Method for providing nitrogen absorption data of plants and / or plant parts in a field

Abstract

A computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, comprising: providing field leaf area index data (100); providing field chlorophyll content data (110); providing a nitrogen absorption model configured to provide nitrogen absorption data of plants and / or plant parts based on the leaf area index data and chlorophyll content data (120); and providing nitrogen absorption data of plants and / or plant parts in a field based on the provided leaf area index data and chlorophyll content data (130). The method further comprises determining stem weight data based on the provided crop-specific leaf weight ratio, and identifying stem nitrogen data based on the stem weight data and the provided crop-specific stem nitrogen concentration. Providing nitrogen absorption data of plants and / or plant parts in a field is further based on the identified stem nitrogen data.

Description

[Technical Field]

[0001] This disclosure relates to a computer implementation method for providing nitrogen absorption data of field plants and / or plant parts, a system for providing nitrogen absorption data of field plants and / or plant parts, an apparatus for providing nitrogen absorption data of field plants and / or plant parts, a fertilizer applicator for applying fertilizer products to a field, corresponding computer program elements, and the use of the data. [Background technology]

[0002] The general background to this disclosure is the treatment of fields with fertilizer products. Farmers apply fertilizer products, such as urea, ammonium nitrate, ammonium sulfate, calcium ammonium nitrate, compost, slurry, etc., which contain nitrogen forms such as ammonium, nitrates, and / or organic nitrogen. Nitrogen is an essential element for plant growth, plant health, and reproduction. Some of the nitrogen (ammonium or nitrates) available to plants in the soil comes from the decomposition process (mineralization) of organic nitrogen compounds such as humus, animal and plant residues, and organic fertilizers. Another portion is obtained from rainfall. However, globally, the vast majority (according to some sources, about 90%) is supplied to plants by organic and inorganic (so-called inorganic) nitrogen fertilizers. The most commonly used inorganic nitrogen fertilizers contain urea and / or ammonium compounds or their derivatives; in other words, nearly 90% of nitrogen fertilizers applied worldwide are in the form of urea and / or NF (see Subbarao et al., 2012, Advances in Agronomy, 114, 249-302). However, in many cases, it is difficult for farmers to objectively determine whether and how they should apply each fertilizer product.

[0003] Inorganic nitrogen (N) fertilizers are crucial for meeting global food demand. More than 50% of global protein production depends on the production and use of inorganic N fertilizers. However, excessive use of N fertilizers threatens the quality of the atmosphere, water, oceans, and soil pools and contributes to global warming. The methods and systems of this disclosure will contribute to the more sustainable use of fertilizers. As can be seen from the following description, this can be achieved, for example, by making it possible to determine the in-situ crop N uptake during the growing season of the crop.

[0004] This disclosure refers to the paper "Vegetation Indices Combining the Red and Red Edge Spectral Information for Leaf Area Index Retrieval" in the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (Volume: 11, Issue: 5, May 2018).

[0005] It is clear that there is a greater need to provide objective means to support farmers in the use of fertilizer products. In particular, there is a greater need to provide objective means to actually avoid over-fertilization. [Overview of the project] [Means for solving the problem]

[0006] One aspect of this disclosure relates to a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, The steps include providing leaf area index data for the field, The steps include providing chlorophyll content data for the field, The steps include providing a nitrogen absorption model configured to provide nitrogen absorption data for plants and / or plant parts based on leaf area index data and chlorophyll content data, Using a nitrogen absorption model, the steps include providing nitrogen absorption data for plants and / or plant parts in a field based on the provided leaf area index data and chlorophyll content data, Computer implementation methods, including the above, are disclosed.

[0007] In particular, in some embodiments, the method may optionally include the steps of identifying stem weight data based on a provided crop-specific leaf weight ratio, and identifying stem nitrogen data based on the stem weight data and a provided crop-specific stem nitrogen concentration. According to this disclosure, providing nitrogen uptake data for field plants and / or plant parts is further based on the identified stem nitrogen data.

[0008] In particular, the crop-specific leaf weight ratio may be used as input for a nitrogen absorption model, or it may be determined by a growth model, for example, as part of a nitrogen absorption model.

[0009] Another aspect of this disclosure is a system for providing nitrogen absorption data of plants and / or plant parts in a field, A leaf area index data providing unit configured to provide field leaf area index data, A chlorophyll content data providing unit configured to provide field chlorophyll content data, A nitrogen absorption model providing unit configured to provide a nitrogen absorption model configured to provide nitrogen absorption data of plants and / or plant parts based on leaf area index data and chlorophyll content data, Including, related to the system.

[0010] The system can optionally, A stem nitrogen concentration identification unit configured to identify stem weight data based on the provided crop-specific leaf weight ratio, and to identify stem nitrogen data based on the stem weight data and the provided crop-specific stem nitrogen concentration, A nitrogen absorption data providing unit configured to provide nitrogen absorption data for field plants and / or plant parts based on a nitrogen absorption model, provided leaf area index data and chlorophyll content data, and further based on identified stem nitrogen data, This may further include:

[0011] Another aspect of this disclosure relates to an apparatus for providing nitrogen absorption data of field plants and / or plant parts, wherein the apparatus comprises one or more computing nodes and one or more computer-readable media, which, when executed by one or more computing nodes, provides the apparatus the following steps, namely: The steps include providing leaf area index data for the field, The steps include providing chlorophyll content data for the field, The steps include providing a nitrogen absorption model configured to provide nitrogen absorption data for plants and / or plant parts based on leaf area index data and chlorophyll content data, and One or more computer-readable media having computer-executable instructions configured thereon to execute, Regarding devices including...

[0012] The steps are optional. Steps include identifying stem weight data based on the provided crop-specific leaf weight ratio, The steps include determining stem nitrogen data based on stem weight data and provided crop-specific stem nitrogen concentration, and providing nitrogen absorption data for field plants and / or plant parts based on provided leaf area index data and chlorophyll content data, and further based on the identified stem nitrogen data, using a nitrogen absorption model. It also includes.

[0013] In particular, crop-specific leaf weight ratios can be used as input for nitrogen absorption models.

[0014] Another aspect of the present disclosure relates to a fertilizer applicator for applying a fertilizer product to a field, wherein the control data of the fertilizer applicator is provided at least in part according to a computer-implemented method that provides nitrogen uptake data of plants and / or plant parts in the field according to the present disclosure. Note that the fertilizer applicator may be a specific type of fertilizer applicator, such as a sprayer. The fertilizer applicator is configured to receive, via a communication interface, control data and / or data for performing one or more of the method steps for providing the control data, and / or may include a processor configured to perform at least some or all of the method steps for providing the control data.

[0015] Another aspect of the present disclosure relates to a computer program element having instructions that, when executed on a computing device in a computing environment, are configured to perform the steps of a computer-implemented method that provides nitrogen uptake data of plants and / or plant parts in a field according to the present disclosure.

[0016] Another aspect of the present disclosure relates to the use of leaf area index data, chlorophyll content data, nitrogen uptake models, and / or satellite images in a computer-implemented method for providing nitrogen uptake data of plants and / or plant parts in a field.

