Method for validating and / or correcting geographic map data

Abstract

1. A computer-implemented method for validating and / or correcting map data, the method comprising: providing (S10) geographical topography data for at least one geographic area; providing (S20) at least one historical time series of geographical topography data for at least a portion of the geographic area to which the geographical topography data relates; extracting predetermined features from the geographical topography data and extracting features from the historical time series of geographical topography data; classifying and assigning (S40) the geographical topography data to at least a first group of geographical map data or a second group of geographical map data based on a comparison of the features extracted from the geographical topography data and the features extracted from the historical time series of geographical topography data; and performing (S50) a first operation on the first group of geographical map data and a second operation on the second group of geographical map data.

Description

[Technical Field]

[0001] The present invention relates to a computer-implemented method for validating and / or correcting geographical map data, the use of the method for producing agricultural decision maps and / or agricultural application maps, a system for validating and / or correcting geographical map data, and computer program elements for carrying out the method. [Background technology]

[0002] When planning agricultural decisions or applications, input / geographical map data of a geographical area, e.g., satellite maps, are used to create so-called decision or application maps. These maps are intended to show users where and in what quantities applications (e.g., pesticide discharges) should be carried out. Such maps can also be used to create control data for agricultural equipment. In this respect, it is important that the input / geographical map data is of good quality and suitable for creating decision or application maps.

[0003] In view of this, it can be seen that there is a further need to provide a method by which the quality and / or suitability of input / texture map data can be improved. Summary of the Invention

[0004] In view of the above, it is an object of the present invention to provide a method by which the quality and / or suitability of input / texture map data can be improved. These and other objects 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.

[0005] In a first aspect, a computer-implemented method for validating and / or correcting geographical map data is provided, comprising the steps of: providing geographical topography data associated with at least one geographical map data; providing at least one time series of geographical map data associated with at least a portion of the geographic area to which the geographical topography data is associated; extracting predetermined features from the geographical topography data and extracting features from the time series of geographical map data; classifying and assigning the geographical topography data to at least a first group of geographical map data or a second group of geographical map data based on a comparison of the features extracted from the geographical topography data and the features extracted from the time series of geographical map data; performing a first operation for the first group of geographical map data and a second operation for the second group of geographical map data. In particular, although the present disclosure is preferably used to validate and / or correct geographical map data, it may also be performed to validate or correct geographical map data.

[0006] In other words, it is proposed to provide a time series of geographical map data covering the same geographic area or at least a portion of that geographic area referenced by the geographical map data. The time series of geographical map data preferably includes at least two sets of geographical map data, each of which refers to a different historical point in time. The geographical map data is preferably map data that has not undergone further data processing, in particular verification or correction, e.g., data obtained directly from a sensor. The time series of geographical map data includes maps that are already considered suitable, whereby these maps have already been determined as good or suitable map data by a person or an image recognition algorithm. The determined / extracted features of the geographical map data and the time series of geographical maps are then compared using a classification or clustering algorithm to determine to what extent the features of the geographical map data in question match the features of the time series. In this context, using features as a basis for comparison reduces the data dimensionality, allowing the framework to be sensitive only to the types of errors / noise that affect the structure of the geographical map. This also means that the selection of these features depends on the data type and the factors that generate the noise. Furthermore, by including temporal information, e.g., data acquisition time, as input to the algorithm, the framework can distinguish between natural / accepted and unnatural / anomalous inconsistencies when comparing raw geographic maps and time series. Typically, this indicates that the longer the time between the collection time of the raw geographic map and its historical reference set, the more tolerant the algorithm is to image feature changes without anomalies being detected. The result of this (similarity) comparison step is preferably a probability or quality probability value that the geographic map data corresponds to a map from a past time series of geographic data. Because the geographic data from the past time series has already been classified as usable, this probability value also corresponds to the probability that the geographic map data can also be considered usable.As a result, the proposed comparison between the features of the time series of geographical map data and the features of the texture map data can be used to determine whether the texture map data are suitable for further use. Based on this probability value, the texture map data is classified and assigned to a first or second group for further processing. In other words, in the classification and assignment step, a quality probability value is calculated for the geographical texture map data based on the comparison between the features extracted from the geographical texture map data and the features extracted from the time series of geographical map data, and the geographical texture map data is assigned to the first or second group of geographical map data based on the quality probability value. In particular, if similar quality probability values ​​are obtained in the classification step, only one of the possible data can be used. The quality probability value can provide a numerical value representing the similarity value between the texture map data and the time series of geographical map data. In particular, in this regard, ranges and / or thresholds for the quality probability values ​​based on which the geographical map data is classified and assigned to the first or second group of geographical map data can be, for example, predetermined and / or provided by the user.

