MÉTODO IMPLEMENTADO POR COMPUTADOR, APARELHO PARA FORNECER DADOS DE ABSORÇÃO DE NITROGÊNIO, DISPOSITIVO DE APLICAÇÃO DE FERTILIZANTE, ELEMENTO DE PROGRAMA DE COMPUTADOR E USO

Abstract

Computer-implemented method for providing nitrogen uptake data of plants and / or plant parts of an agricultural field, comprising: providing (100) leaf area index data for the agricultural field; providing (110) chlorophyll content data for the agricultural field; providing (120) an nitrogen uptake model configured to provide nitrogen uptake data of plants and / or plant parts based on leaf area index data and chlorophyll content data; providing (130) nitrogen uptake data of plants and / or plant parts of the agricultural field based on the provided leaf area index data and chlorophyll content data utilizing the nitrogen uptake model. The method further comprises determining stem weight data based on a provided crop specific leaf weight ratio and determining stem nitrogen data based on the stem weight data and a provided crop specific stem nitrogen concentration. Providing nitrogen uptake data of plants and / or plant parts of the agricultural field is further based on the determined stem nitrogen data.

Description

1 / 43 “COMPUTER-IMPLEMENTED METHOD, APPARATUS FOR PROVIDING NITROGEN ABSORPTION DATA, DEVICE OF "APPLICATION OF FERTILIZER, COMPUTER PROGRAM ELEMENT AND USE" Field of Invention

[001] This disclosure relates to a computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, a system for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, an apparatus for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, a fertilizer application device for applying a fertilizer product in an agricultural field, a corresponding computer program element and the respective use of data. Background of the Invention

[002] The general context of this disclosure is the treatment of an agricultural field with a fertilizer product. Farmers apply fertilizer products, for example, urea, ammonium nitrate, ammonium sulfate, calcium and ammonium nitrate, manure, slurry, etc., which contain forms of nitrogen such as ammonium, nitrate, and / or organic nitrogen. Nitrogen is an essential element for plant growth, health, and reproduction. Some of the nitrogen available to plants in soils (ammonium and nitrate) originates from decomposition processes (mineralization) of organic nitrogen compounds, such as humus, plant and animal residues, and organic fertilizers. Another part derives from precipitation. On a global basis, by far the largest part (according to some sources, about 90%), however, is supplied to the plant by organic and inorganic nitrogen fertilizers (the so-called minerals). The most widely used inorganic nitrogen fertilizers are urea compounds. Petition 870250085504, dated 09 / 22 / 2025, page 63 / 119 2 / 43 and / or ammonium compounds or their derivatives, that is, almost 90% of nitrogen fertilizers applied worldwide are in the form of urea and / or Nf (cf. Subbarao et al., 2012, Advances in Agronomy, 114, 249-302). However, it is often difficult for the farmer to make an objective decision about whether, and how, the respective fertilizers should be applied.

[003] Nitrogen (N) from mineral fertilizers is essential to meet global food demand. More than 50% of global protein production depends on the production and use of nitrogenous mineral fertilizers. However, the excessive use of nitrogenous fertilizers threatens the quality of atmospheric, aquatic, marine, and terrestrial resources, as well as contributing to global warming. The methods and systems of the present invention will contribute to a more sustainable use of fertilizer applications. As will be understood from the description below, this can be achieved, for example, by allowing the in situ determination of N uptake by crops during the crop growing season.

[004] In the present invention, reference is made to the article “Vegetation Indices Combining the Red and Red-Edge Spectral Information for Leaf Area Index Retrieval”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (Volume: 11, Issue: 5, May 2018).

[005] An additional need has been identified to provide objective means to assist the farmer in the use of fertilizer products. In particular, there is an additional need to provide objective means to avoid over-fertilization in practice. Brief Description of the Invention

[006] In one aspect of the present invention, a computer-implemented method is disclosed for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, comprising: Petition 870250085504, dated 09 / 22 / 2025, page 64 / 119 3 / 43 provide leaf area index data for the agricultural field; To provide chlorophyll content data for the agricultural field; To provide a nitrogen uptake model configured to supply nitrogen uptake data by plants and / or plant parts based on leaf area index data and chlorophyll content data; To provide nitrogen uptake data by plants and / or plant parts in the agricultural field based on provided leaf area index data and chlorophyll content data using the nitrogen uptake model.

[007] In particular, in some exemplary embodiments, the method may optionally comprise the determination of stem weight data based on a specific leaf weight ratio for the given crop; the determination of stem nitrogen data based on stem weight data and a specific stem nitrogen concentration for the given crop. According to the present invention, the provision of nitrogen uptake data by plants and / or plant parts from the agricultural field is further based on the determined stem nitrogen data.

[008] In particular, the specific leaf weight ratio for a given crop can be used as an input to the nitrogen uptake model or determined by a growth model, for example, as part of the nitrogen uptake model.

[009] A further aspect of the present invention relates to a system for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, comprising: a leaf area index data supply unit configured to provide leaf area index data for the agricultural field; a unit for supplying chlorophyll content data Petition 870250085504, dated 09 / 22 / 2025, page 65 / 119 4 / 43 configured to provide chlorophyll content data for the agricultural field; A nitrogen uptake model delivery unit configured to provide nitrogen uptake data by plants and / or plant parts based on leaf area index data and chlorophyll content data.

[010] The system may optionally include: A stem nitrogen concentration determination unit configured to determine stem weight data based on a crop-specific leaf weight ratio and to determine stem nitrogen data based on stem weight data and a crop-specific stem nitrogen concentration; and a nitrogen uptake data supply unit configured to supply nitrogen uptake data by plants and / or plant parts from the agricultural field based on provided leaf area index data and chlorophyll content data using the nitrogen uptake model, and also based on determined stem nitrogen data.

[011] A further aspect of the present invention relates to an apparatus for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, wherein the apparatus comprises: one or more computing nodes (or computing nodes); and one or more computer-readable media containing computer-executable instructions that are structured in such a way that, when executed by one or more computing nodes, they cause the apparatus to perform the following steps: To provide leaf area index data for the agricultural field; To provide chlorophyll content data for the agricultural field; provide a nitrogen absorption model configured for Petition 870250085504, dated 09 / 22 / 2025, page 66 / 119 5 / 43 provide nitrogen uptake data by plants and / or plant parts based on leaf area index data and chlorophyll content data.

[012] The steps may optionally include further: determining stem weight data based on a crop-specific leaf weight ratio provided; and determining stem nitrogen data based on stem weight data and a crop-specific stem nitrogen concentration provided; providing nitrogen uptake data by plants and / or plant parts from the agricultural field based on leaf area index data provided and chlorophyll content data using the nitrogen uptake model and, additionally, based on the determined stem nitrogen data.

[013] In particular, the crop-specific leaf weight ratio can be used as an input to the nitrogen uptake model.

[014] A further aspect of the present invention relates to a fertilizer application device for applying a fertilizer product to an agricultural field, wherein the control data for the fertilizer application device are, at least partially, provided according to a disclosed computer-implemented method for providing nitrogen uptake data by plants and / or plant parts of an agricultural field. It is noted that a fertilizer application device may be a specific form of an application device, for example, a spraying device. The application device may comprise a processor configured to receive, via a communication interface, the control data and / or data to execute one or more of the steps of the method for providing the control data, and / or configured to execute at least some or all of the steps of the method. Petition 870250085504, dated 09 / 22 / 2025, page 67 / 119 6 / 43 to provide the control data.

[015] A further aspect of the present invention relates to a computer program element with instructions that, when executed on computing devices in a computing environment, is configured to execute the steps of the computer-implemented method disclosed to provide nitrogen uptake data by plants and / or plant parts from an agricultural field.

[016] A further aspect of the present invention relates to the use of leaf area index data, chlorophyll content data, nitrogen uptake model and / or satellite imagery in a computer-implemented method to provide nitrogen uptake data by plants and / or plant parts from an agricultural field.