[0017] In certain aspects according to the present disclosure, this embodiment and other embodiments described herein relate to the methods, systems, agricultural devices, uses, computer program elements outlined above, and vice versa. Advantageously, the advantages provided by any of the plurality of embodiments and examples apply equally to all other embodiments and examples, and vice versa. As used herein, "determine" also includes "estimate", "calculate", "initiate or cause a determination to be made", "generate" also includes "initiate or cause a generation to be made", and "provide" also includes "initiate or cause a determination, generation, selection, transmission, query, or reception to be made".

[0018] Leaf area index data may particularly include leaf area index and optionally other data. Chlorophyll content data may particularly include chlorophyll content and optionally other data. Nitrogen uptake data may particularly include nitrogen uptake amount and optionally other data. Stem weight data may particularly include stem weight and optionally other data.

[0019] Chlorophyll content data may be provided as leaf chlorophyll content and optionally other data including leaf chlorophyll content (LC) data, and / or as canopy chlorophyll content and optionally other data including canopy chlorophyll content (CCHL) data.

[0020] Leaf area index is a term commonly used in the industry. It should be understood as the leaf area per unit area of the ground (e.g., leaf m 2 per ground 1 m 2 ). This can be derived from proximity or remote sensing devices, such as satellite images, as will be described in detail below.

[0021] LAI can be converted to leaf mass (also called LDM, e.g., kg / ground 1 m 2 ). This can be done by multiplying LAI by the specific leaf area (called SLA, leaf m 2 per kg of leaf DrM (dry mass)). The value of SLA may vary for each crop and growth stage and is derived from databases or crop growth models.

[0022] Stem mass (called SDM, kg per ground 1 m 2 ) can be derived from the leaf weight ratio (called LWR, LDM kg / (LDM + SDM kg)).

[0023] LWR may be considered a biomass allocation coefficient, which varies for each crop and growth stage and can be derived from databases or crop growth models.

[0024] Chlorophyll concentration (CHL, measured per 1 cm² of leaf area) 2 The amount of Chl (μg) per unit can be derived from proximity or remote sensing equipment, for example, from satellite imagery.

[0025] CHL can be converted to leaf nitrogen concentration (LNC; N kg / LDM kg) by using the chlorophyll-to-N coefficient (called Chl_N, the mass of N per unit mass of Chl) and the molecular weight of chlorophyll (MM; kg / mol).

[0026] Crop-specific Chl_N and MM can be obtained or derived from, for example, data sources. Publicly available data exists that can be obtained for this purpose.

[0027] According to this disclosure, the leaf weight ratio (LWR) may be a dynamic value, i.e., a value that changes over time, for example, throughout the seasons. As an example, the daily leaf weight ratio may be used. The leaf weight ratio is an example of a dynamic biomass allocation coefficient.

[0028] LWR can be geographically dependent. In particular, LWR can be time and location dependent. Leaf weight ratio can be dependent on at least one of the following: geographical location, weather conditions, and agricultural practices / parameters such as sowing date and variety.

[0029] The leaf weight ratio can be determined using a model. For example, the model may take into account geographical location, weather conditions, the model's internal logic, and at least one of agricultural practices / parameters such as sowing date and variety.

[0030] Using leaf weight ratios to determine nitrogen absorption allows for more accurate determination of nitrogen absorption.

[0031] For example, the LWR (Leaf Weight Ratio) can be obtained using a (crop) model configured to provide location-specific crop organ allocation coefficients such as the LWR. The LWR provided by the model is influenced by geographical location, weather conditions, the model's internal logic, and agricultural practices such as sowing date and variety.

[0032] From the above, it will be understood that this disclosure may provide a (nitrogen absorption) model that provides data indicating the dry mass of one or more crop organs (e.g., at least one of root mass data, stem weight data, leaf mass data, seed mass data, and fruit mass data) based on dynamic biomass allocation coefficients (LWR and / or root-to-bud and / or stem-to-bud, etc.) on a daily basis, particularly throughout the season.

[0033] This disclosure may provide a (nitrogen absorption) model, which is a process-based model and may take at least one of the following as input data: crop type, variety, sowing / planting date, and site-specific soil and weather data. This is the case when a growth model disclosed below is employed, for example, a plant-specific growth model in which stem weight data is identified by the plant-specific growth model (details of which are given below). Such a growth mode may take at least one of the following as input data: crop type, variety, sowing / planting date, and site-specific soil and weather data, and may output, for example, stem weight data.

[0034] The purpose of this disclosure is to provide objective means to assist farmers in the use of fertilizer products. In particular, the purpose of this disclosure is to provide objective means to actually avoid over-fertilization. Another purpose of this disclosure is to provide data that can be used to provide control data for fertilizer applicators.

[0035] These objectives, and other objectives which will become clear from reading the following description, are addressed by the subject matter of the independent claims. The dependent claims relate to preferred embodiments of the present invention.

[0036] As used herein, the term “field” should be understood broadly and refers to all areas of soil to be treated with fertilizer products, i.e., the surface and subsurface. A field can be any area where any plant or crop is cultivated, such as a farm or greenhouse. Plants can be crops, weeds, native plants, crops from the previous growing season, useful plants, or any other plants present in the field. A field can be identified by referring to its geographical location or georeferencing location data through field data. Reference coordinates, size, and / or shape may be used to further identify a field. Field data may be used to calculate fertilizer rate / amount for a field. Field data may also be used to indicate which climatic region the field is located in. Field data, in particular the geographical location of the field, may be further used to provide meteorological data, e.g., historical, current, and / or forecast meteorological data. In particular, field data can be further used to provide soil parameter data, topographic data, and any other data that can be used to fine-tune the emissions calculation model.

[0037] The "Leaf Area Index (LAI)" is defined as the total one-sided leaf area per unit ground area. LAI is one of the most important biophysical parameters characterizing the canopy. "Chlorophyll content" may be provided as chlorophyll content (LC) data and / or canopy chlorophyll content (CCHL) data. In this regard, field leaf area index (LAI) data and chlorophyll content data may be obtained by 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. The leaf area index and chlorophyll content model is preferably adapted to different crop varieties, crop types, growth stages, soil conditions, and / or data sources.

[0038] LAI data may be provided in netCDF file format, for example, as a global multiband NetCDF4 file containing metadata compliant with the Climate and Forecasting (CF) standard. In addition, or alternatively, LAI data may also be provided as an INSPIRE-compliant metadata file in XML format, a corresponding XSLT for XML viewing, and a subsampled color Quicklook in GeoTIFF format.

[0039] Furthermore, the leaf area and chlorophyll content models may be machine learning models, and the leaf area index data and chlorophyll content data for a field can be obtained using the leaf area and chlorophyll content models. That is, for example, the predictions of the machine learning model may be leaf area index data and chlorophyll content data. The machine learning model may preferably be an artificial neural network (ANN), multiple linear regression, random forest regression, or a method capable of establishing statistical relationships for predicting leaf area index data and chlorophyll content data. The leaf area and chlorophyll content models may be provided as a single integrated machine learning model, or as two separate machine learning models, one for the leaf area index and the other for chlorophyll content. In the case of two separate machine learning models, for example, one may predict leaf area index data and the other may predict chlorophyll content.