[0007] In particular, the extraction of predetermined features from the geographical topographical map data and / or the extraction of features from the time series of geographical map data, and / or the classification and assignment steps are preferably performed by analytical algorithms executable by a central computing device, a network computing solution, and / or a cloud computing solution. This therefore offers the possibility of combining the individual steps of extracting features, classifying the topographical map data, and assigning them to one of the groups. However, it is also possible to use two or more analytical algorithms to perform each step. In this regard, it is preferred that each analytical algorithm or algorithms are based on the results of a machine learning algorithm. The machine learning algorithm 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 dimensionality into outputs with much lower dimensionality. Such machine learning algorithms are called "intelligent" because they can be "trained." The algorithm can be trained using records of training data. The records of training data include training input data and corresponding training output data. The training output data for a record of training data is the result that a machine learning algorithm is expected to produce when given the training input data for the same record of training data as input. The deviation 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 parameters of the machine learning algorithm's internal processing chain. For example, the parameters may be adjusted with the optimization goal of minimizing the value of the loss function that occurs when all training input data is fed to the machine learning algorithm and the results are compared to the corresponding training output data.The results of this training enable a machine learning algorithm to perform well on a large number of orders of magnitude larger input data records when given a relatively small number of training data records as "ground truth." It is during this training process that the analytical algorithm "learns" the nonlinear relationship between the extracted features and the temporal information provided as input, and whether or to what extent a particular raw geographic map constitutes an anomaly with respect to the provided historical set. Thus, the training set preferably includes both good-quality / consistent geographic maps and poor-quality / inconsistent maps, as well as many instances of the expected classifications that the algorithm needs to replicate. Based on this data, the analytical algorithm then learns what values ​​for which features, and under what temporal conditions, indicate significant deviations from the historical set.

[0008] The term geographical map data should be broadly understood and relate to any data relating to a specific area, for example, satellite map data, data generated by sensor-equipped agricultural machinery, data generated by aircraft such as airplanes, planes, or helicopters, or data generated by unmanned aerial vehicles such as drones. Furthermore, the present invention is not limited to a specific format of the geographical map data or the time series of geographical map data. In this regard, the geographical map data and / or the time series of geographical map data can be provided as spatially resolved map data, as raster map data, and / or as image map data, and the geographical map data and the time series of geographical map data are preferably provided as satellite or regional maps and / or images, and the geographical map data and / or the time series of geographical map data are preferably provided with time information. Furthermore, it should be noted that the present invention is not limited to using acquired map data to generate decision-making or application maps in an agricultural context, but includes all applications that can be based on the use of acquired map data. Finally, it should be noted that the present invention is also not limited to a specific sequence of the first and second operations or the fact that they are performed in a specific temporal context.

[0009] In one implementation, in the classifying and allocating step, the first group of geographical map data relates to geographical map data classified as unusable for creating agricultural decision maps and / or agricultural application maps; the second group of geographical map data relates to geographical map data classified as usable for creating agricultural decision maps and / or agricultural application maps. The second operation for the second group of geographical map data preferably means that this geographical map data is used to process map data, for example in the context of a farm manager system or in an agricultural recommendation engine or system, so that an agricultural decision / application map can subsequently be generated.

