Method, system, device and storage medium for identifying calcium accumulation problems in brown soil farmland

Abstract

The present invention provides a method, system, device and storage medium for identifying calcium accumulation problems in brown soil farmland, which belongs to the field of soil feature identification, including obtaining the spatial distribution range of typical soil types and the corresponding typical profile description and calcium accumulation problem label information; calculating calcium accumulation problem indicators and extracting them to sample points to construct a calcium accumulation problem dataset for farmland. The data is cleaned and the indicators are screened according to the contribution degree, and input into the enhanced regression tree model for fitting to obtain a calcium accumulation problem prediction model. The calcium accumulation problem prediction model is used to perform a predictive analysis on the entire brown soil farmland area to obtain a brown soil farmland image with a calcium accumulation problem prediction value; the brown soil farmland image with the calcium accumulation problem prediction value is divided into two parts according to a set threshold of the prediction value, and a spatial distribution map of the calcium accumulation problem is obtained according to the dichotomy result. The spatial distribution of calcium accumulation problems in brown soil farmland can be obtained with less manpower and material resources, thereby improving the quality of farmland.

Description

Technical Field

[0001] The present invention belongs to the technical field of soil feature recognition, and in particular relates to a method, system, equipment and storage medium for identifying calcium accumulation problems in brown soil farmland. Background Art

[0002] Brown soils are widely distributed across China, and brown soil farmland in northern my country is a key wheat and corn-growing region. However, due to constraints on soil parent material, climate, and topography, brown soil farmland suffers from calcium accumulation, which severely impacts its physical and chemical properties. This includes clogging soil pores, impairing water infiltration and movement through the rhizosphere, and reducing plant availability of trace elements. This results in reduced crop yields, threatening the sustainable development of agriculture and urgently requires remediation. However, obtaining data and identifying the spatial distribution of brown soil farmland with calcium accumulation is a prerequisite for remediation, but traditional field surveys are cumbersome, time-consuming, and labor-intensive. Existing digital soil mapping technologies based on soil landscape models are conventional techniques for predicting these difficult-to-estimate soil properties. Currently, a more efficient approach is to select multiple environmental factors associated with calcium accumulation as variables and utilize legacy soil data and soil landscape models to predict and identify calcium accumulation. However, this approach still suffers from limitations in identification efficiency and accuracy. Summary of the Invention

[0003] In order to solve the problem of calcium accumulation identification in brown soil farmland, the present invention provides a method, system, device and storage medium for identifying calcium accumulation problems in brown soil farmland.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] A method for identifying calcium accumulation problems in brown soil farmland comprises the following steps:

[0006] Obtaining a soil map with calcium accumulation problem label information; the soil map includes spatial location points and calcium accumulation problem label information; extracting sample points corresponding to spatial locations of calcium accumulation problem indicators in the soil map to establish a calcium accumulation problem dataset;

[0007] Calculating the contribution of the calcium accumulation problem indicator to the calcium accumulation problem label information, and screening the indicator data of the calcium accumulation problem dataset according to the contribution information; selecting part of the data from the screened calcium accumulation problem dataset as a training set;

[0008] The training set data is input into the enhanced regression tree model to train the model and obtain a calcium accumulation problem prediction model;

[0009] The calcium accumulation problem prediction model is used to predict the brown soil farmland image to be detected, and a brown soil farmland image with a calcium accumulation problem prediction value is obtained; the brown soil farmland image with the calcium accumulation problem prediction value is divided into two parts according to a set threshold of the prediction value, and a spatial distribution map of the calcium accumulation problem is obtained according to the binary result.

[0010] Preferably, the step of inputting the training set data into the enhanced regression tree model to train the model and obtain a calcium accumulation problem prediction model specifically includes the following steps:

[0011] For the dataset ,in is the indicator feature, is the label information of the calcium accumulation problem and the initial prediction value of the initialization model Set to the mean of all target values:

[0012] ;

[0013] The enhanced regression tree model is specifically:

[0014] ;

[0015] in, It is a prediction model for calcium accumulation problems. is the number of iterations, It is The output of a weak learner;

[0016] In each round of iteration, the residual is calculated and the model's prediction value is , residual is the target value and the model's predictions are The differences between:

[0017] ;

[0018] Train a new regression tree to fit the residuals of the previous regression tree model;

[0019] The newly trained regression tree model The weight is added to the previous round of regression tree model and the learning rate is introduced To control the step size of each update:

[0020] ;

[0021] in, is the learning rate, usually , No. The output of a weak learner It is expressed as follows:

[0022] ;

[0023] The grid search method was used to optimize the model's hyperparameters. The hyperparameter values ​​were adjusted and the above training process was repeated to obtain a calcium accumulation problem prediction model.