[0040] "Machine learning algorithms" may include decision trees, Naive Bayesian classification, nearest neighbor algorithms, neural networks, convolutional or recurrent neural networks, transformers, generative adversarial networks, support vector machines, linear regression, logistic regression, random forests, and / or gradient boosting algorithms. Preferably, the results of a machine learning algorithm are used to refine the fertilizer application logic. Preferably, the machine learning algorithm is configured to process high-dimensional inputs into much lower-dimensional outputs. Such machine learning algorithms are referred to as "intelligent" because they can be "trained." The algorithm may be trained using records of training data. Records of training data include training input data and corresponding training output data. The training output data of the training data records is the result that the machine learning algorithm is expected to produce when given training input data of the same training data records as the input. The difference between this expected result and the actual result produced by the algorithm is observed and evaluated by a "loss function." This loss function is used as feedback to adjust the parameters of the internal processing chain of the machine learning algorithm. For example, parameters can be adjusted to optimize a loss function that minimizes the value of a loss function obtained by feeding all input data to a machine learning algorithm and comparing the results with the corresponding training output data. As a result of this training, even if a relatively small number of training data records are given as "ground truth," the machine learning algorithm can perform its job properly for a number of input data records that are orders of magnitude larger.

[0041] As used herein, the term “control data” should be understood broadly hereof to represent any data configured to operate and control a fertilizer spreader. The control data is provided by a control unit and may be configured to control one or more technical means of the fertilizer spreader, such as, but is not limited to, a drive control unit.

[0042] As used herein, the term "fertilizer applicator" should be understood in a broad sense in this case and represents any device configured to apply fertilizer to the soil of a field or to the crop canopy of a field. The fertilizer applicator can be configured to traverse a field. The fertilizer applicator can be a ground or aerial vehicle, such as a tractor, rail vehicle, robot, airplane, unmanned aerial vehicle (UAV), drone, etc. The fertilizer applicator can be an autonomous or non-autonomous fertilizer applicator.

[0043] As used herein, the term "fertilizer" or "fertilizer product" should be understood in a broad sense and includes any solid or liquid fertilizer product and combinations thereof. As used herein, the term fertilization should be understood in a broad sense in this case and represents any action for spreading, placing, or introducing fertilizer / fertilizer product into the soil area of a field. Fertilizer is any substance of natural or synthetic origin applied to the soil or plant tissue to supply plant nutrients. Fertilizer products can contain urea, NO 3- , NH4 + -ions, NH3, and / or organic N, or can decompose, for example by hydrolysis, to NH4 in the soil +It may be possible to generate ions or NH3. The term fertilizer 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), or through substitutional bases in the soil (likewise 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 described below. The term fertilizer can be subdivided into several categories, including a) organic fertilizers (consisting of decaying plant / animal matter), b) inorganic fertilizers (consisting of chemicals and minerals), and c) urea-containing fertilizers. Examples of organic fertilizers include compost, e.g., liquid fertilizers, semi-liquid fertilizers, biogas fertilizers, manure or straw compost, slurry, worm cast, peat, seaweed, compost, sewage, and guano. Green manure crops are also grown regularly to add nutrients (especially nitrogen) to the soil. Examples of organic fertilizers produced include compost, blood meal, bone meal, and seaweed extracts. Other examples include enzyme-digested proteins, fish meal, and feather meal. Decomposed crop residues from the previous year are yet another source for fertilization. In addition, natural minerals such as phosphate rock, potassium sulfate, and limestone are also considered inorganic fertilizers. Inorganic fertilizers are usually produced using naturally occurring deposits and chemical processes that chemically transform them (e.g., concentrated superphosphate of lime) (e.g., obtaining N from the Haber-Bosch process). Examples of naturally occurring inorganic fertilizers include Chilean nitrate, phosphate rock, limestone, and raw potassium fertilizer. In certain embodiments, inorganic fertilizers may be "NPK fertilizers," "NP fertilizers," and "NK fertilizers." NPK fertilizers are inorganic fertilizers formulated in appropriate concentrations and combinations, typically containing three major nutrients: nitrogen (N), phosphorus (P), and potassium (K), as well as S, Mg, Ca, and trace elements. NP fertilizers are inorganic fertilizers formulated with appropriate concentrations and combinations of two major nutrients, nitrogen (N) and phosphorus (P), as well as typically S, Mg, Ca, and trace elements. NK fertilizers are inorganic fertilizers formulated with appropriate concentrations and combinations of two major nutrients, nitrogen (N) and potassium (K), as well as typically S, Mg, Ca, and trace elements.Other inorganic fertilizers may include ammonium nitrate, calcium ammonium nitrate, ammonium nitrate sulfate, ammonium sulfate, or ammonium phosphate. In certain embodiments, urea-containing fertilizers may be urea, formaldehyde urea, urea-ammonium nitrate (UAN) solution, sulfur-coated urea, stabilized urea, urea-based NPK fertilizer, or urea-ammonium sulfate. The use of urea as a fertilizer is also envisioned. When urea-containing fertilizers or urea are used or provided, it is particularly preferable that urease inhibitors, as already defined herein, may be added, or may be present or used concurrently with or in conjunction with the urea-containing fertilizer. Urea-containing fertilizers are hydrolyzed by microorganisms, thereby releasing ammonia, which in turn forms ammonium ions. Therefore, urea-containing fertilizers can be considered a storage form of ammonium. The fertilizer may be selected from solid or liquid ammonium-containing and / or nitrate-containing inorganic fertilizers, such as NPK, NP, and NK fertilizers, ammonium nitrate, calcium ammonium nitrate, ammonium nitrate sulfate, ammonium sulfate, calcium nitrate, or ammonium phosphate; solid or liquid organic fertilizers, such as liquid fertilizers, semi-liquid fertilizers, stabilized fertilizers, biogas fertilizers, and straw fertilizers, wormcast, compost, seaweed, or guano; or urea-containing fertilizers, such as urea, formaldehyde urea, urea-ammonium nitrate (UAN) solution, sulfur-coated urea, stabilized urea, urea-based NPK, NP, and NK fertilizers, urea-ammonium sulfate, or mixtures thereof. Preferably, the fertilizer contains NH4+- ions, and more preferably, the fertilizer is selected from solid or liquid ammonium-containing inorganic fertilizers. The fertilizer may be provided in any suitable form, for example, as powder, crystals, solid-coated or uncoated prills or granules, in liquid or semi-liquid form, or as a sprayable fertilizer. Fertilizers can be applied by fertilization and application methods. Various materials can be provided for coated fertilizers. Coatings can be applied, for example, to large-grain or small-grain nitrogen (N) fertilizers, or to multi-nutrient fertilizers. Typically, urea is used as the base material for most coated fertilizers.Alternatively, ammonium, nitrates, or NPK, NP, and NK fertilizers are used as base materials for coated fertilizers. However, the disclosure also envisions the use of other base materials for coated fertilizers, any one of the fertilizer materials defined herein. In certain embodiments, elemental sulfur may be used as a fertilizer coating.