[0010] In this context, it should be noted that the present invention is not limited to this proposed classification into two groups. Rather, the geographic data can be divided into any number of groups, each of which can then be processed or used separately as a group. The term "agricultural decision map" is preferably understood to be a map showing the two-dimensional spatial distribution of recommended agricultural actions to be taken at different locations or areas within a farm. The term "agricultural application map" is preferably understood to be a map showing the two-dimensional spatial distribution of product amounts, or product application rates, or product types, or product forms, or treatment methods to be applied to different locations or areas within a farm.

[0011] In one implementation, the first action for the first group of geographical map data is to discard or delete the first group of geographical map data. In this regard, it is possible to delete the data of the first group of geographical map data without showing these map data to the user. However, it is also possible to show the discarded geographical map data to the user, so that the user can manually decide how to proceed with the first group of geographical map data. In another implementation, the first action for the first group of geographical map data is to postpone or refrain from (further) processing the first group of geographical map data or to transfer the first group of geographical map data to another storage medium or system. In an alternative or additional implementation, the first action for the first group of geographical map data is to execute at least one default correction algorithm to obtain corrected geographical map data, which is preferably fed back at least once to the classification and assignment step as geographical texture data. In this regard, the default correction algorithm is preferably an image smoothing algorithm, an image sharpening algorithm, an image brightness adjustment algorithm, and / or an image blurring algorithm. In other words, it is possible and preferable to attempt to improve / correct the geographical map data that are initially classified as unusable / unsuitable, so that they can ultimately be classified as suitable map data.

[0012] In one implementation, the first operation for the first group of geographical map data is to perform at least one heuristic correction procedure to obtain corrected geographical map data, the at least one heuristic correction procedure preferably including performing a grid search to identify suitable parameters of a smoothing filter and / or a sharpening filter and / or any other deconvolution filter, the ranges of these parameters being preferably preset, and the corrected geographical map data being fed back at least once to the classification and assignment step, preferably as geographic raw map data. In this respect, a predetermined number of potentially corrected geographical map data are generated by means of the heuristic correction algorithm, the predetermined number of potentially corrected geographical map data being preferably fed back at least once to the classification and assignment step as geographic raw map data, and the geographical map data with the highest quality probability being assigned to the second group of geographical map data.

[0013] In one implementation, the first operation for the first group of geographical map data is to perform at least one extensive search of historical records for alternative map data, wherein the at least one extensive search of historical records includes evaluating whether geographical map data generated at a different time matches a reference historical set, thereby being able to replace data previously assigned to the first group, wherein the extensive search of historical records is performed with the aid of auxiliary data including, but not limited to, growth stage, crop variety, season, and weather conditions, and the virtual alternative set is preferably fed back at least once to the classification and assignment step as geographical topography data, and wherein the geographical map data with the highest quality probability value is allocated to the second group of geographical map data.

[0014] Again, a correction algorithm based on the results of a machine learning algorithm can be used. Here, the machine learning algorithm preferably includes a decision tree, a naive Bayes classification, a nearest neighbor, a neural network, a convolutional neural network, a generative adversarial network, a support vector machine, a linear regression, a logistic regression, a random forest, and / or a gradient boosting algorithm. Preferably, the machine learning algorithm is configured to process inputs having high dimensionality into outputs having much lower dimensionality. Such machine learning algorithms are called "intelligent" because they can be "trained." The algorithm can be trained using records of training data. The records of training data include training input data and corresponding training output data. The training output data of a record of training data are the results expected to be produced by the machine learning algorithm when given the training input data of the same record of training data as input. The deviation between this expected result and the actual result produced by the algorithm is observed and evaluated by means of a "loss function." This loss function is used as feedback to adjust parameters of the machine learning algorithm's internal processing chain. For example, parameters may be tuned with an optimization goal of minimizing the value of a loss function that occurs when all training input data is fed into a machine learning algorithm and the output results are compared to the corresponding training output data. The result of this training is that, given a relatively small number of training data records as "ground truth," the machine learning algorithm is able to perform well on a large number of input data records that are orders of magnitude larger.