[0024] Preferably, the step of calculating the contribution of the calcium accumulation problem indicator to the calcium accumulation problem label information and screening the indicator data of the calcium accumulation problem dataset according to the contribution information specifically includes the following steps:

[0025] The correlation coefficient calculation formula is used to obtain the correlation between the indicator and the calcium accumulation problem label information. The correlation calculation formula is:

[0026] ;

[0027] in, and are the mean values ​​of the terrain features when the calcium accumulation problem label is 1 and 0, respectively; is the standard deviation of the terrain characteristics; and are the number of samples when the calcium accumulation problem label is 1 and 0 respectively; is the total sample size;

[0028] Use the correlation degree to construct the correlation matrix; where the correlation matrix is:

[0029] ;

[0030] in, is the correlation between the i-th terrain index and the j-th sample point;

[0031] Obtain the eigenvalues ​​of the correlation matrix and arrange the eigenvalues ​​in descending order to form an eigenvalue sequence;

[0032] The contribution rate of each indicator is calculated based on the eigenvalue sequence using the formula:

[0033] ;

[0034] in, represents the contribution rate corresponding to the i-th terrain index, represents the i-th value in the eigenvalue sequence, represents the kth value in the eigenvalue sequence;

[0035] Refer to the contribution rate ranking to filter the data.

[0036] Preferably, the method further includes selecting data from the screened calcium accumulation problem dataset as a validation set, and inputting the validation set data into a validation model, specifically including the following steps:

[0037] Input the validation set into the trained calcium accumulation problem prediction model;

[0038] Traverse the true positive rate TPR and false positive rate FPR at different classification thresholds and draw the ROC curve. The formula is as follows:

[0039] ;

[0040] ;

[0041] Among them, TP represents true positive, FP represents false positive, and FN represents false negative;

[0042] Calculate the area under the ROC curve, or AUC. If the AUC is lower than the set threshold, reselect the model variables and hyperparameters.

[0043] Preferably, the set threshold value of the predicted value is obtained by the following steps:

[0044] Use the optimal recall rate curve to calculate the threshold and set multiple thresholds , traverse each threshold , calculate the recall and precision based on the model prediction results:

[0045] ;

[0046] ;

[0047] in, is at the threshold The true number of cases under is the number of false negatives, is the number of false positives;

[0048] According to the traversal results, draw the optimal recall rate curve and select the threshold.

[0049] Preferably, when there are insufficient sample points in the soil map, additional sampling is performed on the area with insufficient data, specifically: a total number of samples n is set, random sampling is performed with the patch area as the weight, and each patch The number of random sampling points The calculation formula is as follows:

[0050] ;

[0051] in, Plaque The number of sampling points; Plaque area; is the total area of ​​all patches; is the total number of samples.

[0052] Preferably, the calcium accumulation problem index specifically includes a terrain index, a climate index or a soil parent material index; and each sample point corresponds to a plurality of calcium accumulation problem index values.

[0053] The present invention also provides a system for identifying calcium accumulation problems in brown soil farmland, which specifically includes:

[0054] The data acquisition module is used to obtain a soil map with calcium accumulation problem label information; the soil map includes spatial location points and calcium accumulation problem label information; sample points corresponding to the spatial location of calcium accumulation problem indicators are extracted from the soil map to establish a calcium accumulation problem data set.

[0055] The data processing module is used to calculate the contribution of the calcium accumulation problem indicator to the calcium accumulation problem label information, and screen the indicator data of the calcium accumulation problem data set according to the contribution information; and select part of the data in the screened calcium accumulation problem data set as a training set.

[0056] The model module is used to input the training set data into the enhanced regression tree model to train the model and obtain a calcium accumulation problem prediction model.

[0057] The calcium accumulation problem identification module uses the calcium accumulation problem prediction model to predict the brown soil farmland image to be detected, and obtains a brown soil farmland image with a calcium accumulation problem prediction value; the brown soil farmland image with the calcium accumulation problem prediction value is divided into two parts according to the set threshold of the prediction value, and the spatial distribution map of the calcium accumulation problem is obtained according to the binary result.