[017] In one aspect according to the disclosure.

[018] This and the embodiments described herein refer to the method, system, agricultural device, use, computer program element described above and vice versa. Advantageously, the benefits provided by any one embodiment and example apply equally to all other embodiments and examples and vice versa. As used in the present invention, the terms “determine” also encompass “estimate, calculate, initiate or cause to be determined”, “generate” also encompasses “initiate or cause to be generated” and “provide” also encompasses “initiate or cause to be determined, generate, select, send, consult or receive”.

[019] Leaf area index data may, in particular, include a leaf area index and, optionally, other data. Chlorophyll content data may, in particular, include chlorophyll content and, optionally, other data. Nitrogen uptake data may, in particular, include nitrogen uptake and, optionally, other data. Stem weight data may, in particular, include stem weight and, Petition 870250085504, dated 09 / 22 / 2025, pp. 68 / 119 7 / 43 optionally, other data.

[020] Chlorophyll content data may be provided as leaf chlorophyll content (LC) data, which may include leaf chlorophyll content and optionally other data, and / or canopy chlorophyll content (CCHL) data, which may include canopy chlorophyll content and optionally other data.

[021] Leaf Area Index is a term commonly used in the field. It can be understood as leaf area per area of ​​soil (e.g., m2 of leaf per m2 of soil). This index can be derived from remote or proximal sensing devices, such as satellite imagery, as explained in detail below.

[022] LAI can be converted into leaf mass (also called net leaf mass (NLM); kg per m2 of soil, for example). This can be done by multiplying the LAI by a specific leaf area (called LSA; m2 of leaf per kg of leaf (DrM (dry mass)). LSA values ​​can be specific to the crop and growth stage and are derived from a crop growth database or model.

[023] The stem mass (also called MDC; kg per m2 of soil) can be derived from a ratio of leaf weight (called RPF; kg MFL / (kg MFL+MDC)).

[024] The RPF, which can be considered a biomass allocation coefficient, is specific to the crop and growth stage and can be derived from a database or a crop growth model.

[025] Chlorophyll concentration (called CHL; pg Chl per cm2 of leaf area) can be derived from near or remote sensing devices, for example, satellite imagery.

[026] CHL can be converted into nitrogen concentration Petition 870250085504, dated 09 / 22 / 2025, pp. 69 / 119 8 / 43 foliar (CNF; kg N per kg MFL) using the chlorophyll coefficient for N (called Chl_N, mass of N per mass Chl) and molecular mass (MM; kg per mol) of chlorophyll.

[027] Chl_N and MM specific to each crop can, for example, be retrieved or derived from a data source. There is published data that can be retrieved for this purpose.

[028] According to the present invention, the leaf weight ratio, LWR, can be a dynamic value, i.e., a value that changes over time, for example, over a season. As an example, a daily leaf weight ratio can be used. The leaf weight ratio is an example of a dynamic biomass allocation coefficient.

[029] The RPF may depend on geographical location. In particular, the RPF may depend on the season and location. The leaf weight ratio may depend on at least one of the following factors: geographical location, climatic conditions and agricultural practices / parameters such as sowing date and variety.

[030] The relationship (ratio) between leaf weight and leaf density can be determined using a model. For example, the model can take into account at least one of the following factors: geographic location, climatic conditions, internal logic of the model, and agricultural practices / parameters such as sowing date and variety.

[031] Using the leaf weight ratio in determining nitrogen uptake allows for more precise determinations of nitrogen uptake.

[032] As an example, a (crop) model configured to provide a site-specific crop organ allocation coefficient, such as leaf weight ratio (LWR), can be used to obtain the LWR. The LWR, provided by a model, is affected by the location. Petition 870250085504, dated 09 / 22 / 2025, pp. 70 / 119 9 / 43 geographical, climatic conditions, internal logic of the model and agricultural practices, such as sowing date and variety.

[033] It is understood from the above that the present invention can provide a model (of nitrogen absorption) that provides indicative data of the dry mass of one or more crop organs (for example, at least one of the root mass data, stem weight data, leaf mass data, seed mass data and fruit mass data) based on a dynamic biomass allocation coefficient (such as RPF and / or root-to-shoot ratio and / or stem-to-shoot ratio), particularly daily throughout the season.

[034] The present invention can provide a process-based (nitrogen uptake) model that can take as input data at least one of crop type, variety, sowing / planting date, and site-specific soil and climate data. This is the case when a growth model, as disclosed below, is employed (details thereof are provided below), for example, a plant-specific growth model, according to which stem weight data are determined by a plant-specific growth model. Such growth models can receive at least one of crop type, variety, sowing / planting date, and site-specific soil and climate data as input data and, for example, stem weight data as output.

[035] The objective of the present invention is to provide objective means to assist the farmer in the use of fertilizer products. In particular, the objective of the present invention is to provide objective means to avoid over-fertilization in practice. Furthermore, the objective of the present invention is to provide data that allow the control of a fertilizer application device. Petition 870250085504, dated 09 / 22 / 2025, pp. 71 / 119 10 / 43

[036] These and other objectives, which become evident from reading the following description, are addressed by the subject matter of the independent claims. The dependent claims refer to preferred embodiments of the invention.

[037] The term “agricultural field,” as used in the present invention, should be understood broadly in this case and refers to any area, i.e., surface and subsurface, of soil to be treated with a fertilizer product. The agricultural field can be any area for cultivating plants or crops, such as an agricultural field, a greenhouse, or similar. A plant can be a crop, a weed, a volunteer plant, a crop from a previous growing season, a beneficial plant, or any other plant present in the agricultural field. The agricultural field can be identified by means of field data relating to its geographic location or georeferenced location data. A reference coordinate, a size, and / or a shape can be used to better specify the agricultural field. The field data can be used to calculate the application rate / quantity for the agricultural field.Field data can also be used to specify the climatic region in which an agricultural field is located. Field data, particularly the geographical location of the agricultural field, can also be used to provide meteorological data, such as historical, actual, and / or forecast weather data. Notably, field data can be used to provide soil parameter data, topography data, and any other data that can be used to adjust the emissions calculation model.

[038] The “leaf area index (LAI)” is defined as the total one-sided leaf area per unit area of ​​soil. LAI is one of the most important biophysical parameters that characterize a canopy. The “content of Petition 870250085504, dated 09 / 22 / 2025, page 72 / 119 11 / 43 chlorophyll” can be provided as chlorophyll content (CL) data and / or canopy chlorophyll content (CCHL) data. In this sense, leaf area index (LAI) data and chlorophyll content data for the agricultural field can be obtained using a leaf area and chlorophyll content model configured to provide leaf area index data and chlorophyll content data based on the surface reflectance bands of at least one satellite image. The leaf area index and chlorophyll content model are preferably adapted to different crop varieties, crop types, growth stages, soil conditions, and / or data sources.

[039] IAF data can be provided in a netCDF file format, for example, as a global, multiband NetCDF4 file with metadata in accordance with Climate and Forecast (CF) conventions. In addition, or alternatively, IAF data can be provided as INSPIRE-compliant metadata files in XML format, corresponding XSLT for XML visualization, and a quick, coloured, subsampled visualization in GeoTiff format.

[040] Furthermore, the leaf area and chlorophyll content model can be a machine learning model, and the leaf area index and chlorophyll content data for the agricultural field can be obtained using the leaf area and chlorophyll content model. That is, for example, the machine learning model's prediction can be the leaf area index data and the chlorophyll content data. The machine learning model can preferably be: an artificial neural network (ANN), multiple linear regression, random forest regression, or an approach that is capable of establishing a statistical relationship to predict leaf area index and chlorophyll content data. The leaf area and chlorophyll content model can be provided as an integral machine learning model or as two separate machine learning models, one Petition 870250085504, dated 09 / 22 / 2025, page 73 / 119 12 / 43 focused on leaf area index and one focused on chlorophyll content. In the case of two separate machine learning models, for example, one can predict leaf area index data and the other can predict chlorophyll content.