[0015] In one implementation, the time series of geographical map data includes between 2 and 1,000 datasets associated with the geographic map. In one example, the time series of geographical map data includes at least two datasets, between at least 2 and 100, between at least 2 and 20, or between at least 2 and 10 datasets. In a further implementation, the time series of geographical map data provided is filtered based on temporal information of the geographical topographic map data. This allows for a certain amount of pre-filtering to be performed based on temporal coherence, so that corresponding features only need to be extracted and compared for some or one map of the time series of geographical map data.

[0016] In one embodiment, the provided historical time series of geographical map data is filtered based on auxiliary filtering data, preferably crop harvest data relating to the amount of crop harvested in the past, crop type data relating to the type of crop sown in the geographic area, sowing data relating to the amount and spatial pattern of sowing, weather data relating to the weather conditions at the time the geographical map data was recorded, growth stage data relating to the growth stage of the crop at or before the time the geographical map data was recorded, temperature data relating to the temperature at or before the time the geographical map data was recorded, precipitation data relating to the amount of precipitation at or before the time the geographical map data was recorded, and / or soil and / or air humidity data relating to the soil and / or air humidity at or before the time the geographical map data was recorded. These auxiliary filtering data also enable reduction of relevant maps from the time series of geographical map data, so that corresponding features need only be extracted and compared for multiple or only one map of the time series of geographical map data.

[0017] In one implementation, the features extracted from the geographical topography data and / or time series of geographical map data are one or more of the following: variance, entropy, uniformity, gray-level co-occurrence matrix (GLCM), gray-level size zone (GLSZM), neighborhood gray-tone difference matrix (NGTDM), and other radiometric features. In one example, the features extracted are predetermined / selected by a user and / or administrator. In a further example, the features extracted may be provided by different predetermined sets of features. These sets of features can be provided to a user, who can select which set of features to apply.

[0018] In a further aspect, use of the method for validating and / or correcting geographical map data as described above for a method for generating an agricultural decision map and / or an agricultural application map is disclosed. In yet another aspect, a system for validating and / or correcting geographical map data is disclosed, the system comprising: at least one data entry interface configured to receive geographical topography data for at least one geographic area; at least one data entry interface configured to receive at least one time series of geographical map data for at least a portion of the geographic area to which the geographical topography data pertains; at least one processing unit configured to extract predetermined features from the geographical topography data and extract features from the time series of geographical map data; at least one processing unit configured to classify and assign the geographical topography data to at least a first group of geographical topography data or a second group of geographical map data based on a comparison of the features extracted from the geographical topography data with the features extracted from the time series of geographical map data; and at least one processing unit configured to perform a first operation on the first group of geographical map data and a second operation on the second group of geographical map data.

[0019] Finally, the present invention relates to a computer program or computer program element configured to execute the above-described method on a suitable device or system. Thus, the computer program element may be stored on a computer unit that is part of the embodiment. This computing unit may be configured to execute or trigger the execution of the above-described method steps. Furthermore, it may be configured to operate the above-described device and / or system components. The computing unit may be configured to operate automatically and / or to execute user instructions. The computer program is loaded into the working memory of a data processor. Thus, the data processor may be implemented to execute a method according to one of the above-described embodiments. This exemplary embodiment of the present invention encompasses both a computer program that uses the present invention from the beginning and a computer program that transforms an existing program into a program that uses the present invention by means of an update. Furthermore, the computer program element may provide all the steps necessary to implement the procedures of the above-described exemplary method embodiments. According to a further exemplary embodiment of the present invention, a computer-readable medium, such as a CD-ROM or USB stick, is presented, having stored thereon a computer program element, which is described in the previous section. The computer program may be stored and / or distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless communication systems. However, the computer program may also be presented over a network such as the World Wide Web and downloaded from such a network into the working memory of a data processor. Cloud computing solutions may also be used.According to a further exemplary embodiment of the present invention, a medium is provided for making available a computer program element for downloading, the computer program element being configured to perform a method according to one of the aforementioned embodiments of the present invention. [Brief explanation of the drawings]

