Computer-implemented method for estimating agricultural product consumption in a geographic region - Patents.com

Abstract

1. A computer-implemented method (100) for estimating consumption of an agricultural product in an area of ​​a geographical region cultivated with a particular crop, the method comprising the steps of: providing crop growth index data for the geographical region (110); determining an area of ​​the geographical region cultivated with the particular crop based at least on a comparison of the provided crop growth index data to plant-specific reference data (120); providing a product consumption model for the agricultural product configured to estimate consumption of the agricultural product based at least on the area of ​​the geographical region cultivated with the particular crop (130); and using the product consumption model to provide an estimate of consumption of the agricultural product for the determined area of ​​the geographical region cultivated with the particular crop in the geographical region based at least on the determined area cultivated with the particular crop (140).

Description

[Technical field]

[0001] The present disclosure relates to a computer-implemented method for estimating consumption of agricultural products in areas of a geographic region cultivated with a particular crop, a computer-implemented method for providing training data for a machine learning algorithm for estimating consumption of agricultural products in areas of a geographic region cultivated with a particular crop, a neural network / machine learning model for estimating consumption of agricultural products in areas of a geographic region cultivated with a particular crop, an apparatus for estimating consumption of agricultural products in areas of a geographic region cultivated with a particular crop, and corresponding computer program elements. [Background technology]

[0002] In agriculture, many agricultural products (e.g. seeds, pesticides, fertilizers, etc.) need to be applied or spread on the fields by the farmers at certain times or time frames, and for this reason it is crucial that the agricultural products required at these determined times can be delivered to the farmers. However, the production and transportation of many of these agricultural products requires a certain lead time before they can be delivered to the farmers. For this reason, in the production, purchase, storage, and other logistics sub-areas of agriculture, manufacturers, suppliers, and subcontractors must estimate the required quantity of agricultural products that are needed for agriculture in a certain period of time in order to be able to ensure that they can provide the corresponding quantity of the agricultural products required. Until now, the required quantity of agricultural products has often been estimated based on the long experience of the manufacturers. However, in practice, this also leads to discrepancies between the estimated quantity and the actual required quantity, which is a considerable disadvantage in the case of overproduction of agricultural products that cannot be easily stored and / or that can only be stored at high cost. In addition, if the estimates are too low, supply bottlenecks may occur.

[0003] It has therefore been found that a further need exists to provide a means for estimating consumption of agricultural products in geographical regions. Summary of the Invention [Problem to be solved by the invention]

[0004] It is therefore an object of the present invention to provide a means (e.g. a method, a system, etc.) for estimating the consumption of agricultural products in a geographical area. These objects, as well as others that will become apparent on reading the following description, are solved by the subject matter of the independent claims. The dependent claims refer to preferred embodiments of the invention. [Means for solving the problem]

[0005] A first aspect of the present disclosure is a computer-implemented method for estimating consumption of agricultural products in an area of ​​a geographic region cultivated with a particular crop, the method comprising: providing crop growth index data for a geographic region; determining an area of ​​the geographic region cultivated with a particular crop based at least on a comparison of the provided crop growth index data to plant-specific reference data; providing a product consumption model for an agricultural product configured to estimate consumption of the agricultural product based at least on an area of ​​a geographic region cultivated with a particular crop; providing an estimate of consumption of agricultural products for the determined area of ​​the geographic region cultivated with the particular crop in the geographic region based at least on the determined area cultivated with the particular crop using the product consumption model; The present invention relates to a computer-implemented method, including:

[0006] A further aspect of the present disclosure is a computer-implemented method for providing training data for a machine learning algorithm that estimates consumption of an agricultural product in an area of ​​a geographic region cultivated with a particular crop, the method comprising: Providing data including information regarding areas cultivated with a particular crop; providing agricultural product consumption data relating to a provided area cultivated with a particular crop; labelling the data containing information about areas cultivated with a particular crop with consumption data of agricultural products relating to the provided area cultivated with the particular crop; The present invention relates to a computer-implemented method, including:

[0007] A further aspect of the present disclosure relates to a neural network / machine learning model for estimating consumption of agricultural products in areas of a geographic region cultivated with a particular crop, trained with training data according to the above-described computer-implemented method of providing training data for a machine learning algorithm for estimating consumption of agricultural products in areas of a geographic region cultivated with a particular crop.