[0058] The present invention also provides a computer device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps described in the method for identifying calcium accumulation problems in brown soil farmland.

[0059] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is loaded by a processor, the computer program can execute the steps described in the method for identifying calcium accumulation problems in brown soil farmland.

[0060] The method for identifying calcium accumulation problems in brown soil farmland provided by the present invention has the following beneficial effects:

[0061] The present invention constructs a data set of calcium accumulation problems in cultivated land by acquiring the spatial distribution range of typical soil types and the corresponding typical profile descriptions and calcium accumulation problem label information, and extracting sample points of spatial positions corresponding to calcium accumulation problem indicators. The contribution of calcium accumulation problem indicators to calcium accumulation problem label information is calculated, and the cultivated land calcium accumulation problem data set is screened according to the contribution information to obtain a data set with a high correlation with the calcium accumulation problem of brown soil cultivated land, thereby improving the accuracy of subsequent model processing. The screened data is input into the enhanced regression tree model for training to obtain a calcium accumulation problem prediction model. The calcium accumulation problem prediction model is used to predict the area to be detected, and a brown soil cultivated land image with a calcium accumulation problem prediction value is obtained. The brown soil cultivated land image with a calcium accumulation problem prediction value is divided into two parts according to a set threshold of the prediction value to obtain a spatial distribution map of the calcium accumulation problem. The traditional time-consuming and labor-intensive field investigation method is changed. The calcium accumulation problem distribution map of the area to be detected is obtained through model processing, which is intuitive and convenient, and is conducive to timely discovery of land calcium accumulation problems and improvement of cultivated land quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] To more clearly illustrate the embodiments of the present invention and its design, the following briefly introduces the drawings required for this embodiment. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0063] Figure 1 This is a flow chart of a method for identifying calcium accumulation problems in brown soil farmland according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to enable those skilled in the art to better understand the technical solution of the present invention and to be able to implement it, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solution of the present invention and are not intended to limit the scope of protection of the present invention.

[0065] Example

[0066] The present invention provides a method for identifying calcium accumulation problems in brown soil farmland. Figure 1 As shown, the specific steps include:

[0067] Step 1: Refer to relevant soil survey results and soil records and other related materials to obtain the spatial distribution range of typical soil types, corresponding typical profile descriptions and calcium accumulation problem label information, and conduct additional sampling. This includes:

[0068] Step 1.1: Collect representative profiles of all brown soil types. If the typical profile descriptions include features such as lime reaction, pseudohyphae deposition, calcium carbonate deposition, lime nodules, and white stem layers, the soil type is considered to have some degree of calcium accumulation. This generates a soil map that includes the spatial distribution of local brown soil types and labels indicating whether the soil type has calcium accumulation. If the soil profile data in the relevant soil data is insufficient to construct the model, perform additional sampling in areas with insufficient data, as described in Step 1.2.

[0069] Step 1.2: Set a total number of samples n, and randomly sample with the patch area as the weight. The number of random sampling points The calculation formula is as follows:

[0070] ;

[0071] in, Plaque The number of sampling points; Plaque area; is the total area of ​​all patches; is the total number of samples.

[0072] Step 2: Calculate the calcium accumulation problem indicators and extract them to sample points to construct a cultivated land calcium accumulation problem dataset.

[0073] Step 2.1: Indicators for calcification generally include climate, soil parent material, and topography. Indicators with spatial heterogeneity should be selected based on regional characteristics for subsequent steps. Here, topographic indicators are used as an example, and they include multiple topographic sub-elements.

[0074] Step 2.2: Use the sample points with calcification problem label information obtained in step 1, extract the value of the terrain indicator corresponding to the spatial position of each sample point, and then construct a cultivated land calcification problem dataset. Each sample point corresponds to the value of multiple terrain indicators.

[0075] Step 3: Clean the data and screen indicators based on their contribution. Input the screened indicators into the enhanced regression tree model for fitting, obtain the calcium accumulation problem prediction model, and use the grid search method for hyperparameter optimization.

[0076] Step 3.1: Clean the calcification problem dataset to obtain a cleaned dataset containing terrain indicators and calcification problem label information.

[0077] Step 3.1.1: Check the location of missing values ​​in the dataset. If there are too many missing values ​​(more than 80%), delete the rows or columns containing missing values. For the terrain feature x, its missing values ​​are filled with the mean:

[0078] ;

[0079] in, is the number of non-missing values.

[0080] Step 3.1.2: Check and remove all duplicate rows in the terrain feature dataset.