[0020] In the following, the invention will be described, by way of example only, with reference to the accompanying drawings, in which: [Figure 1] 1 is a schematic diagram of a method according to a preferred embodiment of the present invention; [Figure 2] 1 is an exemplary illustration of the data used in the method shown in FIG. 1 ; [Figure 3] 1 is an exemplary illustration of a time series of geographic map data and two geographic topographic map data. DETAILED DESCRIPTION OF THE INVENTION

[0021] Figure 1 is a schematic diagram of a computer-implemented method for verifying and / or correcting geographical topographic map data according to a preferred embodiment of the present invention. Figure 2 is an exemplary illustration of the data used in the method shown in Figure 1, and Figure 3 is an exemplary illustration of a time series of geographical map data taking into account which two pieces of geographical topographic map data are analyzed. The present invention will now be described in more detail with reference to Figures 1-3.

[0022] In step S10, geographical topography data 10 relating to at least one geographic area during a time t is provided. These geographical topography data 10 may be provided, for example, in the form of satellite image data. In step S20, at least one time series of geographical map data 20 relating to at least a portion of the geographical area to which the geographical topography data 10 relates is provided. In the illustrated example, the historical time series of geographical map data 20 includes two sets of geographical map data for two different times. The geographical topography data 10 and / or the time series of geographical map data 20 may be provided as spatially resolved map data, as raster map data, and / or as image map data, and the geographical topography data 10 and the time series of geographical map data 20 are preferably provided as satellite maps and / or images, and the geographical topography data 10 and / or the time series of geographical map data 20 are preferably provided with time information. The series of time series of geographical map data 20 includes maps that have already been deemed suitable, whereby these maps have already been determined as good or suitable map data by a person or an image recognition algorithm.

[0023] In step S30, predetermined features 30 from the geographical texture map data 10 and features from the time series of the geographical map data 20 are extracted. For example, these features may be one or more of the following: variance, entropy, homogeneity, gray level co-occurrence matrix (GLCM), gray level size zone (GLSZM), neighborhood gray tone difference matrix (NGTDM), and other radiometric features.

[0024] In step S40, the geographical texture map data 10 is classified and assigned to at least a first group of geographical map data or a second group of geographical map data based on a comparison of features extracted from the geographical texture map data 10 with features extracted from the time series of geographical map data 20. The determined / extracted features of the geographical texture map data 10 and the time series of the geographical map 20 are compared to determine the degree to which the features match. In this regard, the result of this (similarity) comparison step is preferably a probability value or quality probability value that the geographical texture map data 10 corresponds to a map from the geographic time series data 20. Since the time series of geographical data has already been classified as usable, this probability value also corresponds to the probability that the texture map data can also be considered usable. As a result, the recommendation regarding the comparison of the features of the time series of the geographical map data 20 with the features of the texture map data 10 can be used to determine whether the texture map data 10 is suitable for further use. In light of this probability value, the texture map data 10 is classified and assigned to the first group or the second group for further processing.