[0008] A further aspect of the present disclosure is an apparatus for estimating consumption of agricultural products in an area of ​​a geographic region cultivated with a particular crop, the apparatus comprising: one or more computing nodes; and, when executed by the one or more computing nodes, an apparatus providing crop growth index data for a geographic region; determining an area of ​​the geographic region cultivated with a particular crop based at least on a comparison of the provided crop growth index data to plant-specific reference data; providing a product consumption model for an agricultural product configured to estimate consumption of the agricultural product based at least on an area of ​​a geographic region cultivated with a particular crop; providing an estimate of consumption of agricultural products for the determined area of ​​the geographic region cultivated with the particular crop based at least on the determined area cultivated with the particular crop using the product consumption model; one or more computer-readable media having computer-executable instructions configured to cause The present invention relates to an apparatus comprising:

[0009] A further aspect of the present disclosure is a system for estimating consumption of agricultural products in an area of ​​a geographic region cultivated with a particular crop, the system comprising: a providing unit configured to provide crop growth index data relating to a geographical region; a determining unit configured to determine an area of ​​the geographical region cultivated with a particular crop based at least on a comparison of the provided crop growth index data with plant-specific reference data; a providing unit configured to provide a product consumption model for agricultural products, the providing unit configured to estimate consumption of the agricultural products based at least on an area of ​​a geographical region cultivated with a particular crop; a providing unit configured to provide an estimate of consumption of an agricultural product for a determined area of ​​a geographic region cultivated with a particular crop based at least on the determined area cultivated with the particular crop using a product consumption model; The present invention relates to a system comprising:

[0010] In a further aspect of the present disclosure, a computer program element is disclosed that includes instructions configured to execute, when executed on a computing node / device of a computing environment, steps of a method for estimating consumption of agricultural products in areas of a geographic region cultivated with a particular crop. In a further aspect of the present disclosure, a computer readable medium having stored thereon such a computer program element is provided.

[0011] Any disclosures and embodiments described herein relate to the methods, systems, devices, computer program elements outlined above, and vice versa. Advantageously, benefits provided by any of the embodiments and examples apply to all other embodiments and examples as well, and vice versa.

[0012] As used herein, "determining" also includes "initiating or causing a determination," "generating" also includes "initiating or causing a generation," and "providing" also includes "initiating or causing a determination, generation, selection, transmission, or reception." "Initiating or causing the performance of an action" includes any processing signal that triggers a computing device to perform the respective action.

[0013] The present disclosure is based, inter alia, on the discovery that crop growth indices allow determining which areas of a geographical region are cultivated with which crops. Based on information about the area, i.e., the size of the area, it is possible to estimate the consumption of agricultural products in the geographical region. As a result, manufacturing processes, logistics processes, and warehouse activities can be planned and executed in a safer and more predictable manner, with the costs associated with planning and resulting forecast errors being significantly reduced. Furthermore, the present disclosure allows for a significant reduction in agricultural products that have to be disposed of, since agricultural products can also be used up to their expiration date.

[0014] definition The term agricultural product is to be understood broadly in this disclosure and includes any object or material that is useful / necessary for the treatment of a field. In the context of this disclosure, the term agricultural product is used without limitation: - chemical products, such as fungicides, herbicides, insecticides, acaricides, molluscicides, nematicides, birdicides, pisciicides, rodenticides, repellents, bactericides, biocides, safeners, plant growth regulators, urease inhibitors, nitrification inhibitors, denitrification inhibitors, or any combination thereof; - microorganisms useful as biological products, such as fungicides (bio-fungicides), herbicides (bio-herbicides), insecticides (bio-insecticides), acaricides (bio-acaricides), molluscicides (bio-molluscicides), nematicides (bio-nematicides), birdicides, piscicides, rodenticides, repellents, bactericides, biocides, safeners, plant growth regulators, urease inhibitors, nitrification inhibitors, denitrification inhibitors, or any combination thereof; - fertilizers and nutrients, - seeds and seedlings, - water, - Agricultural equipment / devices (e.g. sprayers, harvesters, machinery) and spare parts for such equipment / devices; and / or - Any combination of these Includes.

[0015] The term "geographical region" should be understood in the present disclosure in a broad sense and ranges from a farmer's field to an entire country (e.g., Germany). Preferably, the term geographical region can be understood to mean, for example, a state / district, a region (such as Southern Bavaria), etc. The geographical region can be selected such that product consumption can be estimated with respect to the producer's delivery area. Particularly preferably, the term geographical region is understood to mean an area of ​​more than 400 square kilometers.

[0016] "Area of ​​a geographical region cultivated with a specific crop" means the area of ​​the geographical region where the specific crop is planted. In other words, "area of ​​a geographical region cultivated with a specific crop" is the area obtained as a result of adding up each sub-area where the specific crop is cultivated in the geographical region. For example, if wheat is cultivated in 100 individual fields of 2 hectares each, and the individual fields can be randomly distributed in the geographical region, then "area of ​​a geographical region cultivated with a specific crop" is 200 hectares. Based on this area, the consumption of agricultural products required for the treatment of the determined area can be estimated. In one example, "area" can be expressed in hectares, square meters, square kilometers, etc.