[041] The term “machine learning algorithm” may encompass decision trees, Naive Bayes classifiers, nearest neighbors, neural networks, convolutional or recurrent neural networks, transformers, generative adversarial networks (GANs), support vector machines (SVMs), linear regression, logistic regression, random forest, and / or gradient boosting algorithms. Preferably, the output of a machine learning algorithm is used to fine-tune the application rate decision logic. Preferably, the machine learning algorithm is designed to process a high-dimensional input into a much lower-dimensional output. Such a machine learning algorithm is termed “intelligent” because it is capable of being “trained.” The algorithm can be trained using training data records.A training data record comprises training input data and corresponding training output data. The training output data of a training data record is the result that the machine learning algorithm is expected to produce when given the training input data from the same training data record. The deviation between this expected result and the actual result produced by the algorithm is observed and classified using a "loss function". This loss function is used as feedback to adjust the parameters of the machine learning algorithm's internal processing chain. For example, parameters can be adjusted with the goal of optimization to minimize the resulting loss function values. Petition 870250085504, dated 09 / 22 / 2025, pp. 74 / 119 13 / 43 feeding all the training input data into the machine learning algorithm and comparing the result with the corresponding training output data. The result of this training is that, given a relatively small number of training data records as "ground truth," the machine learning algorithm can perform its function well for many input data records that are many orders of magnitude larger.

[042] The term “control data”, as used in the present invention, should be understood broadly in the present case and refers to any data configured to operate and control an application device. Control data is provided by a control unit and may be configured to control one or more technical means of the application device, for example, drive control, but is not limited to that.

[043] The term “fertilizer application device” as used herein should be understood broadly in the present case and represents any device configured to apply fertilizer to the soil of an agricultural field or to the vegetation cover of an agricultural field. The application device may be configured to traverse the agricultural field. The application device may be a ground or aerial vehicle, for example, a tractor, a rail vehicle, a robot, an aircraft, an unmanned aerial vehicle (UAV), a drone or similar. The application device may be autonomous or non-autonomous.

[044] The term “fertilizer” or “fertilizer product,” as used in the present invention, should be understood broadly and includes any solid or liquid fertilizer products and combinations thereof. The term fertilization / fertigation, as used in the present invention, should be understood broadly in the present case and includes Petition 870250085504, dated 09 / 22 / 2025, p. 75 / 119 14 / 43 Any action to place, position, or bring fertilizer / a fertilizer product into an area of ​​soil in an agricultural field. A fertilizer is any material of natural or synthetic origin that is applied to the soil or plant tissues to provide nutrients to plants. The fertilizer product may contain urea, NO3-, NH4+, NH3 and / or organic N ions or may be capable of producing NH4+ or NH3 ions in the soil by decomposition, for example, hydrolysis. The term 'fertilizers' can be understood as organic and / or chemical compounds applied to promote the growth of plants and fruits. Fertilizers are typically applied through the soil (for absorption by plant roots), through soil amendments (also for absorption by plant roots), or by foliar application (for absorption by leaves). The term also includes mixtures of one or more different types of fertilizers, as mentioned below.The term 'fertilizers' can be subdivided into several categories, including: a) organic fertilizers (composed of decomposing plant / animal matter), b) inorganic fertilizers (composed of chemicals and minerals), and c) fertilizers containing urea. Organic fertilizers can include manure, for example, liquid manure, semi-liquid manure, biogas manure, stable manure or manure with straw, slurry, worm castings, peat, seaweed, compost, sewage sludge, and guano. Green manure crops are also regularly grown to add nutrients (especially nitrogen) to the soil. Manufactured organic fertilizers include, for example, compost, blood meal, bone meal, and seaweed extracts. Other examples are enzyme-digested proteins, fishmeal, and feather meal. Decomposing crop residues from previous years are another source of fertility.In addition, natural minerals such as phosphate from mined rock, potassium sulfate, and limestone are also considered inorganic fertilizers. Inorganic fertilizers are generally manufactured through chemical processes (e.g. Petition 870250085504, dated 09 / 22 / 2025, pp. 76 / 119 15 / 43 example, N of how the Haber-Bosch process), also using natural deposits, while chemically altering them (e.g., concentrated triple superphosphate). Natural inorganic fertilizers include Chilean sodium nitrate, mine rock phosphate, limestone, and raw potassium fertilizers. Inorganic fertilizer may, in a specific embodiment, be an “NPK fertilizer,” “NP fertilizer,” and “NK fertilizer.” NPK fertilizers are inorganic fertilizers formulated in appropriate concentrations and combinations, comprising the three main nutrients nitrogen (N), phosphorus (P), and potassium (K), as well as typically S, Mg, Ca, and trace elements. NP fertilizers are inorganic fertilizers formulated in appropriate concentrations and combinations, comprising two main nutrients nitrogen (N) and phosphorus (P), as well as typically S, Mg, Ca, and trace elements.NK fertilizers are inorganic fertilizers formulated in appropriate concentrations and combinations, comprising the two main nutrients nitrogen (N) and potassium (K), as well as typically S, Mg, Ca, and trace elements. Other inorganic fertilizers may include ammonium nitrate, ammonium nitrate and calcium, ammonium sulfate nitrate, ammonium sulfate, or ammonium phosphate. Fertilizers containing urea may, in specific embodiments, be urea, urea formaldehyde, urea-ammonium nitrate solution (UAN), urea sulfur, stabilized urea, urea-based NPK fertilizers, or urea-ammonium sulfate-based fertilizers. The use of urea as a fertilizer is also foreseen.In the case of using or supplying fertilizers containing urea or pure urea, it is particularly preferable that urease inhibitors, as defined above, be added or present additionally or used simultaneously or in conjunction with the urea-containing fertilizers. Urea-containing fertilizers are hydrolyzed by microorganisms, releasing ammonia which, in turn, forms ammonium ions. Urea-containing fertilizers can therefore be considered a form of... Petition 870250085504, dated 09 / 22 / 2025, page 77 / 119 16 / 43 ammonium storage. The fertilizer may be selected from solid or liquid inorganic fertilizers containing ammonium and / or nitrate, such as NPK, NP and NK fertilizers, ammonium nitrate, calcium ammonium nitrate, ammonium sulfate nitrate, ammonium sulfate, calcium nitrate or ammonium phosphate; solid or liquid organic fertilizers, such as liquid manure, semi-liquid manure, stable manure, biogas manure and straw manure, worm humus, compost, seaweed or guano; or fertilizers containing urea, such as urea, urea formaldehyde, urea ammonium nitrate solution (UAN), urea sulfur, stabilized urea, NPK, NP and NK fertilizers based on urea, urea ammonium sulfate or a mixture thereof. Preferably, the fertilizer contains NH4+ ions; More preferably, the fertilizer is selected from among inorganic fertilizers containing ammonium, either solid or liquid.Fertilizers can be supplied in any suitable form, for example, as powders, crystals, granules or solid spheres, coated or uncoated, in liquid or semi-liquid form, or as a sprayable fertilizer. The fertilizer can be applied in the uses and application methods via fertigation. Coated fertilizers can be supplied with a wide range of materials. Coatings can, for example, be applied to granular or spherical nitrogen (N) fertilizers or to multi-nutrient fertilizers. Typically, urea is used as the base material for most coated fertilizers. Alternatively, ammonium, nitrate or NPK, NP and NK fertilizers are used as base material for coated fertilizers. The present invention, however, also provides for the use of other base materials for coated fertilizers, any of the fertilizer materials defined in the present invention.In certain applications, elemental sulfur can be used as a fertilizer coating.