[0081] Step 3.1.3: Check and delete outliers in the terrain feature dataset. The outlier processing process is as follows:

[0082] Assume that the terrain feature x has a mean of u and a standard deviation of If a value A value is considered an outlier if it meets any of the following conditions:

[0083] ;

[0084] ;

[0085] in, is a constant, usually 2 or 3.

[0086] Step 3.1.4: Standardize the terrain feature data processed in the previous steps.

[0087] Step 3.2: Calculate the contribution of terrain indicators to the label information of the calcification problem and select some indicators as the filtered indicators based on the ranking.

[0088] Step 3.2.1: Use the point-biserial correlation coefficient calculation formula to obtain the correlation between the terrain indicators after data cleaning and the calcification problem label information: The correlation calculation formula is:

[0089] ;

[0090] in, and are the mean values ​​of the terrain features when the calcium accumulation problem label is 1 and 0, respectively; is the standard deviation of the terrain characteristics; and are the number of samples when the calcium accumulation problem label is 1 and 0 respectively; is the total sample size.

[0091] Step 3.2.2: Use the correlation degree to construct the correlation matrix; where the correlation matrix is:

[0092] ;

[0093] in, is the correlation between the i-th terrain index and the j-th sample point.

[0094] Step 3.2.3: Obtain the eigenvalues ​​of the incidence matrix and arrange them in descending order to form an eigenvalue sequence.

[0095] Step 3.2.4: Calculate the contribution rate of each indicator based on the eigenvalue sequence using the formula:

[0096] ;

[0097] Calculate the contribution rate corresponding to each terrain indicator; where, represents the contribution rate corresponding to the i-th terrain index, represents the i-th value in the eigenvalue sequence, Represents the kth value in the eigenvalue sequence.

[0098] Step 3.2.5: Refer to the contribution rate ranking and select some indicators as the filtered indicators.

[0099] Step 3.3: Input the filtered terrain indicator sample dataset into the tree model, of which 80% is used as the training dataset and 20% is used as the validation set.

[0100] Step 3.4: Use the boosted regression tree model in the tree model and fit the data set using the boosted regression tree model to obtain a calcium accumulation prediction model; the boosted regression tree model can be expressed as follows:

[0101] ;

[0102] in, is the final integrated model, is the number of iterations, It is The output of the weak learner, in each round of iteration, a new regression tree is trained to fit the residual of the current model; The output of a weak learner It can be expressed as follows:

[0103] ;

[0104] in, is a decision tree model. It is The parameters of a decision tree.

[0105] Step 3.4.1: Initialize the model, for the dataset ,in It is a topographic feature. is the label information of the calcium accumulation problem. Initialize the initial prediction value of the model Set to the mean of all target values:

[0106] ;

[0107] Step 3.4.2: Calculate the residual. In each iteration of t, the prediction value of the current model is , residual is the actual target value The difference between and the model's current prediction:

[0108] ;

[0109] Step 3.4.3: Train a new regression tree to fit the current residual.

[0110] Step 3.4.4: Update the model and add the newly trained regression tree Weighted addition to the existing model, introducing a learning rate To control the step size of each update:

[0111] ;

[0112] in, is the learning rate, usually .

[0113] Step 3.4.5: Repeat the above steps to reduce the residual optimization model until the predetermined number of trees is reached.

[0114] Step 3.4.6: Use the grid search method to optimize the model's hyperparameters. Continuously adjust the hyperparameter values ​​and repeat the above training process to obtain the optimal calcium accumulation prediction model.

[0115] Step 3.5: Use the validation set to validate the model and obtain the accuracy verification index; repeat step 3 until the accuracy verification is qualified.

[0116] Step 3.5.1: Input the validation set into the trained calcium accumulation prediction model.

[0117] Step 3.5.2: Traverse the TPR and FPR at different classification thresholds and draw the ROC curve. The formula is as follows:

[0118] ;

[0119] ;

[0120] Among them, TP represents true positive examples, FP represents false positive examples, and FN represents false negative examples.

[0121] Step 3.5.3: Calculate the area under the ROC curve (AUC). If the AUC is low, repeat steps 3-4, reselecting variables and adjusting hyperparameters.

[0122] Step 4: Use the calcium accumulation problem prediction model to perform prediction analysis on the entire brown soil farmland area to obtain a brown soil farmland image with calcium accumulation problem prediction values.