[0017] The term "crop growth index data" should be understood in a broad sense and includes any crop growth index data that allows at least determining the type of crop grown in a geographical region by comparison with reference data. In one example, the crop growth index data is Normalized Difference Vegetation Index (NDVI) data and the reference data is crop-specific NDVI data. The reference data, e.g. NDVI data, can be used not only to determine a particular crop by comparing the data, but also to determine or compare, for example, whether a particular crop is healthy, damaged or diseased. The latter can be particularly well compared, identified and quantified using NDVI data, since the leaves of the crop reflect light differently depending on their state.

[0018] The term "plant-specific reference data" refers to any data from which a conclusion can be made regarding a particular crop by comparison of the provided crop growth index data to the reference data. In one example, the "plant-specific reference data" may be used to train a machine learning algorithm, and the machine learning algorithm may identify a particular crop grown in a geographic region.

[0019] The term "biomass data" of a particular crop should be understood broadly in this disclosure and refers to any data / indicator / number / parameter that directly or indirectly indicates the biomass of a particular crop at a certain time t1 in a geographical region. However, different sources from different times may be used to determine the biomass data for a geographical region at time t1, as long as they can be calculated / aligned to time t1. Biomass data may be derived from remote sensing measurements (e.g., satellite images or multispectral information) and analysis of the spectral reflectance of the observed geographical area / region. An example of how such biomass data can be derived / calculated for a particular crop (e.g., corn or soybeans) is described in the paper "Vegetation water content estimation for corn and soybeans using spectral indices derived from MODIS near- and short-wave infrared bands" (Daoyi Chen et al., Remote Sensing of Environment, Volume 98, Issues 2-3, October 15, 2005, Pages 225-236).

[0020] The term "specific crop" includes all agronomically usable plants, trees, shrubs, etc., such as, for example, wheat, fruit trees, or fruit shrubs, etc. Furthermore, the term specific crop can also be understood as all crops / plants that require treatment with a specific agricultural product (e.g., all crops that require treatment with a soil herbicide).

[0021] The term "crop growth model" should be understood broadly in this disclosure and refers to any computer-operable model, method, mathematical algorithm that can be used to calculate / estimate biomass data at time t2 based on biomass data of a particular crop at time t1. An example of such a crop growth model is described in the paper "Use time series NDVI and EVI to develop dynamic crop growth metrics for yield modeling" (Sadia Alam Shammi, et al., Ecological Indicators, Volume 121, February 2021).

[0022] The term "product consumption model" should be understood broadly in this disclosure and refers to any computer-operable model, method, mathematical algorithm that can be used to calculate / estimate the consumption of an agricultural product at a certain time or period. Such product consumption can be based at least on a determined area of ​​a geographical region cultivated with a particular crop. However, it is not excluded that further parameters are used in the product consumption model. Also, shelf life data of agricultural products, expected planting decisions of farmers, pest pressure data, regulatory data of agricultural products, etc. can be considered here to improve the accuracy of the product consumption estimate. The relationship between the determined area during the season and the demand for agricultural products can be derived from previously observed demand patterns and practical experience (e.g. as described in the "Pflanzenschutzberater-Kloster Muehle", where the usual use of various agricultural products in various plant conditions is described). However, numerous other sources / recommendations are known in this context that can be used here. In addition, specialized or trained consumption models for this purpose can be used for each agricultural product. For example, a consumption model of herbicides, a consumption model of fertilizers, a consumption model of pesticides, etc. can be used. However, these consumption models can also be combined into a single consumption model. In one example, a consumption model may be provided with a standard recommended application rate, for example for Cantus Gold (a fungicide for the treatment of maturity diseases in rapeseed), where a standard application rate of 0.5 l / ha is recommended.

[0023] The term machine learning algorithm should be understood in a broad sense and preferably includes decision trees, naive Bayes classification, nearest neighbors, neural networks, convolutional neural networks, generative adversarial networks, support vector machines, linear regression, logistic regression, random forests, and / or gradient boosting algorithms. Preferably, the machine learning algorithm is configured to process inputs with high dimensions into outputs with much lower dimensions. Such machine learning algorithms are called "intelligent" because they can be "trained". The algorithm may be trained using records of training data. A record of training data includes training input data and corresponding training output data. The training output data of a record of training data is the result expected to be generated by the machine learning algorithm when the training input data of the same record of training data are given as input. The deviation between this expected result and the actual result generated 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, the parameters can be adjusted with an optimization objective of minimizing the value of the loss function, obtained when all training input data are put into the machine learning algorithm and the result is compared with the corresponding training output data. As a result of this training, even if a relatively small number of records of training data are given as "ground truth", the machine learning algorithm is able to perform its task well on a number of records of input data that are orders of magnitude larger.