[0025] In step S50, a first operation is performed on the first group of geographical map data and a second operation is performed on the second group of geographical map data. For example, in the classification and allocation step, the first group of geographical map data 50B relates to geographical map data classified as unusable for creating agricultural decision-making maps and / or agricultural application maps; the second group of geographical map data 50A relates to geographical map data classified as usable for creating agricultural decision-making maps and / or agricultural application maps. In this context, it should be noted that the present invention is not limited to the proposed classification into two groups. Rather, the geographical map data can be divided into any number of groups, each of which can then be processed or used separately as a group. The first operation on the first group of geographical map data 50B may be to discard or delete the first group of geographical map data 50B. This allows data in the first group of geographical map data 50B that will not be presented to the user to be deleted. However, it is also possible to present the discarded geographical map data 50B to the user, so that the user can manually decide how to further process the first group of geographical map data 50B or the particular geographical map data 10. In an alternative or additional implementation, the first operation for the first group of geographical map data 50B is to execute at least one default correction algorithm to obtain corrected geographical map data, which is preferably fed back at least once to the classification and assignment step as geographical map data 10. In this regard, the default correction algorithm is preferably an image smoothing algorithm, an image sharpening algorithm, an image brightness adjustment algorithm, and / or an image blurring algorithm. In other words, it is possible and preferable to attempt to improve / correct the geographical map data 10 that were initially classified as unusable / unsuitable, so that they are ultimately classified as suitable map data.Alternatively or additionally, the first operation for the first group of geographical map data 50B is to execute at least one heuristic correction algorithm to obtain corrected geographical map data 10, the at least one heuristic correction algorithm preferably including performing a grid search to identify appropriate parameters of a smoothing filter and / or parameters of a sharpening filter, the ranges of these parameters being preferably preset, and the corrected geographical map data being fed back at least once to the classification and assignment step, preferably as geographical raw map data. In this respect, it is preferred that a predetermined number of corrected geographical map data are generated by means of the heuristic correction algorithm, and the predetermined number of corrected geographical map data 10 are fed back at least once to the classification and assignment step, preferably as geographical texture map data 10, and the geographical map data with the highest quality probability is assigned to the second group of geographical map data 50A.

[0026] In particular, the extraction of predetermined features from the geographical topographical data 10, and / or the extraction of features from the time series of the geographical map data 20, and / or the classification and assignment of the topographical data 10 classified as "unusable" and / or any correction / improvement steps are preferably performed by analytical algorithms executed by a central computing device, a network computing solution, and / or a cloud computing solution. This therefore offers the possibility of combining the individual steps of extracting features, classifying the topographical data, and assigning them to one of the groups. However, it is also possible to use two or more analytical algorithms to perform each step. In this regard, each analytical algorithm or algorithms are preferably based on the results of a machine learning algorithm. The machine learning algorithms preferably include 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 algorithms are adapted to process inputs with high dimensionality into outputs with much lower dimensionality. Such machine learning algorithms are called "intelligent" because they can be "trained." The algorithms can be trained using records of training data. A training data record includes training input data and corresponding training output data. The training output data of a training data record is the expected result produced by a machine learning algorithm when given the training input data of the same training data record as input. The deviation 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 parameters of the machine learning algorithm's internal processing chain. For example, the parameters may be adjusted with an optimization goal of minimizing the value of the loss function that occurs when all training input data is fed into the machine learning algorithm and the output results are compared to the corresponding training output data.The result of this training is that, when given a relatively small number of training data records as "ground truth," a machine learning algorithm can perform well on a large number of input data records that are orders of magnitude larger.

[0027] The present invention has been described with reference to preferred embodiments and examples. However, other variations are possible, which will be understood and implemented by those skilled in the art in practicing the claimed invention, upon studying the drawings, the disclosure, and the claims. In particular, steps S10 to S50 can be performed in any order; i.e., the present invention is not limited to a specific order of these steps. Also, steps S10 to S50 may be performed individually or merged as appropriate. Furthermore, different steps are not required to be performed at a specific location or at one location; i.e., each step or part of a step may be performed at different locations using different equipment / data processing units. In the claims and the description, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. [Explanation of symbols]

[0028] S10: Provision of geographical topographical data S20: Providing at least one historical time series of geographic map data S30: Extraction of predetermined features S40: Classification and allocation of geographical topography data S50: Performing an operation on a group of geographic map data 10: Geographical surface map data 20: Historical time series of geographic map data 30: Feature extraction 40: Analysis of geographical topographical data 50: 1st and 2nd movements 50A: Matches available fabric map data / history set 50B: Unavailable fabric map data / mismatch with history set