[0044] As used herein, the term “control data” should be understood broadly and represent any data configured to operate and control agricultural machinery and / or parts thereof. Control data may be provided by a control unit and may be configured to control one or more technical means of agricultural machinery, such as drive control, steering, product output, flight altitude, etc. Control data may include metadata for controlling at what location in the field and how much agricultural product to apply to the field. In this regard, control data may further be configured to control nozzles, pumps, valves and / or dispenser discs of fertilizer equipment. Such control may be performed in a so-called on / off manner, i.e., output control can be performed in a so-called on / off manner, where the output means is completely open or completely closed, for example, a valve that is completely open or completely closed. Alternatively, output control can also be performed as so-called variable control, in which case the output means can also take output values ​​between a completely open state and a completely closed state.

[0045] As used herein, the term “provide” should be understood broadly and includes, but is not limited to, providing, receiving, querying, measuring, calculating, identifying, and transmitting data. Data may be provided by a user through a user interface, drawn / displayed to a user by a display, and / or received by other devices, queryed by other devices, measured by other devices, calculated by other devices, identified by other devices, and / or transmitted by other devices.

[0046] As used herein, the term “data” should be understood broadly and encompass all types of data. Data may be, but not limited to, individual numbers / numerical values, multiple numbers / numerical values, multiple numbers / numerical values ​​included in a list, or two-dimensional or three-dimensional maps.

[0047] Particularly preferred embodiments are disclosed below, which may be combined with the methods, systems, apparatus, devices, and / or use cases disclosed above.

[0048] In one embodiment of a computer implementation method for providing nitrogen absorption data for field plants and / or plant parts, chlorophyll content data is provided as leaf chlorophyll content (LC) data and / or canopy chlorophyll content (CCHL) data.

[0049] In one embodiment of a computer implementation method for providing nitrogen absorption data for plants and / or plant parts in a field, leaf area index data and chlorophyll content data for the 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, the leaf area and chlorophyll content model is preferably adapted to different crop varieties, crop types, growth stages, soil conditions, and / or data sources.

[0050] In one embodiment of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, the leaf area index model and chlorophyll content model are machine learning models. The leaf area index data and chlorophyll content data for the field are obtained by utilizing the leaf area index and chlorophyll content models, and the machine learning models are preferably artificial neural networks (ANNs), multiple linear regression, random forest regression, or methods capable of establishing statistical relationships for predicting the leaf area index data and chlorophyll content data.

[0051] A machine learning model for leaf area index data could be an XGBBOOST regression model based on satellite image analysis. In linear regression, the model generally makes predictions based on the features input to the model, for example, by creating a weighted sum of features. In this case, the predictions depend on features that can be derived from satellite imagery. One or more regression models may be used to obtain leaf area index data and chlorophyll content data. Alternatively, there are machine learning models that can predict both leaf area index data and chlorophyll content data. It is also possible to choose to use separate models, which, as those skilled in the art will know, depends on the respective circumstances, for example, the model architecture.

[0052] In this disclosure, features that can be derived from satellite imagery and are suitable for regression modeling methods may include spectral bands and / or vegetation indices derived from satellite imagery. That is, the input to the regression model can be derived from pixel-based information from satellite imagery (i.e., remote sensing photographs). This derivation can be done using known methods and known vegetation indices, for example, MSR_Red&Red_Edge can be used. It is known that the leaf area index can be derived from such vegetation indices. Other indices are also possible. However, MSR_Red&Red_Edge is particularly preferred because it provides very accurate predictions compared to other usable indices such as NDVI.

[0053] In this regard, as an example, a combination of six features may be used, all of which can be derived from satellite imagery. Preferably, five spectral bands and one vegetation index are used as features for a machine learning model, and the features used may be RedEdge2 (spectral band), RedEdge3 (spectral band), Narrowband NIR (spectral band), SWIR1 (spectral band), SWIR2 (spectral band), MSR_Red and Red_Edge (combined vegetation index), and the spectral bands may be defined as follows:

[0054] [Table 1]

[0055] Furthermore, in this regard, refer to the paper "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).

[0056] A machine learning model for chlorophyll content data could be an XGBBOOST regression model based on satellite image analysis. In this regard, a combination of six features can be used, and it is preferable that two spectral bands and four vegetation indices are used as features of the machine learning model: Red Edge 1 (spectral band), SWIR 2 (spectral band), NDWI (vegetation index, normalized differential water index), GNDVI (vegetation index, green normalized vegetation index), REIP (vegetation index, Red Edge Inflection Point), and Chlr_Red_Edge (combined vegetation index). Also in this regard, further reference is made to the paper "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).

[0057] In one embodiment of a computer implementation method for providing nitrogen absorption data for plants and / or plant parts in a field, the nitrogen absorption model is further based on a identified crop-specific chlorophyll-leaf nitrogen conversion coefficient. There is a relationship between the amount of chlorophyll and nitrogen contained in plants and / or plant parts. The conversion coefficient allows the amount of chlorophyll to be converted into the amount of nitrogen. In this regard, such conversion coefficients may be identified by each field trial on a crop-by-crop, field-by-field, and / or climate zone-by-climate basis. The conversion coefficients may be identified for a particular climate region by, for example, a corresponding field trial, after which field-specific adjustments may be taken into account. Thus, crop-specific and field-specific chlorophyll-leaf nitrogen conversion coefficients may be provided for each field. For example, a conversion coefficient of 250 for wheat in the temperate climate zone of Europe was identified by each field trial. This conversion coefficient may or may not be further refined at the field level by each field trial.

[0058] As explained above, the method of this disclosure is Steps include identifying stem weight data based on the provided crop-specific leaf weight ratio, Steps include identifying stem nitrogen data based on stem weight data and provided crop-specific stem nitrogen concentration, Includes, The step of providing nitrogen uptake data for field plants and / or plant parts is further based on the identified stem nitrogen data.

[0059] Optionally, stem weight data can also be identified by plant-specific growth models. For example, plant data, meteorological data, and climate data can be used as input data for such growth models. For instance, such a plant-specific growth model is disclosed by Hunt et al. ("Effects of Nitrate Application on Amaranthus powellii WATS," Plant Physiology, Volume 79, Issue 3, November 1985, Pages 619-624), which is particularly relevant to the bioorganic segment and to Amaranthus powellii, a small-grained crop known in relation to cereals.

[0060] In one embodiment of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, the method is: The process further includes the step of providing a nitrogen absorption map of the field based on the provided nitrogen absorption data, the map preferably having a resolution of 1 to 50 m, 5 to 30 m, and more preferably 10 m. In one example, the nitrogen absorption map may provide a high-grain pixel-based map and / or a field zone-based map (e.g., as a fertilization map) that spatially aggregates information into multiple zones, reflecting the predicted amount of N absorption with different color intensities from low to high, and taking into account constraints related to fertilizer spreaders / machines in spatial resolution during fertilization.

[0061] The unit of absorption maps is N mass / unit area of ​​ground. Maps provide spatially decomposed / clear information (related to geographic information systems, GIS).

[0062] In one embodiment of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, the method is: A step of providing crop-specific nitrogen target values, The steps include providing nitrogen demand data based on nitrogen absorption data and nitrogen target values, It also includes.