[0024] In one embodiment of the computer-implemented method for estimating consumption of agricultural products, the agricultural products are fungicides, herbicides, insecticides, acaricides, molluscicides, nematicides, birdicides, pisciicides, rodenticides, repellents, bactericides, biocides, safeners, plant growth regulators, urease inhibitors, nitrification inhibitors, denitrification inhibitors, fertilizers, nutrients, seeds / seedlings, and / or combinations thereof. In one embodiment, the specific crops are wheat, winter rapeseed, winter rye, sugar beet, winter wheat, etc.

[0025] In one embodiment of the computer-implemented method for estimating consumption of agricultural products, the crop growth index data is Normalized Difference Vegetation Index (NDVI) data, Leaf Area Index (LAI) data, Normalized Difference Water Index (NDWI) data, Extended Vegetation Index (EVI) data.

[0026] In one embodiment of the computer-implemented method for estimating consumption of agricultural products, the acreage in a geographic region is determined for a preselected set of specific crops based on crop growth index data for the geographic region. In one example, the preselected set of specific crops is a combination of winter rapeseed, winter rye, sugar beet, and winter wheat determined in parallel.

[0027] In one embodiment of the computer-implemented method for estimating consumption of agricultural products, crop growth index data is provided at an early crop stage for a particular crop (e.g., 21 days after sowing). The determination of areas that are already at an early planting stage correspondingly already enables consumption estimation at such an early stage of the season.

[0028] In one embodiment of the computer-implemented method of estimating consumption of agricultural products, crop growth index data, preferably Normalized Difference Vegetation Index (NDVI) data, is provided for a period between a start time t1, which is the current time or a time between 15 and 30 days after sowing of the specific crop, preferably between 17 and 25 days after sowing of the specific crop, and most preferably between 21 days after sowing of the specific crop, and an end time t2, which is between 2 and 10 weeks after t1, preferably between 4 and 8 weeks after t1, and most preferably 6 weeks after t1. By considering a period of time rather than just a point in time, the accuracy of determining which areas are planted with which specific crops can be significantly improved. Furthermore, the present disclosure can provide continuous monitoring of geographical areas, so that the respective subsequent processes (e.g., the manufacturing process of agricultural products) can also be continuously adjusted and optimized.

[0029] In one embodiment of the computer-implemented method for estimating consumption of agricultural products, crop growth index data is provided for a pre-determined time series.

[0030] In one embodiment of the computer-implemented method for estimating consumption of agricultural products, the plant-specific reference data is provided by a centralized and / or distributed computing environment.

[0031] In one embodiment of the computer-implemented method for estimating consumption of agricultural products, the step of determining the area cultivated with a particular crop is based on data obtained by using synthetic aperture radar (SAR), light detection and ranging (LIDAR) via satellites, unmanned vehicles, vehicle-mounted sensors, and / or combinations thereof.

[0032] In one embodiment of the computer-implemented method for estimating consumption of agricultural products, a product consumption model for an area cultivated with a particular crop is based on results of a machine learning algorithm configured to estimate consumption of agricultural products based at least on an area of ​​the geographic region cultivated with the particular crop.

[0033] In one embodiment of a computer-implemented method for estimating consumption of an agricultural product, the method comprises: providing inventory recommendation data regarding minimum stock levels of agricultural products at a particular time and / or for a period of time based on the estimate of consumption of the agricultural products; and / or providing inventory recommendation data regarding minimum inventory levels of basic materials required for the production of the agricultural product at a particular time and / or for a period of time based on the estimated consumption of the agricultural product; and / or providing production recommendation data for producing an agricultural product based on the estimated consumption of the agricultural product; and / or providing ordering recommendation data for ordering quantities of agricultural products and / or quantities of basic inputs required for the production of the agricultural products based on the estimate of consumption of the agricultural products; and / or providing summary data regarding agricultural products required and / or recommended for specific crops; and / or providing control data for manufacturing, logistics, and / or warehousing processes with respect to the agricultural products based on the estimate of the consumption of the agricultural products; The present invention further includes at least one of the following:

[0034] Hereinafter, the present disclosure will be further described in conjunction with the accompanying drawings. [Brief description of the drawings]

[0035] [Figure 1] FIG. 1 is a flow diagram of an exemplary method for estimating consumption of agricultural products in a geographic region. [Diagram 2] FIG. 1 is a schematic diagram of an exemplary system for estimating consumption of agricultural products in a geographic region. [Diagram 3] FIG. 1 is a schematic diagram of NDVI data in a geographic region over a period of time. [Figure 4] FIG. 1 is a schematic diagram of geographical regions in which certain crops are shown. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0036] 1 is a flow diagram of an exemplary method 100 for estimating consumption of agricultural products in a geographic region. For example, the agricultural products can be fungicides, herbicides, insecticides, acaricides, molluscicides, nematicides, birdicides, pisciicides, rodenticides, repellents, bactericides, biocides, safeners, plant growth regulators, urease inhibitors, nitrification inhibitors, denitrification inhibitors, fertilizers, nutrients, seeds / seedlings, and / or combinations thereof.