[045] The term “control data”, as used in the present invention, should be understood broadly in the present case and Petition 870250085504, dated 09 / 22 / 2025, pp. 78 / 119 17 / 43 refers to any data configured to operate and control an agricultural device and / or part of an agricultural device. Control data may be provided by a control unit and may be configured to control one or more technical means of the agricultural device, for example, drive control, direction, product output, flight height, etc. Control data may include metadata to control the amount of agricultural product applied to the field and at what position in the field. In this sense, control data may also be configured to control nozzles, pumps, valves and / or dispensing discs of an application device.Such control can be performed in a manner called on / off, that is, in this case, an output control can be performed in a manner called on / off, where the output medium is fully open or fully closed, for example, a fully open or fully closed valve. Alternatively, an output control can also occur as a so-called variable control. In this case, an output medium can also assume output values ​​between fully open and fully closed.

[046] The term “supply”, as used in the present invention, should be understood broadly in the present case and represents, but is not limited to, any supply, receipt, query, measurement, calculation, determination and transmission of data. Data may be supplied by a user through a user interface, represented / displayed to a user by a monitor and / or received from other devices, queried from other devices, measured from other devices, calculated by other devices, determined by other devices and / or transmitted by other devices.

[047] The term “data”, as used in the present invention, should be understood broadly in the present case and represents any Petition 870250085504, dated 09 / 22 / 2025, pp. 79 / 119 18 / 43 Data type. Data can be single numbers / numeric values, a plurality of numbers / numeric values, a plurality of numbers / numeric values ​​arranged in a list, two-dimensional maps, or three-dimensional maps, but are not limited to these examples.

[048] In the following embodiments, particularly preferred methods, systems, apparatus, devices and / or use cases are presented, which can be combined with the methods, systems, apparatus, devices and / or use cases mentioned above.

[049] In an exemplary embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts from an agricultural field, chlorophyll content data are provided as leaf chlorophyll content (LC) data and / or canopy chlorophyll content (CCHL) data.

[050] In an embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts of an agricultural field, leaf area index data and chlorophyll content data for the agricultural field are obtained using a leaf area and chlorophyll content model configured to provide leaf area index data and chlorophyll content data based on surface reflectance bands of at least one satellite image, wherein the leaf area and chlorophyll content model is preferably adapted to different crop varieties, crop types, growth stages, soil conditions and / or data sources.

[051] In an exemplary embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, the leaf area index and chlorophyll content models are machine learning models. The leaf area index and chlorophyll content data for the agricultural field are Petition 870250085504, dated 09 / 22 / 2025, pp. 80 / 119 19 / 43 obtained using the leaf area index and chlorophyll content model, with the machine learning model preferably being: an artificial neural network (ANN), multiple linear regression, random forest regression, or an approach capable of establishing a statistical relationship to predict the leaf area index and chlorophyll content data.

[052] The machine learning model with respect to leaf area index data can be an XGBBOOST regression model based on satellite image analysis. In linear regression, in general, the model makes a prediction based on features that are fed into the model, for example, by creating a weighted sum of the features. In the present case, the predictions depend on features that are derivable from the satellite images. To obtain leaf area index data and chlorophyll content data, one or more regression models can be used. There are machine learning models that can predict both leaf area index data and chlorophyll content data, and alternatively, using separate models is an option, which, as the subject matter expert will understand, depends on the situation in question, for example, model architecture.

[053] In the present invention, derivable features from satellite images and suitable for the regression model approach may contain derived spectral bands and / or a vegetation index derived from satellite images. That is, the input to the regression model may be derived from pixel-based information from satellite images (i.e., remote sensing images). This derivation may be done using known methods and known vegetation indices, such as MSR_Red&Red_Edge (Modified Simple Ratio (MSR) using red and red-edge bands). It is known that the Leaf Area Index can be derived from these vegetation indices. Different indices are Petition 870250085504, dated 09 / 22 / 2025, pp. 81 / 119 20 / 43 conceivable. However, the MSR_Red&Red_Edge is particularly suitable as it produces very accurate forecasts compared to other indices that can also be used, such as the NDVI.

[054] In this regard, as an example, a combination of six features can be used, where it is preferable that 5 spectral bands and a vegetation index, all of which can be derived from satellite imagery, are used as features for the machine learning model, wherein the spectral bands Red Edge 2, Red Edge 3, Narrow NIR, SWIR 1, SWIR 2 and the combined vegetation index MSR_Red&Red_Edge (Modified Simple Ratio using red and red edge bands) can be used as features, wherein the spectral bands can be defined as follows: Table 1 Band Names | Acronym | Central (nm) | Width (nm) | Spatial Resolution (m) | GREEN | B3 | 560 | 35 | 10 | RED | B4 | 665 | 30 | 10 | Red Edge | B5 | 705 | 15 | 20 | Red Edge 2 | B6 | 740 | 15 | 20 | Red Edge 3 | B7 | 783 | 20 | 20 | Narrow Near Infrared (Narrow NIR) | B8a | 865 | 20 | 20 | Shortwave Infrared 1 (SWIR 1) | B11 | 1610 | 90 | 20 | Shortwave Infrared 2 (SWIR 2) | B12 | 2190 | 180 | 20

[055] In addition, in this regard, reference is also made to the article “Vegetation Indices Combining the Red and Red-Edge Spectral Information for Leaf Area Index Retrieval”, IEEE Journal of Selected Topics in Petition 870250085504, dated 09 / 22 / 2025, p. 82 / 119 21 / 43 Applied Earth Observations and Remote Sensing (Volume: 11, Issue: 5, May 2018).

[056] The machine learning model with respect to chlorophyll content data can be an XGBBOOST regression model based on satellite image analysis. In this sense, a combination of six features can be used, with the use of two spectral bands and four vegetation indices as features (variables) for the machine learning model being preferable, the spectral bands being Red Edge 1, SWIR 2, and the vegetation indices being NDWI (Normalized Difference Water Index), GNDVI (Green Normalized Difference Vegetation Index), REIP (Red Edge Inflection Point), Chlr_Red_Edge (combined vegetation index).Furthermore, in this same vein, reference is made to the article “Vegetation Indices Combining the Red and Red-Edge Spectral Information for Leaf Area Index Retrieval”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (Volume: 11, Issue: 5, May 2018).

[057] In an exemplary embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, the nitrogen uptake model is further based on a crop-specific chlorophyll-to-foliar nitrogen conversion factor. There is a relationship between the amount of chlorophyll and the nitrogen contained in the plant and / or plant part. Through the conversion factor, a quantity of chlorophyll can be converted into nitrogen. In this context, such a conversion factor can be determined specifically for the crop, specifically for the field and / or Petition 870250085504, dated 09 / 22 / 2025, page 83 / 119 22 / 43 specifically for the climatic zone through the respective field tests. Conversion factors can, for example, be determined for specific climatic regions through corresponding field trials, in which specific field adjustments can be considered later. Therefore, a crop-specific and field-specific chlorophyll-to-foliar nitrogen conversion factor can be provided for each respective agricultural field. For example, a conversion factor of 250 in a moderate European climatic zone for wheat was determined through the respective field tests. This conversion factor may or may not be refined at a field-specific level through respective field tests.

[058] As explained above, the method of the present invention comprises: Determine stem weight data based on a crop-specific leaf weight ratio provided; To determine stem nitrogen data based on stem weight data and a crop-specific stem nitrogen concentration provided; wherein the provision of nitrogen uptake data by plants and / or plant parts from the agricultural field is further based on the determined stem nitrogen data.

[059] Optionally, stem weight data can also be determined by a plant-specific growth model. As input data for such a growth model, plant data, meteorological data, climatic data, etc., can be used. For example, such a plant-specific growth model was published by Hunt et al. (“Effects of Nitrate Application on Amaranthus powellii Wats”, Plant Physiology, Volume 79, Issue 3, November 1985, pages 619-624), which refers to Amaranthus powellii, a small grain crop, Petition 870250085504, dated 09 / 22 / 2025, p. 84 / 119 23 / 43 is particularly known in the bio-organic and cereal sectors.

