the name for a structure that is well understood to one of ordinary skill in the art in the field of computing as being a structure that can be software, hardware, or a combination thereof or which can be implemented in software, hardware, or a combination thereof. For instance, when implemented in software, one of ordinary skill in the art would understand that the structure of an executable component includes software objects, routines, methods, and so forth, that is executed on the computing nodes 21 , 21.1 to 21. n, independent on whether such an executable component exists in the heap of a computing node 21 , 21.1 to 21 .n, or whether the executable component exists on computer-readable storage media. In such a case, one of ordinary skill in the art will recognize that the structure of the executable component exists on a computer-readable medium such that, when interpreted by one or more processors of a computing node 21 , 21.1 to 21. n (e.g., by a processor thread), the computing node 21 , 21.1 to 21 n is caused to perform a function. Such a structure may be computer-readable directly by the processors (as it is the case if the executable component were binary). Alternatively, the structure may be structured to be interpretable and/or compiled (whether in a single stage or in multiple stages) so as to generate such binary that is directly interpretable by the processors. Such an understanding of example structures of an executable component is well within the understanding of one of ordinary skill in the art of computing when using the term “executable component”. Examples of executable components implemented in hardware include hard-coded or hard-wired logic gates, that are implemented exclusively or near-exclusively in hardware, such as within a field- programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or any other specialized circuit. In this description, the terms “component”, “agent”, “manager”, “service”, “engine”, “module”, “virtual machine” or the like are used synonymous with the term “executable component”.

The processor 22 of each computing node 21 , 21.1 to 21. n may direct the operation of each computing node 21 , 21.1 to 21. n in response to executed computer-executable instructions that constitute an executable component. For example, such computerexecutable instructions may be embodied on one or more computer-readable media that form a computer program product. The computer-executable instructions may be stored in the memory 24 of each computing node 21 , 21.1 to 21. n. Computer-executable instructions comprise, for example, instructions and data which, when executed at a processor 21 , cause a general purpose computing node 21 , 21.1 to 21 .n, special purpose computing node 21 , 21.1 to 21. n, or special purpose processing device to perform a certain function or group of functions. Alternatively, or in addition, the computerexecutable instructions may configure the computing node 21 , 21.1 to 21 .n to perform a certain function or group of functions. The computer executable instructions may be, for example, binaries or even instructions that undergo some translation (such as compilation) before direct execution by the processors, such as intermediate format instructions such as assembly language, or even source code.

Each computing node 21 , 21.1 to 21.n may contain communication channels 28 that allow each computing node 21.1 to 21 .n to communicate with the central computing node 21 , for example, a network (depicted as solid line between peripheral computing nodes and the central computing node in Figure 1). A “network” may be defined as one or more data links that enable the transport of electronic data between computing nodes 21 , 21.1 to 21 .n and/or modules and/or other electronic devices. When information is transferred or provided over a network or another communication connection (either hardwired, wireless, or a combination of hardwired or wireless) to a computing node 21 , 21 .1 to 21. n, the computing node 21 , 21.1 to 21. n properly views the connection as a transmission medium. Transmission media can include a network and/or data links which can be used to carry desired program code means in the form of computer-executable instructions or data structures and which can be accessed by a general-purpose or special-purpose computing nodes 21 , 21.1 to 21 .n. Combinations of the above may also be included within the scope of computer-readable media.

The computing node(s) 21 , 21.1 to 21 .n may further comprise a user interface system 25 for use in interfacing with a user. The user interface system 25 may include output mechanisms 25A as well as input mechanisms 25B. The principles described herein are not limited to the precise output mechanisms 25A or input mechanisms 25B as such and will depend on the nature of the device. However, output mechanisms 25A might include, for instance, displays, speakers, displays, tactile output, holograms and so forth. Examples of input mechanisms 25B might include, for instance, microphones, touchscreens, holograms, cameras, keyboards, mouse or other pointer input, sensors of any type, and so forth. Figure 2 illustrates an example embodiment of a decentralized computing environment 30’ with several computing nodes 21. T to 21 .n’ denoted as filled circles. In contrast to the centralized computing environment 20 illustrated in Figure 1 , the computing nodes 21 .1 to 21. n of the decentralized computing environment are not connected to a central computing node 21 and are thus not under control of a central computing node. Instead, resources, both hardware and software, may be allocated to each individual computing node 21.1 to 21. n (local or remote computing system) and data may be distributed among various computing nodes 21.1 to 21 .n to perform the tasks. Thus, in a decentral system environment, program modules may be located in both local and remote memory storage devices. One computing node 21 has been expanded to provide an overview of the components present in the computing node 21. In this example, the computing node 21 comprises the same components as described in relation to Figure 1.