[0037] In step 110, crop growth index data is provided for a geographical region (e.g., Bavaria). The crop growth index data can be Normalized Difference Vegetation Index (NDVI) data, Leaf Area Index (LAI) data, Normalized Difference Water Index (NDWI) data, Enhanced Vegetation Index (EVI) data. The crop growth index data can be provided at the early planting stage of a particular crop (e.g., soybean). The crop growth index data, preferably Normalized Difference Vegetation Index (NDVI) data, can be provided for a period of time (e.g., two weeks starting 15 days after sowing). Considering a period of time rather than just a point in time can greatly improve the accuracy of determining which areas are planted with which particular crop.

[0038] Areas of the geographic region cultivated with a particular crop are determined based on a comparison of the provided crop growth index data to the plant-specific reference data, step 120. In one example, the crop growth index data and the reference data are NVDI data.

[0039] In step 130, a product consumption model for an agricultural product is provided, the product consumption model being configured to estimate the consumption of the agricultural product based at least on the area of ​​a geographical region cultivated with a particular crop. For example, a consumption model for Cantus Gold (a fungicide for treating maturity diseases of rapeseed) is provided. The product consumption model may be based on the results of a machine learning algorithm that estimates the consumption of the agricultural product. However, it is also possible to use a statistically based product consumption model. Moreover, such a product consumption model is not limited to using only area, i.e., further data may be used in this regard. Shelf life data of the agricultural product, farmers' expected planting decisions, pest pressure data, regulatory data of the agricultural product, etc. may also be considered here to improve the accuracy of the product consumption estimate.

[0040] In step 140, an estimate of the consumption of agricultural products in areas cultivated with particular crops is performed. For example, if it is determined that 1000 hectares in an agricultural area are cultivated with rapeseed, an estimate of the consumption of Cantus Gold can be provided.

[0041] In the following, an alternative solution for estimating the consumption of agricultural products in a geographical region is described.

[0042] In a first step, biomass data of a particular crop (e.g. soybean plants) is provided for a geographical region (e.g. Bavaria) at time t1 (e.g. early crop stage 21 days after sowing). For example, the biomass data may be derived from remote sensing measurements (e.g. satellite images or multispectral information) and analysis of the observed geographical area / region's spectral reflectance values. The biomass data of a particular crop may be based on Normalized Difference Vegetation Index (NDVI) data and / or Leaf Area Index (LAI) data, Normalized Difference Water Quality Index (NDWI) data, Extended Vegetation Index (EVI) data and / or any other vegetation-based index data.

[0043] In a second step, a crop growth model for the particular crop is configured to estimate biomass data of the particular crop at time t2 (e.g., 6 weeks after sowing) based at least on the biomass data at time t1. For example, such a crop growth model may be based on the results of a machine learning algorithm that estimates biomass data of the particular crop at time t2 based on the biomass data at time t1. However, alternatively, a statistically based crop growth model may be used.

[0044] In a third step, a product consumption model for agricultural products is provided, configured to estimate the consumption of agricultural products at time t2 based at least on the estimated biomass data of the particular crop at time t2. Again, the product consumption model may be based on the results of a machine learning algorithm estimating the consumption of agricultural products at time t2 and / or the period t1-t2. However, alternatively, a statistically based product consumption model may be used. Moreover, such a product consumption model is not limited to using only biomass data, i.e. further data may be used in this respect. For example, weather data may also be taken into account if it is not already included in the growth model. Also, shelf life data of agricultural products, expected planting decisions of farmers, pest pressure data, regulatory data of agricultural products, etc. may be taken into account here to improve the accuracy of the product consumption estimate.

[0045] In a fourth step, an estimate of consumption of the agricultural product at time t2 and / or for the period t1-t2 is provided based at least on biomass data of the specific crop at time t1 by using a crop growth model for the specific crop and a product consumption model for the agricultural product in the geographical region.

[0046] FIG. 2 is a schematic diagram of an exemplary system 10 for estimating consumption of agricultural products in an area of ​​a geographical region cultivated with a particular crop, the system 10 comprising: a providing unit 11 configured to provide crop growth index data for the geographical region; a determining unit 12 configured to determine an area of ​​the geographical region cultivated with the particular crop based at least on a comparison of the provided crop growth index data with plant-specific reference data; a providing unit 13 configured to provide a product consumption model for the agricultural product configured to estimate consumption of the agricultural product based at least on the area of ​​the geographical region cultivated with the particular crop; and a providing unit 14 configured to provide an estimate of consumption of agricultural products for the determined area of ​​the geographical region cultivated with the particular crop using the product consumption model based at least on the determined area cultivated with the particular crop.