[060] In an embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, the method further comprises: To provide a nitrogen absorption map of the agricultural field based on the nitrogen absorption data provided, where the map preferably has a resolution between 1 and 50 meters, 5 and 30 m, more preferably 10 m. In one example, the nitrogen absorption map reflects the predicted N absorption in different color intensities, from low to high, and can provide a pixel-based map with high granularity, and / or a field zone-based map that spatially aggregates the information into a given number of zones that take into account the spatial resolution constraints related to the fertilizer distributor / machine during fertilizer application (e.g., an as-applied map, i.e., a map showing how the fertilizer was actually applied).

[061] The unit of the catchment map is the mass of N / unit area of ​​land. The map provides spatially resolved / explicit information (geographic information system, GIS, etc.).

[062] In an embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, the method further comprises: to provide a specific target nitrogen value for the crop; To provide nitrogen demand data based on nitrogen absorption data and target nitrogen value.

[063] In an embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, the method further comprises: provide a map of nitrogen demand for the agricultural field Petition 870250085504, dated 09 / 22 / 2025, page 85 / 119 24 / 43 based on the nitrogen demand data provided, where the map preferably has a resolution between 1 and 50 m, 5 and 30 m, and more preferably 10 m.

[064] In this document, nitrogen demand data, particularly nitrogen demand, can be expressed as the difference between target nitrogen uptake and actual nitrogen uptake, determined as described in the present invention. Alternatively, nitrogen demand can be expressed as actual nitrogen uptake divided by optimum uptake (i.e., ideal nitrogen uptake). This is known as the Nitrogen Nutrition Index, NNI, known and established in agriculture as a metric for nitrogen demand.

[065] In an embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, the method further comprises: To provide control data for a fertilizer application device for the variable application of a fertilizer product in the agricultural field based on nitrogen demand data.

[066] In an embodiment of the computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field, the method further comprises: To provide control data for an application device for the variable application of an agricultural product in the agricultural field based on nitrogen demand data, where the agricultural product is: a crop protection product, a biostimulant product, a growth regulator product and / or a desiccation product. Brief Description of the Figures

[067] The present invention is described in more detail below with reference to the accompanying figures: Petition 870250085504, dated 09 / 22 / 2025, page 86 / 119 25 / 43 Figure 1: illustrates exemplary realizations of a centralized and decentralized computing environment with computing nodes; Figure 2: illustrates exemplary realizations of a centralized and decentralized computing environment with computing nodes; Figure 3: illustrates an implementation of a distributed computing environment; Figure 4: illustrates a flowchart of a computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field; Figure 5: illustrates a system for providing nitrogen uptake data by plants and / or plant parts in an agricultural field; Figure 6: is a further illustration of a computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field; Figure 7: shows an example map of nitrogen absorption in an agricultural field; Figure 8: exemplarily illustrates the different possibilities for receiving and processing field data; and Figure 9: illustrates an example of a leaf weight ratio (LWR) for different locations and years and its development over time. Detailed Description of Illustrative Achievements

[068] The following embodiments are merely examples of implementing the method, system, apparatus or application device disclosed in the present invention and should not be considered limiting.

[069] Figures 1 to 3 illustrate different computing environments: centralized, decentralized, and distributed. The methods, Petition 870250085504, dated 09 / 22 / 2025, page 87 / 119 26 / 43 devices and computational elements of this disclosure can be implemented in decentralized or at least partially decentralized computing environments. In particular, for data sharing or exchange in multi-participant ecosystems, there are different challenges. Data sovereignty can be seen as a central challenge. It can be defined as the ability of a natural or legal person to be fully self-determined in relation to their data. To enable this specific capability, related aspects, including requirements for secure and reliable data exchange in business ecosystems, can be implemented throughout the chemical value chain. In particular, the chemical industry requires customized solutions to supply chemicals more sustainably, utilizing digital ecosystems.The provision, determination, or processing of data can be performed by different computing nodes, which can be implemented in a centralized, decentralized, or distributed computing environment.

[070] Figure 1 illustrates an example 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 on the periphery). The term “computing system” is defined here broadly as including one or more computing nodes, a system of nodes, or combinations thereof. The term “computing node” is defined here 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 computer executable instructions that are executed by a processor. Computing nodes are now increasingly taking on a wide variety of forms. Computing nodes may, for example, be portable devices, production facilities, sensors, monitoring systems, control systems, Petition 870250085504, dated 09 / 22 / 2025, pp. 88 / 119 27 / 43 devices, laptops, desktop computers, mainframes, data centers, or even devices not conventionally considered a computing node, such as wearables (e.g., eyeglasses, watches, or similar). Memory can take any form and depends on the nature and shape of the computing node.

[071] In this example, peripheral computing nodes (21.1 to 21.n) can be connected to a central computing system (or server). In another example, peripheral computing nodes (21.1 to 21.n) can be attached to the central computing node via, for example, a terminal server (not shown). Most functions can be performed by, or obtained from, the central computing node (also called the remote centralized location). A 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 described in relation to the peripheral computing node (21.n).

[072] 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 circuit configured to perform basic operations of a computer or system and / or, generally, to a device that is configured to perform calculations or logical operations. In particular, the processor, or computer processor, may be configured to process basic instructions that power the computer or system. It may be a semiconductor-based processor, a quantum processor, or any other type of processor configured to process instructions. As an example, the processor may comprise at least one arithmetic logic unit (“ALU”), at least one floating-point unit (“FPU”), such as a math coprocessor or a Petition 870250085504, dated 09 / 22 / 2025, pp. 89 / 119 28 / 43 numeric coprocessor, a plurality of registers, specifically registers configured to provide operands to the ALU and store operation results, and memory, such as 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 graphics processing unit (“GPU”), tensor processing unit (“TPU”), Complex Instruction Set Computing (“CISC”) microprocessor, Reduced Instruction Set Computing (“RISC”) microprocessor, Very Long Instruction Word (“VLIW”) microprocessor, or a processor that implements other instruction sets or processors that implement 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 similar. The methods, systems, and devices described in the present invention may be implemented as software in a DSP, in a microcontroller, or in any other side processor, or as hardware circuitry within an ASIC, CPLD, or FPGA. It should be understood that the term processor may also refer to one or more processing devices, such as a distributed system of processing devices located in multiple computer systems (e.g., cloud computing), and is not limited to a single device unless otherwise specified.

[073] Memory (24) may refer to a physical memory of the system, which may be volatile, non-volatile or a combination thereof. Memory Petition 870250085504, dated 09 / 22 / 2025, pp. 90-119 29 / 43 may include non-volatile mass storage, such as physical storage media. Memory may be a computer-readable storage medium, such as RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, non-magnetic disk storage such as solid-state disk, or any other physical and tangible storage medium that can be used to store desired program code media in the form of computer-executable instructions or data structures and that can be accessed by the computing system. Additionally, memory may be a computer-readable medium that carries computer-executable instructions (also called transmission media).Furthermore, when reaching various components of the computing system, program code media in the form of executable instructions or data structures can be automatically transferred from transmission media to storage media (or vice versa). For example, 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 the computing system's RAM and / or to a less volatile storage medium within a computing system. Thus, it should be understood that storage media can be included within computing components that also (or even primarily) utilize transmission media.