[0063] In one embodiment of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, the method is: The process further includes providing a nitrogen demand map of the field based on the provided nitrogen demand data, the map preferably having a resolution of 1 to 50 m, 5 to 30 m, and more preferably 10 m.

[0064] In this specification, nitrogen demand data, particularly nitrogen demand, may be expressed as the difference between the target nitrogen uptake identified as described herein and the actual nitrogen uptake. Alternatively, nitrogen demand may be expressed as the actual nitrogen uptake divided by the optimal (i.e., target) nitrogen uptake. This is called the Nitrogen Nutrition Index (NNI) and is a well-known and established metric for nitrogen demand in agriculture.

[0065] In one embodiment of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, the method is: A step of providing control data for a fertilizer applicator to apply fertilizer products to a field in a variable manner based on nitrogen demand data. It also includes.

[0066] In one embodiment of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, the method is: A step of providing control data for an applicator to apply agricultural products to a field in a variable manner based on nitrogen demand data. Agricultural products further include crop protection products, biostimulant products, growth regulator products, and / or dehydration products.

[0067] The details of this disclosure will be described below with reference to the attached drawings. [Brief explanation of the drawing]

[0068] [Figure 1]Exemplary embodiments of centralized and decentralized computing environments having computing nodes are shown. [Figure 2] Exemplary embodiments of centralized and decentralized computing environments having computing nodes are shown. [Figure 3] This illustrates an exemplary embodiment of a distributed computing environment. [Figure 4] This diagram shows a flowchart of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field. [Figure 5] This describes a system that provides nitrogen absorption data for plants and / or plant parts in a field. [Figure 6] This is another diagram of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field. [Figure 7] An example nitrogen absorption map of a field is shown. [Figure 8] This illustrates another possible method for receiving and processing field data. [Figure 9] Examples of leaf weight ratios (LWR) in different locations and years, as well as their changes over time, are shown. [Modes for carrying out the invention]

[0069] The following embodiments are merely examples of how to implement the methods, systems, apparatus, or fertilizer applicators disclosed herein, and should not be considered limiting.

[0070] Figures 1-3 illustrate different centralized, decentralized, and distributed computing environments. The methods, apparatus, and computer elements of this disclosure may be implemented in a decentralized or at least partially decentralized computing environment. Various challenges exist, particularly in data sharing or exchange within ecosystems involving numerous stakeholders. Data sovereignty may be considered a central challenge. This can be defined as the ability of a natural or legal person to make all decisions regarding their own data. To enable this, certain capability-related aspects, including requirements for secure and reliable data exchange within business ecosystems, may be implemented across the chemical value chain. The chemical industry, in particular, needs solutions that are suited to the objective of delivering chemical products in a more sustainable manner by utilizing digital ecosystems. Data provision, identification, or processing may be achieved by different computing nodes that may be implemented in centralized, decentralized, or distributed computing environments.

[0071] Figure 1 shows an exemplary centralized computing system 20, which includes a central computing node 21 (the central filled circle) and five peripheral computing nodes 21.1–21.n (shown by the surrounding filled circles). The term “computing system” is broadly defined herein to include one or more computing nodes, a system of multiple nodes, or a combination thereof. The term “computing node” is broadly defined herein and may refer to any device or system including at least one physical tangible processor and / or physical tangible memory capable of holding computer executable instructions executed by the processor. Computing nodes are now taking on an increasingly diverse range of forms. Examples of computing nodes include portable devices, production equipment, sensors, monitoring systems, control systems, consumer electronics, laptop computers, desktop computers, mainframes, data centers, and other devices not traditionally considered computing nodes, such as wearables (e.g., glasses, watches, etc.). Memory may take any form, depending on the nature and form of the computing node.

[0072] In this example, peripheral computing nodes 21.1 to 21.n may be connected to a single central computing system (or server). In other examples, peripheral computing nodes 21.1 to 21.n may be attached to the central computing node via, for example, a terminal server (not shown). Most of the functions may be performed by or obtained from the central computing node (also called a remote centralized management location). A single peripheral computing node 21.n is enlarged to illustrate the complete set of elements present in a peripheral computing node. The centralized computing node 21 may contain the same elements as those described for peripheral computing node 21.n.

[0073] Each computing node 21, 21.1 to 21.n may include at least one hardware processor 22 and memory 24. The term “processor” can mean any logic circuit and / or, generally, a device configured to perform calculations or logical operations, configured to perform basic operations of a computer or system. In particular, a processor, or computer processor, may be configured to process basic instructions that drive a 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, a processor may include at least one arithmetic logic unit ("ALU"), at least one floating-point unit ("FPU") such as a numerical coprocessor or numerical coprocessor, a number of registers, registers configured to supply operands to the ALU and store the results of calculations, and memory such as L1 and L2 cache memories. In particular, a processor may be a multi-core processor. Specifically, a processor may be or include a central processing unit ("CPU"). The processor may be a graphics processing unit ("GPU"), a tensor processing unit ("TPU"), a composite instruction set computing microprocessor ("CISC"), a reduced instruction set computing ("RISC") microprocessor, a very long instruction word ("VLIW") microprocessor, or a processor implementing any other instruction set, or a processor implementing any combination of instruction sets. The processing means may also be one or more dedicated processing units, such as an application-specific integrated circuit ("ASIC"), a field-programmable gate array ("FPGA"), a composite programmable logic circuit ("CPLD"), a digital signal processor ("DSP"), or a network processor. The methods, systems, and devices described herein may be implemented as software within a DSP, microcontroller, or any other subprocessor, or as hardware circuits within an ASIC, CPLD, or FPGA.The term "processor" can also refer to one or more processing units, such as a distributed system of processing units deployed across multiple computer systems (e.g., cloud computing), and is not limited to a single device unless otherwise specified.

[0074] Memory 24 may refer to physical system memory, which may be volatile, non-volatile, or a combination thereof. Memory may include non-volatile mass storage such as physical storage media. Memory may be 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 disks, or any other physical tangible storage media that can be used to store desired program code means in the form of computer-executable instructions or data structures and is accessible by the computing system. Furthermore, memory may be a computer-readable medium (also called a transmission medium) that carries computer-executable instructions. Moreover, upon reaching various computing system components, program code means in the form of computer-executable instructions or data structures can be automatically transferred from the transmission medium to the storage medium (or vice versa). For example, computer-executable instructions or data structures received via a network or data link may be buffered in RAM within a network interface module (e.g., "NIC") and then finally transferred to the RAM of the computing system and / or to a less volatile storage medium in the computing system. Therefore, it should be understood that storage media may be included in computing components that also utilize (or primarily utilize) transmission media.