Figure 3 illustrates an example 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 realized through virtualization of physical computing resources. One example of distributed computing is cloud computing. “Cloud computing” may refer a model for enabling on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services). When distributed, cloud computing environments may be distributed internationally within an organization and/or across multiple organizations. In this example, the distributed cloud computing environment 40 may contain the following computing resources: mobile device(s) 42, applications 43, databases 44, data storage and server(s) 46. The cloud computing environment 40 may be deployed as public cloud 47, private cloud 48 or hybrid cloud 49. A private cloud 47 may be owned by an organization and only the members of the organization with proper access can use the private cloud 48, rendering the data in the private cloud at least confidential. In contrast, data stored in a public cloud 48 may be open to anyone over the internet. The hybrid cloud 49 may be a combination of both private and public clouds 47, 48 and may allow to keep some of the data confidential while other data may be publicly available.

Figure 4 illustrates a flow diagram of a computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application. In a first step S100, weed coverage data are provided by a camera sensor detection system for measurement sub-areas. The values are averaged for at least two, in particular 3-4 measurement subareas.

The weed coverage data are provided by at least one detection system, wherein the detection system allows to detect weed coverage at least in the at least one, in particular in the at least two measurement sub-areas while an application device is moving through the agricultural field.

In a second step S200 a threshold model is provided which is configured to provide a threshold value at least based on the provided weed coverage data in the at least one measurement sub-area. , The measured, averaged value is compared to the present threshold in-use to decide if a change is needed based on a threshold model or algorithm. The threshold model comprises at least one lookup table, in which a relationship between the weed coverage and the threshold value is provided. In a third step S300, the threshold value is set for applying the agricultural product on the application sub-area based on the weed coverage data in the at least one measurement sub-area by utilizing the threshold model.

Figure 5 illustrates a system 10 for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application. The system comprises a weed coverage data providing unit 11 configured to provide weed coverage data for at least one measurement sub-area, wherein the weed coverage data are provided by at least one detection system 12. The detection system 12 is adapted to detect weed coverage at least in the at least one measurement sub-area while an application device is moving through the agricultural field. A threshold model providing unit 13 is configured to provide a threshold model configured to provide a threshold value at least based on the provided weed coverage data in the at least one measurement subarea. A threshold value setting unit 14 is configured to set the threshold value for applying the agricultural product on the application sub-area based on the weed coverage data in the at least one measurement sub-area by utilizing the threshold model.

Figure 6 illustrates another flow diagram of a computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application. In a first step S101 , weed coverage data are provided for at least one measurement sub-area. The weed coverage data are provided by at least one detection system, wherein the detection system is adapted to detect weed coverage at least in the at least one measurement sub-area while an application device is moving through the agricultural field. In a second step S202, crop coverage data are provided for the at least one measurement sub-area wherein the crop coverage data are provided by the at least one detection system, wherein the detection system is further adapted to detect crop coverage in the at least one measurement sub-area while the application device is moving through the agricultural field. Relative weed coverage data are derived from the weed coverage data and the crop coverage data by the at least one detection system. In other words, the weed coverage data and the crop coverage data are used for determining the relative weed coverage data. In a third step S303, a threshold model is provided which is configured to provide a threshold value at least based on the derived relative weed coverage data in the at least one measurement subarea. The threshold model comprises at least one lookup table, in which a relationship between the relative weed coverage and the threshold value is provided. In a fourth step S404, the threshold value is set for applying the agricultural product on the application sub-area based on the relative weed coverage data in the at least one measurement subarea by utilizing the threshold model.

Figure 7 illustrates another system 10’ for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field in a spot spray application. The system 10’ comprises a weed coverage data providing unit 1 T configured to provide weed coverage data for at least one measurement sub-area, wherein the weed coverage data are provided by at least one detection system 12’. The detection system 12’ is adapted to detect weed coverage at least in the at least one measurement sub-area while an application device is moving through the agricultural field. A crop coverage data providing unit 15’ for providing crop coverage data for the at least one measurement sub-area, wherein the crop coverage data are provided by the at least one detection system 12’, wherein the detection system 12’ is further adapted to detect crop coverage in the at least one measurement sub-area while the application device is moving through the agricultural field. Relative weed coverage data are derived from the weed coverage data and the crop coverage data by the at least one detection system 12’. The system 10’ further comprises a threshold model providing unit 13’ configured to provide a threshold model configured to provide a threshold value at least based on the provided relative weed coverage data in the at least one measurement subarea. Further, the system 10’ comprises a threshold value setting unit 14’ configured to set the threshold value for applying the agricultural product on the application sub-area based on the relative weed coverage data in the at least one measurement sub-area by utilizing the threshold model.