[074] The computing nodes (21, 21.1 to 21.n) may include multiple structures (26) often referred to as an “executable component, executable instructions, computer executable instructions or instructions”. For example, the memory (24) of the computing nodes (21, 21.1 to 21.n) may be illustrated as including the executable component (26). The term Petition 870250085504, dated 09 / 22 / 2025, pp. 91 / 119 30 / 43 “executable component” or any equivalent may be the name for a structure that is well understood by a person skilled in the art in the field of computing as being a structure that may be software, hardware, or a combination thereof, or that may be implemented in software, hardware, or a combination thereof. For example, when implemented in software, a person skilled in the art would understand that the structure of an executable component includes software objects, routines, methods, and so forth, that are executed on compute nodes (21, 21.1 to 21.n), if such executable component is present in the heap (dynamic memory area) of a compute node (21, 21.1 to 21.n), or if the executable component is present on a computer-readable storage medium.In such a case, a person skilled in the art will recognize that the structure of the executable component is present on a computer-readable medium such that, when interpreted by one or more processors of a computing node (21, 21.1 to 21.n), for example, by a processor thread, the computing node (21, 21.1 to 21.n) is led to execute a function. Such a structure may be directly computer-readable by the processors, as is the case if the executable component were binary. Alternatively, the structure may be structured to be interpretable and / or compiled either in a single stage or in multiple stages in order to generate such a binary that is directly interpretable by the processors. Such an understanding of example structures of an executable component is well within the understanding of a person skilled in the art in the field of computing when using the term "executable component".Examples of executable components implemented in hardware include coded or wired logic gates, which are implemented exclusively or almost exclusively in hardware, such as within a field-programmable gate array (FPGA), an application-specific integrated circuit. Petition 870250085504, dated 09 / 22 / 2025, pp. 92 / 119 31 / 43 ASIC or any other specialized circuit. In this description, the terms "component," "agent," "manager," "service," "mechanism," "module," "virtual machine," or similar terms are used synonymously with "executable component."

[075] The processor 22 of each computing node (21, 21.1 to 21.n) can direct the operation of each computing node (21, 21.1 to 21.n) in response to having executed computer executable instructions that constitute an executable component. For example, such computer executable instructions can be incorporated into one or more computer-readable media that form a computer program product. The computer executable instructions can 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 that, when executed in 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 particular function or group of functions.Alternatively or additionally, computer executable instructions can configure the computing node (21, 21.1 to 21.n) to execute a specific function or group of functions. Computer executable instructions can be, for example, binary 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.

[076] 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 (represented as a solid line between peripheral computing nodes and the central computing node in Figure 1). A “network” can be defined as Petition 870250085504, dated 09 / 22 / 2025, pp. 93 / 119 32 / 43 one or more data links that allow 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 other wired, wireless, or a combination of wired and wireless communications connection to a computing node (21, 21.1 to 21.n), the computing node (21, 21.1 to 21.n) appropriately views the connection as a transmission medium. The transmission medium may include a network and / or data links that can be used to transport desired program code media in the form of computer-executable instructions or data structures and that can be accessed by 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'.

[077] 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 in the present invention are not limited to precise output mechanisms (25A) or input mechanisms (25B), as such mechanisms will depend on the nature of the device. However, output mechanisms (25A) may include, for example, displays, speakers, screens, tactile output, holograms, and so forth. Examples of input mechanisms (25B) may include, for example, microphones, touch screens, holograms, cameras, keyboards, mice or other pointing input devices, sensors of any kind, and so forth.

[078] Figure 2 illustrates an exemplary embodiment of a decentralized computing environment (30) with multiple computing nodes (21.1 to 21.n) denoted as filled circles. In contrast to the Petition 870250085504, dated 09 / 22 / 2025, pp. 94 / 119 33 / 43 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 therefore are not under the control of a central computing node. Instead, resources, both hardware and software, can be allocated to each individual computing node (21.1 to 21.n) (local or remote computing system) and data can be distributed among multiple computing nodes (21.1 to 21.n) to perform tasks. Thus, in a decentralized system environment, program modules can be located on local and remote memory storage devices. A 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 described in relation to Figure 1.

[079] Figure 3 illustrates an exemplary embodiment of a distributed computing environment (40). In this description, “distributed computing” can refer to any computing that utilizes multiple computing resources. Such use can be achieved through the virtualization of physical computing resources. An example of distributed computing is cloud computing. “Cloud computing” can refer to 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 can 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) 4(2), applications (43), databases (44), data storage, and server(s) (46).The cloud computing environment (40) can be deployed as a public cloud (47). Petition 870250085504, dated 09 / 22 / 2025, pp. 95 / 119 34 / 43 private cloud (48) or hybrid cloud (49). A private cloud (47) can be owned by an organization and only members of the organization with appropriate access can use the private cloud (48), making the data in the private cloud at least confidential. In contrast, data stored in a public cloud (48) can be open to anyone via the internet. The hybrid cloud (49) can be a combination of private and public clouds (47, 48) and can allow some data to remain confidential while other data can be made publicly available.

[080] Figure 4 illustrates a flowchart of a computer-implemented method for providing nitrogen uptake data by plants and / or plant parts in an agricultural field. In a first step (100), leaf area index (LAI) data are provided for the agricultural field. In a further step (110), chlorophyll content data are provided for the agricultural field. In a further step (120), a nitrogen uptake model is provided, configured to provide nitrogen uptake data by plants and / or plant parts based on leaf area index data and chlorophyll content data. In a further step (130), nitrogen uptake data by plants and / or plant parts of the agricultural field are provided based on the provided leaf area index data and chlorophyll content data, using the nitrogen uptake model.Figure 5 illustrates a system (10) for providing nitrogen uptake data by plants and / or plant parts from an agricultural field, comprising: a supply unit (11) configured to provide leaf area index data for the agricultural field; an additional supply unit (12) configured to provide chlorophyll content data for the agricultural field; an additional supply unit (13) configured to provide a nitrogen uptake model configured to provide nitrogen uptake data by plants and / or plant parts. Petition 870250085504, dated 09 / 22 / 2025, pp. 96 / 119 35 / 43 plants based on leaf area index data and chlorophyll content data; and an additional supply unit (14) configured to supply nitrogen uptake data by plants and / or plant parts from the agricultural field based on the leaf area index data and chlorophyll content data supplied, using the nitrogen uptake model.

[081] Figure 6 is a further illustration of a computer-implemented method for providing nitrogen uptake data by plants and / or plant parts from an agricultural field. In a first step, satellite data / images (50) of an agricultural field can be provided. This satellite data is provided to the leaf area and chlorophyll content model (51), which can be provided by at least one machine learning model. The machine learning model with respect to the leaf area index data (52) can be an XGBBOOST regression model based on satellite image analysis.In this regard, a combination of six features can be used, where it is preferable that 5 spectral bands and a vegetation index be used as features (variables) for the machine learning model, wherein the spectral bands Red Edge 2, Red Edge 3, Narrow NIR, SWIR 1, SWIR 2 and the combined vegetation index MSR_Red&Red_Edge can be used as features (variables). The machine learning model with respect to chlorophyll content data (53) can also be an XGBBOOST regression model based on satellite image analysis.In this sense, a combination of six features can be used, with the use of two spectral bands and four vegetation indices as features (variables) for the machine learning model being preferable, with the spectral bands being Red Edge 1 and SWIR 2. Petition 870250085504, dated 09 / 22 / 2025, pp. 97 / 119 36 / 43 (shortwave infrared 2), and the vegetation indices NDWI (Normalized Difference Water Index), GNDVI (Green Normalized Difference Vegetation Index), REIP (Red Edge Inflection Point), Chlr_Red_Edge (combined vegetation index). In this regard, reference is also made to the article “Vegetation Indices Combining the Red and Red-Edge Spectral Information for Leaf Area Index Retrieval”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (Volume: 11, Issue: 5, May 2018). Leaf area index data and chlorophyll content data for the agricultural field are obtained using the leaf area and chlorophyll content model (51).

[082] In the illustrated example, a leaf area index of 1.6 m2 of leaves per m2 of soil and a leaf chlorophyll concentration of 50 pg of chlorophyll per cm2 of leaf were determined based on satellite data / images. Both values ​​can be used to determine / calculate leaf nitrogen uptake (54). For the illustrated example, a leaf nitrogen uptake of 52 kg of nitrogen per hectare (ha) can be derived.