[0075] Computing nodes 21, 21.1 to 21.n may contain several components 26, often referred to as “executable components, executable instructions, computer executable instructions, or instructions.” For example, the memory 24 of computing nodes 21, 21.1 to 21.n may be exemplified to contain executable components 26. The term “executable component” or any equivalent thereof may be the name of a structure that is well understood by those skilled in the field of computing as a structure that can be software, hardware, or a combination thereof, or can be implemented in software, hardware, or a combination thereof. For example, if implemented in software, those skilled in the field will understand that the structure of an executable component includes software objects, routines, methods, etc., that run on computing nodes 21, 21.1 to 21.n, regardless of whether such executable components reside on the heap of computing nodes 21, 21.1 to 21.n or on computer-readable storage media. In such a case, a person skilled in the art will understand that the structure of the executable component, when placed on a computer-readable medium and interpreted by one or more processors of computing nodes 21, 21.1 to 21.n (e.g., by a processor thread), causes computing nodes 21, 21.1 to 21.n to perform a function. Such a structure may be directly computer-readable by the processor (as is the case if the executable component is a binary). Alternatively, the structure may be structured to produce an interpretable and / or compiled (whether in one or more stages) binary that is directly interpretable by the processor. Such an exemplary understanding of the structure of an executable component is well within the scope of the understanding of a person skilled in the art when using the term “executable component”.Examples of hardware-implemented executable components include hardcoded or hardwired logic gates that are exclusively or nearly exclusively implemented in hardware, such as in field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), or any other dedicated circuitry. In this description, terms such as “component,” “agent,” “manager,” “service,” “engine,” “module,” and “virtual machine” are used synonymously with the term “executable component.”

[0076] The processor 22 of each computing node 21, 21.1 to 21.n may instruct the operation of each computing node 21, 21.1 to 21.n in response to executing computer executable instructions that constitute an executable component. For example, such computer executable instructions may be implemented on one or more computer-readable media that form a computer program product. Computer executable instructions may be stored in the memory 24 of each computing node 21, 21.1 to 21.n. Computer executable instructions include instructions and data that, when executed by processor 21, cause a general-purpose computing node 21, 21.1 to 21.n, a dedicated computing node 21, 21.1 to 21.n, or a dedicated processing unit to perform a specific function or set of functions. Alternatively or additionally, computer executable instructions may configure the computing nodes 21, 21.1 to 21.n to perform a specific function or set of functions. Computer executable instructions may be binary or instructional text that undergoes some form of translation (such as compilation) before being directly executed by the processor, such as assembly language or even intermediate format instructions like source code.

[0077] Each computing node 21, 21.1 to 21.n may include a communication channel 28, such as a network (shown as a solid line between the peripheral computing nodes and the central computing node in Figure 1), which enables each computing node 21.1 to 21.n to communicate with the central computing node 21. "Network" may be defined as one or more data links that enable the transmission 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 to computing nodes 21, 21.1 to 21.n via the network or another communication connection (either wired, wireless, or a combination of wired and wireless), computing nodes 21, 21.1 to 21.n appropriately view this connection as a transmission medium. The transmission medium can be used to carry desired program code means in the form of computer executable instructions or data structures and may include networks and / or data links accessible by general-purpose or dedicated computing nodes 21, 21.1 to 21.n. The aforementioned combinations may also fall within the scope of computer-readable medium.

[0078] Computing nodes 21, 21.1 to 21.n may further include a user interface system 25 for use in the interface with the user. The user interface system 25 may include not only an input mechanism 25B but also an output mechanism 25A. The principles described herein are not strictly limited to the output mechanism 25A or the input mechanism 25B, as they depend on the nature of the device. However, the output mechanism 25A may include, for example, a display, a speaker, a tactile output, a hologram, etc. Examples of input mechanisms 25B may include, for example, a microphone, a touchscreen, a hologram, a camera, a keyboard, a mouse or other pointer input, a sensor of any kind, etc.

[0079] Figure 2 shows a decentralized computing environment 30 of an exemplary embodiment, having several computing nodes 21.1–21.n, indicated as filled circles. In contrast to the centralized computing environment 20 shown in Figure 1, the computing nodes 21.1–21.n in the decentralized computing environment are not connected to the central computing node 21 and are therefore not under the control of the central computing node. Instead, both hardware and software resources can be allocated to each of the individual computing nodes 21.1–21.n (local or remote computing systems), and data can be distributed across various computing nodes 21.1–21.n to perform tasks. Therefore, in a decentralized system environment, program modules can reside in both local and remote memory storage devices. One computing node 21 is enlarged to show an overview of the multiple components present in the computing node 21. In this example, the computing node 21 contains the same components as described with respect to Figure 1.

[0080] Figure 3 shows a distributed computing environment 40 of an exemplary embodiment. 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 that enables on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services). In the distributed case, the cloud computing environment can be distributed internationally within one organization and / or across multiple organizations. In this example, the distributed cloud computing environment 40 may include the following computing resources: mobile devices 42, applications 43, databases 44, data storage, and servers 46. The cloud computing environment 40 can be deployed as a public cloud 47, a private cloud 48, or a hybrid cloud 49. The private cloud 47 may be owned by an organization, and only members of that organization with appropriate access rights can use the private cloud 48 and keep the data within the private cloud at least confidential. In contrast, data stored in the public cloud 48 may be made available to anyone via the internet. A hybrid cloud 49 may be a combination of both private and public clouds 47 and 48, where some data can be kept confidential while other data can be made public.

[0081] Figure 4 shows a flowchart of a computer implementation method for providing nitrogen absorption data for plants and / or plant parts in a field. In the first step 100, field leaf area index (LAI) data is provided. In another step 110, field chlorophyll content data is provided. In yet another step 120, a nitrogen absorption model is provided that is configured to provide nitrogen absorption data for plants and / or plant parts based on the leaf area index data and chlorophyll content data. In yet another step 130, nitrogen absorption data for plants and / or plant parts in the field is provided using the nitrogen absorption model based on the provided leaf area index data and chlorophyll content data. Figure 5 shows a system 10 for providing nitrogen absorption data of plants and / or plant parts in a field, which includes a providing unit 11 configured to provide field leaf area index data, another providing unit 12 configured to provide field chlorophyll content data, another providing unit 13 configured to provide a nitrogen absorption model configured to provide nitrogen uptake data of plants and / or plant parts based on the leaf area index data and chlorophyll content data, and another providing unit 14 configured to use the nitrogen absorption model to provide nitrogen absorption data of plants and / or plant parts in the field based on the provided leaf area index data and chlorophyll content data.

[0082] Figure 6 is another diagram of a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field. In the first step, satellite data / images 50 of the field may be provided. These satellite data are provided to a leaf area and chlorophyll content model 51, which may be provided by at least one machine learning model. The machine learning model for leaf area index data 52 may be an XGBBOOST regression model based on satellite image analysis. From this viewpoint, a combination of six features may be used, preferably with five spectral bands and one vegetation index used as features for the machine learning model, and Red Edge 2 (spectral band), Red Edge 3 (spectral band), Narrowband NIR (spectral band), SWIR 1 (spectral band), 2 (spectral band), MSR_Red and Red_Edge (combined vegetation index) may be used as features. The machine learning model for chlorophyll content data 53 may also be an XGBBOOST regression model based on satellite image analysis. In this regard, a combination of six features may be used, and it is preferable that two spectral bands and four vegetation indices be used as features for the machine learning model: Red Edge 1 (spectral band), SWIR 2 (spectral band), NDWI (vegetation index, normalized differential water index), GNDVI (vegetation index, green normalized differential vegetation index), REIP (vegetation index, Red Edge Inflection Point), and Chlr_Red_Edge (combination). In this regard, further reference is made to the paper "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). Field leaf area index data and chlorophyll content data are obtained using the leaf area and chlorophyll content model 51.