[0047] FIG. 3 is a schematic diagram of NDVI data in a geographical region over the period April 2019 to November 2020. The vertically highlighted areas in the NDVI data highlight the planting period, i.e. the start of the respective season. Dates are shown on the horizontal axis and NDVI is shown on the vertical axis. In the illustrated example, NDVI data for winter-sown rapeseed (WRa2, see reference 20), winter-sown wheat (WW, see reference 21), sugar beet (ZR, see reference 22) and winter-sown rye (WR, see reference 23). As shown, the present disclosure can provide a continuous monitoring of a geographical region, so that the respective subsequent processes, for example the manufacturing process of an agricultural product, can also be continuously adjusted and optimized.

[0048] Fig. 4 shows a diagram of a geographical region in which different fields with different specific crops are highlighted as an example for clarity of explanation. This allocation of each field with each crop can be obtained as a result of a comparison of the received NVDI data with NVDI reference data. From this, the areas planted with specific crops can be determined later by adding up the respective areas.

[0049] Below, a non-exhaustive list of non-limiting examples is provided as embodiments A through R. Any one or more of the features of these examples may be combined with any one or more features of another example, embodiment, or aspect described herein.

[0050] Embodiment A 1. A computer-implemented method for estimating consumption of an agricultural product in a geographic region, comprising: Providing biomass data for a particular crop for a geographical region at time t1; providing a crop growth model for a particular crop, the model being configured to estimate biomass data for the particular crop at time t2 based at least on biomass data at time t1; providing a product consumption model for agricultural products configured to estimate a consumption of the agricultural product at time t2 based at least on estimated biomass data of a particular crop at time t2; providing an estimate of consumption of the agricultural product at time t2 and / or for the period t1-t2 based at least on biomass data of the particular crop at time t1 using a crop growth model for the particular crop and a product consumption model for the agricultural product in the geographic region; 4. A computer-implemented method comprising:

[0051] Embodiment B The method of embodiment A, wherein the agricultural product is a fungicide, herbicide, insecticide, acaricide, molluscicide, nematicide, birdcide, pisciicide, rodenticide, repellent, bactericide, biocide, safener, plant growth regulator, urease inhibitor, nitrification inhibitor, denitrification inhibitor, fertilizer, nutrient, seed / seedling, and / or combinations thereof.

[0052] Embodiment C The method of embodiment A or B, wherein the biomass data for a particular crop is based on Normalized Difference Vegetation Index (NDVI) data and / or Leaf Area Index (LAI) data, Normalized Difference Water Index (NDWI) data, Extended Vegetation Index (EVI) data and / or any other vegetation-based index data.

[0053] Embodiment D The method of any one of embodiments A-C, wherein the biomass data is obtained by using synthetic aperture radar (SAR), light detection and ranging (LIDAR) via satellite, unmanned vehicle, vehicle-mounted sensor, and / or combinations thereof.

[0054] Embodiment E The method according to any one of embodiments A to D, wherein time t1 is the present time or 15 to 30 days after sowing, preferably 17 to 25 days after sowing, most preferably 21 days after sowing, and t2 is preferably 2 to 10 weeks after t1, preferably 4 to 8 weeks after t1, most preferably 6 weeks after t1.

[0055] Embodiment F The method of any one of embodiments A to E, wherein the crop growth model for the particular crop is based on the results of a machine learning algorithm that estimates biomass data for the particular crop at time t2 based on biomass data at time t1.

[0056] Embodiment G The method of any one of embodiments A-F, wherein the product consumption model is based on the results of a machine learning algorithm that estimates the consumption of agricultural products at time t2 and / or at the period t1-t2.

[0057] Embodiment H providing inventory recommendation data regarding minimum stock levels of agricultural products at time t2 based on estimates of consumption of agricultural products at time t2 and / or at time period t1-t2; and / or providing inventory recommendation data regarding minimum inventory levels of basic materials required for the production of the agricultural product at time t2 based on the estimates of consumption of the agricultural product at time t2 and / or for the period t1-t2; and / or providing production recommendation data for producing an agricultural product based on the estimate of consumption of the agricultural product at time t2 and / or at time period t1-t2; and / or providing order recommendation data for ordering quantities of agricultural products and / or quantities of basic materials required for the production of the agricultural products based on the estimates of the consumption of the agricultural products at time t2 and / or for the period t1-t2; and / or providing summary data on all agricultural products required and / or recommended for a particular crop at time t2 and / or for the period t1-t2; and / or providing control data for manufacturing, logistics, and / or warehousing processes with respect to the agricultural product based on the estimate of the consumption of the agricultural product at time t2 and / or at the time period t1-t2; The method of any one of embodiments A-G, further comprising at least one of:

[0058] Embodiment I The use of specific crop biomass data for a geographical region in the method according to any one of embodiments A-H.