[0123] Step 5: Calculate the optimal recall curve of the model and select the optimal threshold. Based on the threshold, dichotomize the brown soil farmland image with the predicted value of calcium accumulation problem to obtain the spatial distribution map of calcium accumulation problem and verify it.

[0124] Step 5.1: Calculate the threshold using the optimal recall curve.

[0125] Step 5.1.1: Set a range of possible thresholds , generally speaking, .

[0126] Step 5.1.2: Iterate over each threshold , calculate the recall and precision based on the model prediction results:

[0127] ;

[0128] ;

[0129] in, is at the threshold The true number of cases under is the number of false negatives, is the number of false positives.

[0130] Step 5.1.3: Based on the traversal results, draw the optimal recall rate curve and select the optimal threshold.

[0131] Step 5.2: Divide the spatial distribution image of the calcium accumulation problem into two parts according to the threshold value.

[0132] Step 5.3: Verify the obtained binary image based on some field soil profile points.

[0133] The present invention also proposes a system for identifying calcium accumulation problems in brown soil farmland, which specifically includes:

[0134] The data acquisition module is used to obtain a soil map with calcium accumulation problem label information; the soil map includes spatial location points and calcium accumulation problem label information; sample points corresponding to the spatial location of calcium accumulation problem indicators are extracted from the soil map to establish a calcium accumulation problem data set.

[0135] The data processing module is used to calculate the contribution of the calcium accumulation problem indicator to the calcium accumulation problem label information, and screen the indicator data of the calcium accumulation problem data set according to the contribution information; and select part of the data in the screened calcium accumulation problem data set as a training set.

[0136] The model module is used to input the training set data into the enhanced regression tree model to train the model and obtain a calcium accumulation problem prediction model.

[0137] The calcium accumulation problem identification module uses the calcium accumulation problem prediction model to predict the brown soil farmland image to be detected, and obtains the brown soil farmland image with the calcium accumulation problem prediction value; the brown soil farmland image with the calcium accumulation problem prediction value is divided into two parts according to the set threshold of the prediction value, and the spatial distribution map of the calcium accumulation problem is obtained according to the binary result.

[0138] Each module in the aforementioned system for identifying calcium accumulation in brown soil farmland can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0139] The present invention also provides a computer device comprising a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of an embodiment of a method for identifying calcium accumulation in brown soil farmland. The specific implementation method can be found in the method embodiment and will not be repeated here.

[0140] Furthermore, the present invention also provides a non-transitory computer-readable storage medium containing instructions, wherein a computer program is stored on the storage medium. For example, a memory containing instructions, wherein the instructions can be executed by a processor of a computer device to perform the above-mentioned method. For example, the non-transitory computer-readable storage medium can be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. When executed by the processor, the computer program can implement the steps of an embodiment of a method for identifying calcium accumulation problems in brown soil farmland. The specific implementation method can be found in the method embodiment and will not be repeated here.

[0141] Those skilled in the art will appreciate that embodiments of the present invention may provide methods, systems, or computer program products. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0142] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0143] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0145] It should be pointed out that the specific implementation methods described above can enable those skilled in the art to understand the invention more comprehensively, but do not limit the invention in any way. Therefore, although the present specification and examples have described the invention in detail, those skilled in the art should understand that the invention can still be modified or replaced by equivalents; and all technical solutions and improvements that do not deviate from the spirit and scope of the invention are included in the scope of protection of the patent for the invention. Any figure mark in the claims should not be regarded as limiting the claims involved. Any simple change or equivalent replacement of the technical solution that can be obviously obtained by any person familiar with the art within the technical scope disclosed in the present invention falls within the scope of protection of the present invention.

Claims

1. A method for identifying calcium accumulation problems in brown soil farmland, characterized in that: The following steps are involved: Obtaining a soil map with calcium accumulation problem label information; the soil map includes spatial location points and calcium accumulation problem label information; extracting sample points corresponding to spatial locations of calcium accumulation problem indicators in the soil map to establish a calcium accumulation problem dataset; Calculating the contribution of the calcium accumulation problem indicator to the calcium accumulation problem label information, and screening the indicator data of the calcium accumulation problem dataset according to the contribution information; selecting part of the data from the screened calcium accumulation problem dataset as a training set; The training set data is input into the enhanced regression tree model to train the model and obtain a calcium accumulation problem prediction model; The calcium accumulation problem prediction model is used to predict the brown soil farmland image to be detected, and the brown soil farmland image with the calcium accumulation problem prediction value is obtained; The brown soil farmland image with the predicted value of the calcium accumulation problem is divided into two parts according to the set threshold of the predicted value, and the spatial distribution map of the calcium accumulation problem is obtained according to the result of the two-part division.