[083] As explained above, according to the present invention, stem nitrogen data, for example, stem nitrogen content, which is used to determine nitrogen absorption, are determined based on the leaf weight ratio, specifically, stem weight data derived from the leaf weight ratio.

[084] For example, the nitrogen content in the stem can be estimated as follows: In a first step, the stem weight can be estimated based on a specific leaf weight ratio for the given crop, i.e., the leaf area index can be converted into stem weight based on empirical and / or experimental values. Then, the Petition 870250085504, dated 09 / 22 / 2025, pp. 98 / 119 37 / 43 stem weight can be converted into a specific stem nitrogen content for the crop, considering a specific stem nitrogen concentration for the crop, which in turn can be derived through empirical and / or experimental values.

[085] Alternatively or additionally, and as shown in Figure 6, stem weight data can also be determined by a specific growth model for the plant in question (55). As input data for such a growth model, meteorological data (56), soil data (57), etc., can be used, for example. From the stem weight data obtained by the model (55), stem nitrogen uptake can be determined as explained above. For the example illustrated, a stem nitrogen uptake of 26 kg of nitrogen per hectare (ha) can be derived. As a result, for the example illustrated, a crop nitrogen uptake (“Crop N” (58)) of 78 kg of nitrogen per ha can be derived, which is the sum of the foliar nitrogen uptake and stem nitrogen uptake described above.

[086] Here, reference is also made to Figure 9, discussed in detail below, which is an illustration showing that the leaf weight ratio can be time- and location-dependent. Thus, a leaf weight ratio can be determined for the time the satellite images are acquired, for the crop represented by the satellite images, based on a query or the growth model described above. To do so, the time of acquisition of the satellite images can be retrieved, for example, from a date and time stamp of the images or from a storage source.

[087] Thus, it is understood that the overall modeling involves the combination of the determination of LAI (52) and chlorophyll content data (53), for example, determined by a model (51) and derived from images of Petition 870250085504, dated 09 / 22 / 2025, pp. 99 / 119 38 / 43 satellites that provide input data for the model (51), and stem weight data derived from the RPF value (time-dependent), which in turn can be derived from a (growth) model (55) or can be consulted. Thus, within the overall nitrogen uptake modeling, models can optionally be used for different substages. Alternatively to one model (51), multiple models can be used for the respective determination of LAI and chlorophyll content data.

[088] Figure 7 shows an exemplary map of nitrogen uptake from an agricultural field, in which nitrogen uptake by the crop is derived as explained above. For example, such a specific plant growth model was published by Hunt et al. (“Effects of Nitrate Application on Amaranthus powellii Wats”, Plant Physiology, Volume 79, Issue 3, November 1985, pages 619-624), which refers to Amaranthus powellii, a small grain crop, particularly known in the bioorganic and cereal segment.

[089] Figure 8 illustrates, in an exemplary way, the different possibilities of receiving and processing field data (e.g., image data, control data, etc.). For example, field data can be obtained by all types of agricultural equipment (300) (e.g., a tractor (300)) as so-called as-applied maps (i.e., a map showing how the fertilizer was actually applied), or by recording the application rate at the time of application. It is also possible that such agricultural equipment includes sensors (e.g., optical sensors, cameras, infrared sensors, soil sensors, etc.) to provide, for example, a map of weed distribution. It is also possible that, during harvesting, the production (e.g., in the form of biomass) is recorded by a harvesting vehicle (310). In addition, corresponding maps / data can be provided by ground drones and / or Petition 870250085504, dated 09 / 22 / 2025, pages 100 / 119 39 / 43 aerial (320), capturing images of the field or part of it. Finally, it is also possible that a georeferenced visual assessment (330) is carried out and that this field data is also processed. The field data collected in this way can then be merged into a computing device (340), where the data can be transmitted and computed, for example, via any wireless link, cloud applications (350) and / or work platforms (360), where the field data can also be processed in whole or in part in the cloud application (350) and / or work platform (360) (for example, by cloud computing).

[090] Figure 9 illustrates an example of a leaf weight ratio (LWR) for different locations and years and its development over time, such as the day of the year (DOY). More specifically, Figure 9 illustrates, for two years (here, for example, 2021 and 2022, for illustrative purposes only), the annual and spatial effects on the seasonal dynamics of LWR for two specific geographic field positions (denoted as Loc_1 and Loc_2). The x-axis refers to time, in this example, the time of year, for example, the Day of the Year (DOY), and the y-axis, to LWR.

[091] To further emphasize and illustrate the role of RPF, the method of the present invention is reiterated below.

[092] As explained above, the present invention provides a computer-implemented method for providing nitrogen uptake data by plants and / or plant parts from an agricultural field, comprising: providing leaf area index data for the agricultural field; providing chlorophyll content data for the agricultural field; providing a nitrogen uptake model configured to provide nitrogen uptake data by plants and / or plant parts based on leaf area index data and chlorophyll content data; providing nitrogen uptake data by plants and / or plant parts from the field. Petition 870250085504, dated 09 / 22 / 2025, pp. 101 / 119 40 / 43 agricultural based on provided leaf area index and chlorophyll content data, using the nitrogen uptake model. The method further comprises determining stem weight data based on a specific leaf weight ratio for the provided crop; determining stem nitrogen data based on stem weight data and a specific nitrogen concentration for the provided crop. According to the present invention, the provision of nitrogen uptake data by plants and / or plant parts from the agricultural field is further based on the determined stem nitrogen data.

[093] Using the leaf weight ratio in determining nitrogen uptake allows for more precise determinations of nitrogen uptake.

[094] A (crop) model configured to provide a site-specific crop organ allocation coefficient, such as the leaf weight ratio (LWR), can be employed to obtain the LWR. The LWR, provided by a model, is affected by geographic location, climatic conditions, the model's internal logic, and agricultural practices such as sowing date and variety.

[095] It is understood from the above that the present invention can provide a model (of nitrogen absorption) that provides, as an intermediate step, indicative data of the dry mass of one or more crop organs (for example, at least one of root mass data, stem weight data, leaf mass data, seed mass data and fruit mass data) at a given time, for example, the time when satellite images are acquired, based on a dynamic biomass allocation coefficient (such as RPF and / or root-to-shoot ratio and / or stem-to-shoot ratio), particularly on a daily basis throughout the season. The dry mass, particularly the RPF value at that time Petition 870250085504, dated 09 / 22 / 2025, pages 102 / 119 41 / 43 moment, can additionally be used to predict nitrogen absorption.

[096] More specifically, a model, such as a crop growth model. One can provide the RPF and an ideal N uptake (in g of N per m2 of soil). Using data derived from remote sensing, such as satellite imagery, and data derived from the crop growth model, the nitrogen uptake model provides an actual N uptake (in g of N per m2 of soil).

[097] For example, when determining nitrogen uptake for a given moment, for example, for a given day, using nitrogen uptake models, satellite images acquired at that moment can be retrieved. The moment when the satellite images were acquired can be determined or retrieved, for example, from a timestamp or database. Using that moment and the temporal dependence of the RPF value, the RPF value at that moment can be determined. For example, the satellite image can be captured on a specific day and the RPF value for that day can be determined based on the temporal dependence. An example of this temporal dependence is illustrated in Figure 9.

[098] The present invention can provide a (nitrogen uptake) model that is a process-based model and can take, as input data, at least one of the following: crop type, variety, sowing / planting data and site-specific soil and climate data, particularly for use by the crop growth model that predicts RPF.