Figure 8 illustrates an application device 100 for applying an agricultural product on an application sub-area 111 of an agricultural field 120 in a spot application mode. The application sub-area 111 is located underneath the sprayer boom 130. As shown in Figure 8, the agricultural field 120 is divided into measurement sub-areas 110. The weed coverage of at least two subsequent, in particular 3-4 measurement subareas, are for example averaged and compared to the pre-set or the previous used thresholds to decide based on a threshold model or algorithm, if a threshold needs adaptation on a given camera sensor position. The different striped and shaded of areas show for which parts of the field which threshold was used to take a on/off decision for the spot application.

In Figure 8 (by different shading etc.) the measurement sub-areas 110 have different threshold values. The threshold triggers the on/off decision for the nozzle for the spot application based on a threshold model or look-up table separately for every nozzle or boom section. Based on the threshold a single nozzle can be controlled to be on or off. These measurement sub areas 110 may be areas that extend in a length being defined by a preselected and/or pre-defined cycle (e.g., 10 or 15 images). The threshold is used to make a decision, if the application rate for applying the agricultural product on the respective application sub-area need to be changed or not. The repetition rate of the measurement and image sampling and thus the overlap of the measurement sub-areas 110 may also be adapted to the processing speed of the measurement and evaluation equipment. If the measurement and processing speed is comparatively high, more images may be acquired and processed. Additionally, or alternatively, the available activation time or the response time of the application sub-devices, e.g., nozzles, may also be taken into account when setting the repetition rate of the measurement and image sampling and thus the overlap of the measurement sub-areas 110. The application device 100 may comprise one or more spray lines on a sprayer boom 130, wherein such a sprayer boom 130 may comprise one or more detection systems 14. Such a detection system 14 may in turn comprise one or more camera units and one or more light emitting diode (LED) lightning/illum ination units. A detection system 14 may be assigned to one or more application sub-devices, e.g., a nozzle unit and/or a boom section of the sprayer boom 130 of the application device 100. The LED lightning/illum ination units are particularly provided as a flash unit that is directed towards the ground. Such a setup is particularly useful since an image may be captured synchronized with a flash triggering. In this way, the ground or the plants may be illuminated sufficiently so that shadowing by plants or parts of plants may be avoided as far as possible. Such shadowing may be problematic, since such shadows are often interpreted as green leaf area by image recognition software.

The data of one camera system may serve at the same time two different spray lines for example to guide a spot spray of herbicides and in the second spray line a VRA spray of PGR's and fungicides with a two-tank sprayer system.

The illustrated thresholds 1 , 2 und 3 are determined (set or adapted) thresholds after the application device 100 has passed the respective area 110, 111. Threshold 1 may be considered as an exemplary base threshold, whereas threshold 2 may be considered as an adaption of the base threshold by increasing and threshold 3 may be considered as an adaption of the base threshold by decreasing. Threshold determination can be carried our either before entering the region of interest (ROI) or after having entered the ROI. In the first case the following steps are proceeded: Recording the previous ROI with e.g. a camera and determining the coverage in the previous ROI from the recording; Deriving a threshold value for the preceding ROI from the coverage, taking into account the preceding coverage and the past values I averaging; Comparing the previous coverage with the threshold just determined and make the spraying decision (yes/no) for the previous ROI. The spraying decision remains unchanged while the previous ROI is being traversed (in an example, the current coverage could be compared with the threshold while the ROI is being traversed). In the second case the following steps are proceeded: Recording the ROI ahead with e.g. a camera and determining the coverage in the ROI ahead from the recording; Deriving a threshold value from the coverage of the ROI just passed (past) and values even further in the past I averaging of a threshold value; Comparing the threshold value of the past ROI coverage values with the previous coverage value and make the spraying decision (yes/no). During the crossing of the previous ROI, the spraying decision remains unchanged (in an example, the current coverage could be compared with the threshold while the ROI is being crossed).

Referring again to Fig. 8, the application or spray boom during application may be located at a particular position, which is allocated to a particular sub-area. Sub-areas the application boom has already passed can be considered as previous sub-areas which are already sprayed. When the application or spray boom arrives at a sub-area to be sprayed, the threshold value for this current sub-area is determined. For this purpose, the detection is carried out for the current sub-area and makes the current spraying decision for this sub-area. The currently determined coverage in the current sub-area is taken into account and the threshold value is then set and no longer changed while driving over the current sub-area. Also the coverage of the previous sub-area can be considered for determining the threshold value for the current sub-area. In a further embodiment, also the coverage of the sub-area before the previous sub-area can be considered, i.e. the last both sub-areas, for determining the threshold value for the current sub-area. When considering the coverage of a plurality of sub-areas, the relation of coverage between the different sub-areas can be considered for setting the threshold for the current sub-area. The coverage of the different sub-areas can be averaged, or a gradient thereof can be determined. Depending on the relation, an average and/or a gradient the threshold can be set or adapted.