2. The method for identifying calcium accumulation problems in brown soil farmland according to claim 1, characterized in that: The calculating of the contribution of the calcium accumulation problem indicator to the calcium accumulation problem label information, and screening the indicator data of the calcium accumulation problem dataset according to the contribution information, specifically includes the following steps: The correlation coefficient calculation formula is used to obtain the correlation between the indicator and the calcium accumulation problem label information. The correlation calculation formula is: ； in, and are the mean values ​​of the terrain features when the calcium accumulation problem label is 1 and 0, respectively; is the standard deviation of the terrain characteristics; and are the number of samples when the calcium accumulation problem label is 1 and 0 respectively; is the total sample size; Use the correlation degree to construct the correlation matrix; where the correlation matrix is: ； in, is the correlation between the i-th terrain index and the j-th sample point; Obtain the eigenvalues ​​of the correlation matrix and arrange the eigenvalues ​​in descending order to form an eigenvalue sequence; The contribution rate of each indicator is calculated based on the eigenvalue sequence using the formula: ； in, represents the contribution rate corresponding to the i-th terrain index, represents the i-th value in the eigenvalue sequence, represents the kth value in the eigenvalue sequence; Refer to the contribution rate ranking to filter the data.

3. The method for identifying calcium accumulation problems in brown soil farmland according to claim 1, characterized in that: The method further includes selecting data from the screened calcium accumulation problem dataset as a validation set, and inputting the validation set data into a validation model, specifically including the following steps: Input the validation set into the trained calcium accumulation problem prediction model; Traverse the true positive rate TPR and false positive rate FPR at different classification thresholds and draw the ROC curve. The formula is as follows: ； ； Among them, TP represents true positive, FP represents false positive, and FN represents false negative; Calculate the area under the ROC curve, or AUC. If the AUC is lower than the set threshold, reselect the model variables and hyperparameters.

4. The method for identifying calcium accumulation problems in brown soil farmland according to claim 1, characterized in that: The threshold value of the prediction value is obtained by the following steps: Use the optimal recall rate curve to calculate the threshold and set multiple thresholds , traverse each threshold , calculate the recall and precision based on the model prediction results: ； ； in, is at the threshold The true number of cases under is the number of false negatives, is the number of false positives; According to the traversal results, draw the optimal recall rate curve and select the threshold.

5. The method for identifying calcium accumulation problems in brown soil farmland according to claim 1, characterized in that: The method also includes supplementing sampling for areas with insufficient data when there are insufficient sample points in the soil map, specifically: setting a total number of samples n, and randomly sampling with the patch area as the weight, and each patch The number of random sampling points The calculation formula is as follows: ； in, Plaque The number of sampling points; Plaque area; is the total area of ​​all patches; is the total number of samples.

6. The method for identifying calcium accumulation problems in brown soil farmland according to claim 1, characterized in that: The calcium accumulation problem index specifically includes a terrain index, a climate index or a soil parent material index; each sample point corresponds to a plurality of calcium accumulation problem index values.

7. A system for identifying calcium accumulation problems in brown soil farmland, characterized in that: include: A data acquisition module is configured to acquire a soil map having calcium accumulation problem label information; the soil map includes spatial location points and calcium accumulation problem label information; sample points corresponding to spatial locations of calcium accumulation problem indicators are extracted from the soil map to establish a calcium accumulation problem dataset; a data processing module, configured to calculate the contribution of the calcium accumulation problem indicator to the calcium accumulation problem label information, filter the indicator data of the calcium accumulation problem dataset according to the contribution information; and select part of the data from the filtered calcium accumulation problem dataset as a training set; The model module is used to input the training set data into the enhanced regression tree model to train the model and obtain a calcium accumulation problem prediction model; The calcium accumulation problem identification module uses the calcium accumulation problem prediction model to predict the brown soil farmland image to be detected, and obtains the brown soil farmland image with the calcium accumulation problem prediction value; The brown soil farmland image with the predicted value of the calcium accumulation problem is divided into two parts according to the set threshold of the predicted value, and the spatial distribution map of the calcium accumulation problem is obtained according to the result of the two-part division.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is loaded into a processor, it can execute the steps of the method according to any one of claims 1 to 6.

Images