[0083] In the illustrated example, the ground is 1 meter high.2 Per leaf area: 1.6m 2 The leaf area index, and leaf 1cm 2 The chlorophyll concentration in leaves at 50 μg of Chl was determined based on satellite data / images. Using both values, the leaf nitrogen uptake of 54 can be determined / calculated. In the example shown in the figure, a leaf nitrogen uptake of 52 kg of nitrogen per hectare can be derived.

[0084] As described above, according to this disclosure, stem nitrogen data used to determine nitrogen uptake, such as stem nitrogen content, is determined based on leaf weight ratios, specifically stem weight data derived from leaf weight ratios.

[0085] As an example, the nitrogen content in the stem can be estimated as follows: In the first step, the stem weight can be estimated based on the provided crop-specific leaf weight ratio, i.e., the leaf area index can be converted to stem weight based on empirical and / or experimental values. Then, the stem weight can be converted to crop-specific stem nitrogen content, taking into account the crop-specific stem nitrogen concentration, which itself can be derived by empirical and / or experimental values.

[0086] Alternatively or additionally, as shown in Figure 6, stem weight data can also be determined by a plant-specific growth model 55. For example, meteorological data 56 and soil data 57 may be used as input data for such a growth model. From the stem weight data obtained by model 55, stem nitrogen uptake can be determined as described above. In the example shown, a stem nitrogen uptake of 26 kg per hectare can be derived. As a result, in the example shown, a crop nitrogen uptake of 78 kg per hectare ("crop N" 58) can be derived, which is the sum of leaf nitrogen uptake and stem nitrogen uptake outlined above.

[0087] Here, we will refer to Figure 9, which will be explained in detail later, and this figure shows that the leaf weight ratio can be time-dependent and location-dependent. Therefore, the leaf weight at the time the satellite image was taken can be determined for the crop shown in the satellite image based on a lookup or based on the growth model described above. To this end, the time the satellite image was taken can be retrieved, for example, from the image's timestamp or storage.

[0088] Therefore, the overall modeling would be understood to involve identifying together LAR 52 and chlorophyll content data 53, which are identified by, for example, model 51 and derived from satellite imagery that provides input data for model 51, and stem weight data which can itself be derived from (growth) model 55 or look up from (time-dependent) LWR values. Thus, within the overall nitrogen uptake modeling, models may optionally be used for different substeps. Instead of one model 51, multiple models may be used to determine each of the LAR and chlorophyll content data.

[0089] Figure 7 shows an exemplary nitrogen uptake map of a field, and the nitrogen uptake of the crop is derived as described above. For example, such a plant-specific growth model is disclosed by Hunt et al. ("Effects of Nitrate Application on Amaranthus powellii WATS", Plant Physiology, Volume 79, Issue 3, November 1985, Pages 619-624), which concerns Amaranthus powellii, a small-grained cereal crop known particularly for its bioorganic segment and cereals.

[0090] Figure 8 illustrates several possibilities for receiving and processing field data (e.g., image data, control data, etc.). For example, field data can be obtained as a so-called fertilization map by recording the application rate at the time of fertilization using any kind of agricultural equipment 300 (e.g., a tractor 300). Such agricultural equipment may also include sensors (e.g., light sensors, cameras, infrared sensors, soil sensors, etc.) to provide, for example, a weed distribution map. It is also possible for harvesters 310 to record yield (e.g., in the form of biomass) during harvesting. Furthermore, the corresponding map / data can be provided by a land and / or aerial drone 320 by taking images of the field or a part thereof. Finally, it is also possible to perform georeferencing visual assessment 330 and process this field data as well. The field data thus collected can then be fused within the computing device 340, and the data can be transmitted and computed, for example, via any wireless link, cloud application 350, and / or work platform 360. The field data may also be processed entirely or partially within the cloud application 350 and / or work platform 360 (e.g., by cloud computing).

[0091] Figure 9 shows an example of the leaf weight ratio (LWR) at different locations and in different years, as well as its change over time, here as a function of time, e.g., year, month, and day (DOC). More specifically, Figure 9 shows the annual and spatial effects on the seasonal dynamics of LWR at two specific geographic locations of a field (indicated as Loc_1 and Loc_2) for two years (2021 and 2022, for illustrative purposes only). The x-axis is in relation to time, in this example, day, e.g., year, month, and day (DOY), and the y-axis is related to LWR.

[0092] To further emphasize and explain the role of LWR, the method of this disclosure is described again below.

[0093] As stated above, this disclosure provides a computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, the method comprising the steps of providing leaf area index data of the field, The method includes the steps of: providing field chlorophyll content data; providing a nitrogen absorption model configured to provide nitrogen absorption data for plants and / or plant parts based on leaf area index data and chlorophyll content data; and using the nitrogen absorption model to provide nitrogen absorption data for plants and / or plant parts in the field based on the provided leaf area index data and chlorophyll content data. The method further includes the steps of: identifying stem weight data based on the provided crop-specific leaf weight ratio; and identifying stem nitrogen data based on the stem weight data and the provided crop-specific stem nitrogen concentration. According to this disclosure, providing nitrogen absorption data for plants and / or plant parts in the field is further based on the identified stem nitrogen data.

[0094] By using leaf weight ratios to determine nitrogen absorption, it becomes possible to determine nitrogen absorption with greater accuracy.

[0095] The Leaf Weight Ratio (LWR) can be obtained using a (crop) model configured to provide location-specific crop organ allocation coefficients such as LWR. The LWR provided by the model is influenced by geographical location, weather conditions, the model's internal logic, and agricultural practices such as sowing date and variety.

[0096] From the above, it will be understood that, as an intermediate step, this disclosure may provide a model for nitrogen absorption that provides the dry mass of one or more crop organs at a certain point in time, for example, at the time when satellite imagery was taken (e.g., at least one of root mass data, stem weight data, leaf mass data, seed mass data, and fruit mass data) based on dynamic biomass allocation coefficients (e.g., LWR and / or root-to-bud and / or stem-to-bud), particularly on a daily basis throughout the season. The dry mass, particularly the LWR value at that point in time, may be further used to predict nitrogen absorption.

[0097] More specifically, models such as crop growth models can provide LWR and also determine the optimal amount of nitrogen absorption (ground level 1m). 2 It is possible to provide the amount of N(g) per square meter. Using data derived from remote sensing such as satellite imagery and data derived from crop growth models, the actual amount of N absorbed (N(g) per square meter of ground) can be obtained by a nitrogen absorption model.

[0098] For example, when determining nitrogen absorption using a nitrogen absorption model for a given point in time, such as a particular day, satellite images taken at that point in time may be retrieved. The time the satellite images were acquired can be identified or retrieved, for example, from a timestamp or a database. Using this time and the time dependence of the LWR value, the LWR value at that time can be determined. For example, satellite images may be taken on a particular day, and the LWR value for that day can be determined based on the time dependence. An example of such a time dependence is shown in Figure 9.

[0099] This disclosure may provide a (nitrogen absorption) model, which is a process-based model and may take as input data at least one of crop type, variety, sowing / planting date, and location-specific soil and weather data, in particular for use by a crop growth model that predicts LWR.