Figure 9 illustrates exemplarily the different possibilities to receive and process field data, in particular weed coverage data. For example, field data can be obtained by all kinds of agricultural equipment 300 (e.g., a tractor 300) as so-called as-applied maps by recording the application rate at the time of application. It is also possible that such agricultural equipment comprises sensors (e.g., optical sensors, cameras, infrared sensors, soil sensors, etc.) to provide, for example, a weed distribution map. It is also possible that during harvesting the yield (e.g., in the form of biomass) is recorded by a harvesting vehicle 310. Furthermore, corresponding maps and/or data can be provided by land- based and/or airborne vehicles/drones 320 by taking images of the field or a part of it. Further, it is also possible that a geo-referenced visual assessment 330 is performed and that this field data is also processed. Field data collected in this way can then be merged in a computing device 340, where the data can be transmitted and computed, for example, via any wireless link, cloud applications 350 and/or working platforms 360, wherein the field data may also be processed in whole or in part in the cloud application 350 and/or in the working platform 360 (e.g., by cloud computing).

Aspects of the present disclosure relate to computer program elements configured to carry out steps of the methods described above. The computer program element might therefore be stored on a computing unit of a computing device, which might also be part of an embodiment. This computing unit may be configured to perform or induce performing of the steps of the method described above. Moreover, it may be configured to operate the components of the above-described system. The computing unit can be configured to operate automatically and/or to execute the orders of a user. The computing unit may include a data processor. A computer program may be loaded into a working memory of a data processor. The data processor may thus be equipped to carry out the method according to one of the preceding embodiments. This exemplary embodiment of the present disclosure covers both, a computer program that right from the beginning uses the present disclosure and computer program that by means of an update turns an existing program into a program that uses the present disclosure. Moreover, the computer program element might be able to provide all necessary steps to fulfill the procedure of an exemplary embodiment of the method as described above. According to a further exemplary embodiment of the present disclosure, a computer readable medium, such as a CD-ROM, USB stick, a downloadable executable or the like, is presented wherein the computer readable medium has a computer program element stored on it, which computer program element is described by the preceding section. A 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 telecommunication systems. However, the computer program may also be presented over a network like the World Wide Web and can be downloaded into the working memory of a data processor from such a network. According to a further exemplary embodiment of the present disclosure, a medium for making a computer program element available for downloading is provided, which computer program element is arranged to perform a method according to one of the previously described embodiments of the present disclosure.

The present disclosure has been described in conjunction with a preferred embodiment as examples as well. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed invention, from the studies of the drawings, this disclosure, and the claims. Notably, in particular, any steps presented can be performed in any order, i.e. , the present invention is not limited to a specific order of these steps. Moreover, it is also not required that the different steps are performed at a certain place or at one node of a distributed system, i.e., each of the steps may be performed at different nodes using different equipment/data processing units.

In the claims as well as in the description the word “comprising” 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 recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation.

Claims

1. Computer-implemented method for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field (120) in a spot spray application, comprising: providing coverage data for at least one of weed coverage and crop coverage for at least one measurement sub-area, wherein the coverage data are provided by at least one detection system, wherein the detection system is adapted to detect coverage of at least one of weed coverage and crop coverage at least in the at least one measurement sub-area while an application device (100) is moving through the agricultural field (120); providing a threshold model configured to provide a threshold value at least based on the provided coverage data in the at least one measurement sub-area; setting the threshold value for applying the agricultural product on the application sub-area based on the coverage data in the at least one measurement sub-area by utilizing the threshold model.

2. Computer-implemented method according to claim 1 , wherein the at least one measurement sub-area substantially corresponds to the application sub-area.

3. Computer-implemented method according to claim 1 , wherein the at least one measurement sub-area comprises at least one previous measurement sub-area, wherein the at least one previous measurement sub-area and the application subarea are located at different positions in the agricultural field (120).

4. Computer-implemented method according to claim 1 , wherein the at least one measurement sub-area comprises an actual/current measurement sub-area and at least one previous measurement sub-are, wherein the at least one measurement sub-area and the application sub-area at least partially overlap.