Claims

1. 1. A computer-implemented method for verifying and / or correcting geographic map data, comprising: A computer providing (S10) geographical topographic map data for at least one geographic area; the computer providing (S20) at least one historical time series of geographic map data relating to at least a portion of the geographic area to which the geographic topographic map data relates; The computer extracts predetermined features from the geographical topographical map data and extracts features from the historical time series of geographical map data (S30); classifying and assigning the geographical texture map data to at least a first group of geographical map data or a second group of geographical map data based on a comparison of the features extracted from the geographical texture map data with the features extracted from the historical time series of geographical map data (S40); the computer performing a first operation on the first group of geographical map data and a second operation on the second group of geographical map data (S50); and wherein in the classifying and allocating step, the first group of geographical map data relates to geographical map data classified as unusable for generating agricultural decision-making maps and / or agricultural application maps, and the second group of geographical map data relates to geographical map data classified as usable for generating agricultural decision-making maps and / or agricultural application maps. method.

2. The method of claim 1 , wherein the geographical topographical data and / or the historical time series of geographical map data are provided as spatially resolved map data, as raster map data, and / or as image map data.

3. 3. The method of claim 1, wherein in the classifying and assigning step, a quality probability value is calculated for the geographical texture map data based on a comparison of the features extracted from the geographical texture map data with the features extracted from the historical time series of geographical map data, and the geographical texture map data is assigned to the first group of geographical map data or the second group of geographical map data based on the quality probability value.

4. The method of claim 1 , wherein the first action on the first group of geographical map data is to discard the first group of geographical map data.

5. 5. The method of claim 1, wherein the first operation for the first group of geographical map data is to execute at least one default correction algorithm to obtain corrected geographical map data.

6. 6. The method of claim 1, wherein the first operation for the first group of geographical map data is to perform at least one heuristic correction procedure to obtain corrected geographical map data, and the geographical map data having the highest quality probability value is assigned to the second group of geographical map data.

7. 7. The method of claim 1, wherein the first operation for the first group of geographical map data is to perform at least one extensive search of historical records to obtain alternatives for the geographical map data, and the alternatives having the highest quality probability values ​​are assigned to the second group of geographical map data.

8. The method of claim 1 , wherein the provided historical time series of the geographical map data is filtered based on temporal information of the geographical topographical map data.

9. The method of claim 1 , wherein the provided historical time series of geographical map data is filtered based on auxiliary filtering data.

10. 10. The method of claim 1, wherein the overlap area of ​​the geographical map data and the provided historical time series are divided into smaller spatial units, and any of the procedures of claim 1 is performed separately for each spatial unit, thereby resulting in a spatially varying correction of the geographical topography data.

11. The features extracted from the historical time series of the geographical topography data and / or geographical map data include: Variance, entropy, homogeneity, gray level co-occurrence matrix (GLCM), gray level size zone (GLSZM), neighborhood gray tone difference matrix (NGTDM), first order statistics or radiomic features, 11. The method of claim 1, wherein the first and second nucleotides are one or more of:

12. 12. A method of using the method for validating and / or correcting geographical map data according to any one of claims 1 to 11 to provide geographical map data for a method of creating agricultural decision-making maps and / or agricultural application maps.

13. 1. A system for verifying and / or correcting geographic map data, comprising: at least one data entry interface configured to receive geographic topographic map data relating to at least one geographic area; at least one data entry interface configured to receive at least one historical time series of geographic map data relating to at least a portion of the geographic area to which the geographic topographic map data pertains; at least one processing unit configured to extract predetermined features from the geographical topographical map data and extract features from the historical time series of geographical map data; at least one processing unit configured to classify and assign the geographical topography data to at least a first group of geographical map data or a second group of geographical map data based on a comparison of the features extracted from the geographical topography data with the features extracted from the historical time series of geographical map data; at least one processing unit configured to perform a first operation on the first group of geographical map data and a second operation on the second group of geographical map data; Equipped with wherein in the classifying and allocating processing unit, the first group of geographical map data relates to geographical map data classified as unusable for generating agricultural decision-making maps and / or agricultural application maps, and the second group of geographical map data relates to geographical map data classified as usable for generating agricultural decision-making maps and / or agricultural application maps. system.

14. A computer program adapted to perform the method of any one of claims 1 to 11 when executed by a processor.

Images