[0100] Aspects of this disclosure relate to computer program elements configured to perform the steps of the method described above. The computer program elements may therefore be stored on a computing unit of a computing device, which may also be part of a particular embodiment. This computing unit may be configured to perform or induce the performance of the steps of the method described above. Furthermore, it may be configured to operate the components of the aforementioned system. The computing unit may be configured to operate automatically and / or to execute user instructions. The computing unit may include a data processor. The computer program may be loaded into the working memory of the data processor. The data processor may therefore be equipped to perform the method according to one of the prior embodiments. This exemplary embodiment of the disclosure encompasses both computer programs that use the disclosure from the outset and computer programs that, through updates, convert existing programs to use the disclosure. Furthermore, the computer program elements may be capable of providing all the steps necessary to perform the steps of the exemplary embodiment of the method described above. According to yet another exemplary embodiment of the disclosure, a computer-readable medium such as a CD-ROM or USB stick, a downloadable executable file, etc., is presented, on which a computer program element is stored, as described in the preceding section. Computer programs may be stored and / or distributed on suitable media such as optical storage media or solid-state media supplied together with or as part of other hardware, or they may be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. However, computer programs may also be provided via networks such as the World Wide Web and can be downloaded from such networks into the working memory of a data processor. According to yet another exemplary embodiment of the present disclosure, a medium is provided that makes a computer program element downloadable, and this computer program element is configured to perform the method according to one of the aforementioned embodiments of the present disclosure.

[0101] This disclosure has described preferred embodiments as examples. However, those skilled in the art and practitioners of the claimed invention can understand and implement other variations by examining the drawings, this disclosure, and the claims. In particular, any of the presented steps may be performed in any order, i.e., the present invention is not limited to any particular order of these steps. Furthermore, these different steps do not need to be performed at a specific location or one node in a distributed system, i.e., each step may be performed at a different node using different equipment / data processing units.

[0102] In both the specification and the claims, the term "including" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude plurals. One element or other unit may perform the function of several entities or items specified in the patent claims. The mere fact that certain means are specified in different dependent claims does not mean that combinations of these means cannot be used in advantageous implementations.

Claims

1. A computer implementation method for providing nitrogen absorption data of plants and / or plant parts in a field, The steps include providing leaf area index data for the field (100), The steps include providing chlorophyll content data for the field (110), Step (120) of providing a nitrogen absorption model configured to provide nitrogen absorption data of plants and / or plant parts, wherein the input data of the nitrogen absorption model is the provided leaf area index data and the chlorophyll content data, Using the nitrogen absorption model, the step (130) provides nitrogen absorption data for the plants and / or plant parts in the field based on the provided leaf area index data and chlorophyll content data, Includes, The method described above is Steps include identifying stem weight data based on the provided crop-specific leaf weight ratio, A step of identifying stem nitrogen data based on the aforementioned stem weight data and the provided crop-specific stem nitrogen concentration, Includes, The step of providing nitrogen absorption data of plants and / or plant parts in the field is a computer implementation method further based on the identified stem nitrogen data.

2. The computer implementation method according to claim 1, wherein the crop-specific leaf weight ratio is used as input to the nitrogen absorption model or is identified by a growth model as part of the nitrogen absorption model.

3. The computer implementation method according to claim 1 or 2, wherein the chlorophyll content data is provided as leaf chlorophyll content (LC) data and / or canopy chlorophyll content (CCHL) data.

4. The computer implementation method according to any one of claims 1 to 3, wherein the leaf area index data and chlorophyll content data of the field are obtained by using a leaf area and chlorophyll content model (51) configured to provide leaf area index data and chlorophyll content data based on the surface reflectance band of at least one satellite image, the leaf area and chlorophyll content model is preferably adjusted to suit different crop varieties, crop types, growth stages, soil conditions, and / or data sources.

5. The computer implementation method according to claim 4, wherein the leaf area and chlorophyll content model is a machine learning model, the leaf area index data and chlorophyll content data for the field are obtained by utilizing the leaf area and chlorophyll content model, and the machine learning model is preferably an artificial neural network (ANN), multiple linear regression, random forest regression, or a method capable of establishing a statistical relationship for predicting the leaf area index data and chlorophyll content data.

6. The computer implementation method according to any one of claims 1 to 5, wherein the nitrogen absorption model is further based on a specified crop-specific chlorophyll-leaf nitrogen conversion coefficient.

7. The computer implementation method according to any one of claims 1 to 6, further comprising the step of providing a nitrogen absorption map of the field based on the nitrogen absorption data provided, wherein the map preferably has a resolution of 1 to 50 m, preferably 5 to 30 m, and more preferably 10 m.

8. A step of providing crop-specific nitrogen target values, The steps include providing nitrogen demand data based on the nitrogen absorption data and the nitrogen target value, A computer implementation method according to any one of claims 1 to 7, further comprising the above.

9. The computer implementation method according to claim 8, further comprising the step of providing a nitrogen demand map of the field based on the nitrogen demand data provided, wherein the map preferably has a resolution of 1 to 50 m, preferably 5 to 30 m, and more preferably 10 m.

10. The step of providing control data for a fertilizer applicator to apply fertilizer products to the field in a variable manner based on the nitrogen demand data. The computer implementation method according to claim 8 or 9, further comprising:

11. The further step includes providing control data for an applicator for variable application of agricultural products to the field based on the nitrogen demand data, wherein the agricultural products are Crop protection products, biostimulant products, growth regulator products and / or dehydration products A computer implementation method according to any one of claims 8 to 10, which is at least one of the above.

12. An apparatus for providing nitrogen absorption data of plants and / or plant parts in a field, wherein the apparatus comprises one or more computing nodes and one or more computer-readable media, and when executed by the one or more computing nodes, the apparatus performs the following steps, namely: The steps include providing leaf area index data for the aforementioned field, The steps include providing chlorophyll content data for the aforementioned field, The steps include providing a nitrogen absorption model configured to provide nitrogen absorption data for plants and / or plant parts based on the leaf area index data and chlorophyll content data, Steps include identifying stem weight data based on the provided crop-specific leaf weight ratio, The steps include identifying the stem nitrogen data based on the stem weight data and the provided crop-specific stem nitrogen concentration, Using the nitrogen absorption model, the step of providing nitrogen absorption data for the plants and / or plant parts of the field based on the provided leaf area index data and chlorophyll content data, Make it run, The step of providing nitrogen absorption data for plants and / or plant parts in the field is further based on the identified stem nitrogen data. A device comprising one or more computer-readable media having computer-executable instructions configured in such a way.

13. A fertilizer applicator for applying a fertilizer product to a field, wherein control data for the fertilizer applicator is provided at least in part as described in claim 10 or claim 11.

14. A computer program element having instructions configured to execute, when executed on a computing device of a computing environment, the steps of the computer implementation method described in any one of claims 1 to 11, and / or in the apparatus described in claim 12.

15. The use of leaf area index data, chlorophyll content data, nitrogen absorption model, and / or satellite images in the computer implementation method according to any one of claims 1 to 11, and / or in the apparatus according to claim 12.

Images