[0059] Embodiment J 1. A computer-implemented method for providing training data for a machine learning algorithm that estimates consumption of an agricultural product in a geographic region, the method comprising: Providing biomass data for a particular crop for a geographic region; providing agricultural product consumption data for a particular crop for a geographical region; labeling the biomass data of a particular crop with agricultural product consumption data for the particular crop; 4. A computer-implemented method comprising:

[0060] Embodiment K The method of embodiment J, wherein the biomass data and consumption data are historical data for a geographic region comprising the last 3 years, preferably 5 years, and most preferably 10 years of data.

[0061] Embodiment L A neural network and / or machine learning model for estimating consumption of agricultural products in a geographic region, trained using the training data of embodiment J or K.

[0062] Embodiment M 1. A system for estimating consumption of an agricultural product in a geographic region, comprising: a providing unit configured to provide biomass data of a particular crop for a geographical region at time t1; a providing unit configured to provide a crop growth model for a particular crop, the providing unit being configured to estimate biomass data for the particular crop at time t2 based at least on biomass data at time t1; a providing unit configured to provide a product consumption model for an agricultural product, the providing unit being configured to estimate a consumption of the agricultural product at time t2 and / or at a time period t1-t2 based at least on estimated biomass data of a particular crop at time t2; a providing unit configured to provide an estimate of consumption of an agricultural product at time t2 and / or at a period t1-t2 based at least on biomass data of the particular crop at time t1 using a crop growth model for the particular crop and a product consumption model for the particular agricultural product; A system comprising:

[0063] Embodiment N A computer program element comprising instructions configured to, when executed on a computing device of a computing environment, perform the steps of the method according to any one of embodiments A to H in the system according to embodiment M.

[0064] Embodiment O A computer-readable medium having stored thereon the computer program element of embodiment N.

[0065] An aspect of the present disclosure relates to a computer program element configured to execute the steps of the above-mentioned method. Thus, the computer program element may be stored in a computing unit of a computing device that may also be part of an embodiment. This computing unit may be configured to execute or induce the execution of the steps of the above-mentioned method. Furthermore, the computing unit may be configured to operate the components of the above-mentioned 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. Thus, the data processor may be equipped to execute the method according to one of the above-mentioned embodiments. This exemplary embodiment of the present disclosure encompasses both a computer program that uses the present disclosure from the beginning and a computer program that updates an existing program to become a program that uses the present disclosure. Furthermore, the computer program element may be capable of providing all the steps necessary to carry out the procedures of the exemplary embodiments of the above-mentioned method. According to a further exemplary embodiment of the present disclosure, a computer readable medium such as a CD-ROM, a USB stick, a downloadable and executable one, is presented, on which computer readable medium are stored computer program elements, such as those described in the previous section. The computer program may be stored on and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems, however, the computer program may also be presented via a network, such as the World Wide Web, and may be downloaded from such a network into the working memory of a data processor.According to a further exemplary embodiment of the present disclosure, a medium is provided making available a computer program element for downloading, the computer program element being configured to perform a method according to one of the above-mentioned embodiments of the present disclosure.

[0066] The disclosure has been described by way of example in conjunction with the preferred embodiment. However, other variations can be understood and implemented by those skilled in the art, by studying the drawings, the disclosure, and the claims, and by practicing the claimed invention. In particular, any steps specifically presented may be performed in any order, i.e., the invention is not limited to a particular order of these steps. Moreover, it is not required that different steps are performed at a particular location or at one node of a distributed system, i.e., each of the steps may be performed at different nodes using different equipment / data processing units.

[0067] In the claims and in this description, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage in an implementation.

Claims

1. A computer-implemented method (100) for estimating the consumption of agricultural products in an area of a geographical region cultivated with a specific crop, comprising: providing (110) crop growth index data regarding the geographical region; determining (120) an area of the geographical region cultivated with the specific crop based at least on a comparison between the provided crop growth index data and plant-specific reference data; providing (130) a product consumption model regarding the agricultural products, configured to estimate the consumption of the agricultural products based at least on the area of the geographical region cultivated with the specific crop; using the product consumption model to provide (140) an estimated value of the consumption of the agricultural products regarding the determined area of the geographical region cultivated with the specific crop based at least on the determined area. A computer-implemented method (100) including the above steps.