5. Computer-implemented method according to any one of the preceding claims, wherein the method further comprises: providing crop coverage data for the at least one measurement sub-area wherein the crop coverage data are provided by the at least one detection system, wherein the detection system is further adapted to detect crop coverage in the at least one measurement sub-area while the application device (100) is moving through the agricultural field (120); wherein the provided threshold model is further configured to provide a threshold value at least based on the provided coverage data and the provided crop coverage data in the at least one measurement sub-area; setting the threshold value for applying the agricultural product on the application sub-area based on the coverage data and the crop coverage data by utilizing the threshold model.

6. Computer-implemented method according to any one of the claims 1 to 4, wherein the method further comprises: providing crop coverage data for the at least one measurement sub-area wherein the crop coverage data are provided by the at least one detection system, wherein the detection system is further adapted to detect crop coverage in the at least one measurement sub-area while the application device (100) is moving through the agricultural field (120); wherein relative coverage data are derived from the coverage data and the crop coverage data by the at least one detection system; wherein the provided threshold model is further configured to provide a threshold value at least based on the derived relative coverage data; setting the threshold value for applying the agricultural product on the application sub-area based on the relative coverage data by utilizing the threshold model.

7. Computer-implemented method according to claims 3, 4, 5 or 6, wherein the method further comprises: averaging of the provided coverage data of at least two measurement subareas, the provided crop coverage data of at least two measurement sub-areas and/or the “relative coverage” data of at least two measurement sub-areas, setting the threshold value for applying the agricultural product on the application sub-area based on the averaged coverage data, the averaged crop coverage data and/or the averaged relative coverage data by utilizing the threshold model.

8. Computer-implemented method according to any one of the preceding claims, wherein the threshold model comprises at least one lookup table in which the relationship between a coverage and a threshold value is provided or determined by an algorithm; the relationship between an averaged coverage and a threshold value is provided or determined by an algorithm; the relationship between a coverage, a crop coverage and a threshold value is provided or determined by an algorithm; or the relationship between an averaged coverage, an averaged crop coverage and a threshold value is provided or determined by an algorithm; or the relationship between a relative coverage and a threshold value is provided or determined by an algorithm; the relationship between an averaged relative coverage and a threshold value is provided or determined by an algorithm.

9. Computer-implemented method according to any one of the preceding claims, wherein setting the threshold value for applying the agricultural product on the application sub-area comprises: providing a base threshold value for the application sub-area for the agricultural field (120); setting the threshold value for applying the agricultural product on the application sub-area based on the base threshold value and the coverage data by utilizing the threshold model, wherein the threshold model is configured to provide a threshold value at least based on the provided base threshold value and the coverage data and/or the crop coverage data for the measurement sub-area.

10. Computer-implemented method according to any one of the preceding claims, wherein the at least one detection system comprises at least one camera unit for capturing image data of the at least one measurement sub-area of the agricultural field (120).

11. Computer-implemented method according to claim 10, wherein the at least one camera unit is configured to provide red green blue-images and/or Near Infrared Images and/or Red Edge Images and/or multi-spectral images, and wherein the at least one detection system is adapted to detect or to determine the coverage or crop and coverage based on the red green blue-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images.

12. Computer-implemented method according to claim 11 , wherein the red green blue-images and/or the Near Infrared Images and/or the Red Edge Images and/or multi-spectral images are converted into binary images, and wherein the at least one detection system is configured to determine the coverage or crop and coverage based on the binary images.

13. Computer-implemented method according to any one of the preceding claims, wherein the at least one detection system is assigned to one or more application sub-devices configured to apply the agricultural product on the application sub-area, wherein the application sub-devices are particularly nozzle units and/or boom sections of a sprayer boom (130) of a sprayer and/or spreader allowing an application sub-area specific setting of thresholds.

14. An apparatus for setting a threshold value for applying an agricultural product on an application sub-area of an agricultural field (120) in a spot spray application, the apparatus comprising: a computing node; and a computer-readable media having thereon computer-executable instructions that are structured such that, when executed by the computing node, cause the apparatus to perform the following steps: providing coverage data for at least one of weed coverage and crop coverage for at least one measurement sub-area, wherein the coverage data are provided by at least one detection system, wherein the detection system is adapted to detect coverage of at least one of weed coverage and crop coverage at least in the at least one measurement sub-area while an application device (100) is moving through the agricultural field (120); providing a threshold model configured to provide a threshold value at least based on the provided coverage data in the at least one measurement sub-area; setting the threshold value for applying the agricultural product on the application sub-area based on the coverage data in the at least one measurement sub-area by utilizing the threshold model.

15. Application device (100) for applying an agricultural product on an application subarea of an agricultural field (120) in a spot spray application, wherein the threshold value is provided according to any one of the claims 1 to 13.