[099] Aspects of the present invention relate to computer program elements configured to perform steps of the methods described above. The computer program element can therefore be Petition 870250085504, dated 09 / 22 / 2025, pp. 103 / 119 42 / 43 stored in a computing unit of a computing device, which may also be part of an exemplary embodiment. This computing unit may be configured to execute or induce the execution of the steps of the method described above. In addition, it may be configured to operate the components of the system described above. The computing unit may be configured to operate automatically and / or execute user commands. The computing unit may include a data processor. A computer program may be loaded into the working memory of a data processor. The data processor may therefore be equipped to execute the method according to a previous exemplary embodiment.This exemplary embodiment of the present disclosure encompasses both a computer program that from the outset uses the present disclosure and a computer program that, through an update, transforms an existing program into a program that uses the present disclosure. Furthermore, the computer program element may be capable of providing all the steps necessary to accomplish the procedure of an exemplary embodiment of the method as described above. According to another exemplary embodiment of the present disclosure, a computer-readable medium is presented, such as a CD-ROM, USB drive, a downloadable executable, or similar, wherein the computer-readable medium has a computer program element stored on it, this computer program element being described in the preceding section.A computer program can be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied with or as part of other hardware, but it can also be distributed in other ways, such as via the internet or other wired or wireless telecommunication systems. However, the computer program can also be presented over a network such as a... Petition 870250085504, dated 09 / 22 / 2025, pp. 104 / 119 43 / 43 World Wide Web and can be downloaded to the working memory of a data processor from such network. According to an exemplary embodiment of the present disclosure, a means is provided for making a computer program element available for download, this computer program element being arranged to execute a method according to one of the exemplary embodiments of the present invention described above.

[100] The present invention has been described in conjunction with a preferred embodiment, which is also exemplary. However, other variations may be understood and carried out by those skilled in the art and practicing the claimed invention, based on studies of the drawings, this disclosure and the claims. Notably, in particular, any of the steps presented can be performed in any order, i.e., the present invention is not limited to a specific order of these steps. Furthermore, it is not necessary that the different steps be performed at a particular location or node of a distributed system, i.e., each of the steps can be performed at different nodes using different data processing equipment / units.

[101] In the claims, as well as in the description, the word “comprising” does not exclude other elements or steps, and the indefinite article “a / an” does not exclude a plurality. A single element or other unit may perform the functions of several entities or items mentioned in the claims. The mere fact that certain measures are mentioned in different claims that are dependent on each other does not indicate that a combination of these measures cannot be used in an advantageous implementation. Petition 870250085504, dated 09 / 22 / 2025, pages 105 / 119

Claims

1 / 5 Claims 1. COMPUTER-IMPLEMENTED METHOD for providing nitrogen uptake data by plants and / or plant parts of an agricultural field, characterized by comprising: providing (100) leaf area index data for the agricultural field; providing (110) chlorophyll content data for the agricultural field; providing (120) a nitrogen uptake model configured to provide nitrogen uptake data by plants and / or plant parts, wherein the input data of the nitrogen uptake model are the provided leaf area index data and chlorophyll content data; providing (130) nitrogen uptake data by plants and / or plant parts of the agricultural field based on the provided leaf area index data and chlorophyll content data using the nitrogen uptake model; wherein the method comprises: - determining stem weight data based on a provided crop-specific leaf weight ratio;- Determine stem nitrogen data based on stem weight data and a crop-specific stem nitrogen concentration provided; wherein the provision of nitrogen uptake data by plants and / or plant parts from the agricultural field is further based on the determined stem nitrogen data.

2. METHOD, according to claim 1, characterized in that the crop-specific leaf weight ratio is used as an input to the nitrogen uptake model or determined by a growth model as part of the nitrogen uptake model. Petition 870250085504, dated 09 / 22 / 2025, pp. 106 / 119 2 / 5 3. METHOD, according to either claim 1 or 2, characterized in that chlorophyll content data are provided as leaf chlorophyll content (LC) data and / or canopy chlorophyll content (CCHL) data.

4. METHOD, according to any of the preceding claims, characterized in that leaf area index data and chlorophyll content data for the agricultural field are obtained using a leaf area and chlorophyll content model (51), configured to provide leaf area index data and chlorophyll content data based on surface reflectance bands of at least one satellite image, wherein the leaf area and chlorophyll content model is preferably adapted to different crop varieties, crop types, growth stages, soil conditions and / or data sources.

5. METHOD, according to claim 4, characterized in that the leaf area and chlorophyll content model is a machine learning model and in that the leaf area index and chlorophyll content data for the agricultural field are obtained by using the leaf area and chlorophyll content model, wherein the machine learning model is preferably: an artificial neural network (ANN), multiple linear regression, random forest regression or an approach capable of establishing a statistical relationship to predict the leaf area index and chlorophyll content data.

6. METHOD, according to any of the preceding claims, characterized in that the nitrogen absorption model is additionally based on a chlorophyll-to-foliar nitrogen conversion factor specific to each crop.

7. METHOD, according to any of the preceding claims, characterized in that the method further comprises: providing a nitrogen absorption map of the agricultural field Petition 870250085504, dated 09 / 22 / 2025, page 107 / 119 3 / 5 based on the nitrogen absorption data provided, wherein the map preferably has a resolution between 1 and 50 meters, preferably 5 and 30 m, more preferably 10 m.

8. METHOD, according to any of the preceding claims, characterized in that the method further comprises: providing a specific target nitrogen value for the crop; providing nitrogen demand data based on nitrogen uptake data and the target nitrogen value.

9. METHOD, according to claim 8, characterized in that the method further comprises: providing a nitrogen demand map of the agricultural field based on the nitrogen demand data provided, wherein the map preferably has a resolution between 1 and 50 m, preferably 5 and 30 m, most preferably 10 m.

10. METHOD, according to any one of claims 8 or 9, characterized in that the method further comprises: providing control data for a fertilizer application device for the variable application of a fertilizer product in the agricultural field based on nitrogen demand data.

11. METHOD, according to any one of claims 8 to 10, characterized in that the method further comprises: providing control data for an application device for the variable application of an agricultural product in the agricultural field based on nitrogen demand data, wherein the agricultural product is: a crop protection product, a biostimulant product, a growth regulator product and / or a desiccation product.

12. APPARATUS FOR PROVIDING NITROGEN UPTAKE DATA by plants and / or plant parts from an agricultural field, Petition 870250085504, dated 09 / 22 / 2025, pp. 108 / 119 4 / 5 characterized by comprising: one or more computing nodes; and one or more computer-readable media containing computer-executable instructions that are structured in such a way that, when executed by one or more computing nodes, they cause the apparatus to perform the following steps: - provide leaf area index data for the agricultural field; - provide chlorophyll content data for the agricultural field; - provide a nitrogen uptake model configured to provide nitrogen uptake data by plants and / or plant parts based on leaf area index data and chlorophyll content data; - determine stem weight data based on a crop-specific leaf weight ratio provided;- Determine stem nitrogen data based on stem weight data and a crop-specific stem nitrogen concentration provided; - Provide nitrogen uptake data by plants and / or plant parts in the agricultural field based on provided leaf area index data and chlorophyll content data using the nitrogen uptake model, where the provision of nitrogen uptake data by plants and / or plant parts in the agricultural field is further based on the determined stem nitrogen data.

13. FERTILIZER APPLICATION DEVICE for applying a fertilizer product to an agricultural field, characterized in that the control data for the fertilizer application device are provided, at least partially, as defined in any one of claims 10 or 11.

14. COMPUTER PROGRAM ELEMENT with Petition 870250085504, dated 09 / 22 / 2025, page 109 / 119 5 / 5 instructions, characterized by, when executed on computing devices in a computing environment, being configured to execute the steps of the computer-implemented method, as defined in any of claims 1 to 11, and / or on an apparatus, as defined in claim 12.

15. USE of leaf area index data, chlorophyll content data, nitrogen absorption model and / or satellite imagery, characterized by being for use in a computer-implemented method, as defined in any of claims 1 to 11 and / or in an apparatus, as defined in claim 12. Petition 870250085504, dated 09 / 22 / 2025, pp. 110 / 119

Images