2. The computer-implemented method according to claim 1, wherein the agricultural products are fungicides, herbicides, insecticides, acaricides, molluscicides, nematicides, avicides, piscicides, rodenticides, repellents, bactericides, biocides, toxicity mitigators, plant growth regulators, urease inhibitors, nitrification inhibitors, denitrification inhibitors, fertilizers, nutrients, seeds / seedlings, and / or combinations thereof.

3. The computer-implemented method according to claim 1, wherein the crop growth index data are normalized difference vegetation index (NDVI) data, leaf area index (LAI) data, normalized difference water index (NDWI) data, enhanced vegetation index (EVI) data.

4. The computer-implemented method according to claim 1, wherein the cultivated area in the geographical region is determined regarding a group of crops preselected based on the crop growth index data regarding the geographical region.

5. The computer-implemented method according to claim 1, wherein the crop growth index data are provided at an initial crop stage of the specific crop.

6. The crop growth index data, preferably the normalized difference vegetation index (NDVI) data, is the start time t which is the current time or 15 to 30 days after sowing of the specific crop, preferably 17 to 25 days after sowing of the specific crop, and most preferably 21 days after sowing of the specific crop. １ and t １ 2 to 10 weeks later, preferably t １ 4 to 8 weeks later, most preferably t １ The computer-implemented method according to claim 1, which is provided during the period up to 6 weeks later at the end time t. ２ ​

7. The computer-implemented method according to claim 1, wherein the crop growth index data are provided regarding a pre-determined time series.

8. The computer-implemented method according to claim 1, wherein the plant-specific reference data are provided by a centralized and / or distributed computing environment.

9. The step of determining the area cultivated using the specific crop is based on data obtained by using synthetic aperture radar (SAR), light detection and ranging (LIDAR) via a satellite, an unmanned vehicle, a vehicle-mounted sensor, and / or a combination thereof. The computer-implemented method according to claim 1.

10. The product consumption model for the area cultivated using the specific crop is based on the result of a machine learning algorithm configured to estimate the consumption amount of the agricultural product based at least on the area of the geographical region cultivated using the specific crop. The computer-implemented method according to claim 1.

11. Based on the estimated value of the consumption amount of the agricultural product, providing inventory recommendation data regarding the minimum inventory level of the agricultural product at a specific time and / or during a certain period, and / or Based on the estimated value of the consumption amount of the agricultural product, providing inventory recommendation data regarding the minimum inventory level of the basic materials required for the production of the agricultural product at a specific time and / or during a certain period, and / or Based on the estimated value of the consumption amount of the agricultural product, providing production recommendation data for producing the agricultural product, and / or Based on the estimated value of the consumption amount of the agricultural product, providing order recommendation data for ordering the quantity of the agricultural product and / or the quantity of the basic materials required for the production of the agricultural product, and / or Providing summary data regarding the agricultural products required and / or recommended for the specific crop, and / or The computer-implemented method according to claim 1, further comprising at least one of the steps of providing control data regarding the manufacturing process, the logistics process, and / or the warehouse process for the agricultural product based on the estimated value of the consumption amount of the agricultural product.

12. A computer-implemented method for providing training data for a machine learning algorithm for estimating the consumption amount of an agricultural product in an area of a geographical region cultivated using a specific crop, the method comprising the steps of providing data including information regarding the area cultivated using the specific crop, and providing consumption amount data of the agricultural product regarding the provided area cultivated using the specific crop. Labeling the data including information about the area cultivated using the specific crop with the consumption data of the agricultural product for the provided area cultivated using the specific crop A computer-implemented method including the above steps.

13. A neural network and / or machine learning model trained using the training data according to Claim 12 for estimating the consumption of an agricultural product in an area of a geographical region cultivated using a specific crop.

14. An apparatus for estimating the consumption of an agricultural product in an area of a geographical region cultivated using a specific crop, comprising: One or more computing nodes, and when executed by the one or more computing nodes, causing the apparatus to: Provide (110) crop growth index data regarding the geographical region; Determine (120) an area of the geographical region cultivated using the specific crop based at least on a comparison between the provided crop growth index data and plant-specific reference data; Provide (130) a product consumption model regarding the agricultural product configured to estimate the consumption of the agricultural product based at least on the area of the geographical region cultivated using the specific crop; Using the product consumption model, provide (140) an estimated value of the consumption of the agricultural product regarding the determined area of the geographical region cultivated using the specific crop based at least on the determined area cultivated using the specific crop; One or more computer-readable media having computer-executable instructions configured to cause the above steps to be executed; An apparatus comprising the above elements.

15. A computer program element including instructions, which when executed on one or more computing nodes, are configured to execute the steps of the method according to any one of Claims 1 to 12 or to be executed by the apparatus according to Claim 14.

Images