Landslide disaster risk assessment method based on HistGB reinforcement model

Abstract

The invention provides a landslide disaster risk assessment method based on a HistGB reinforcement model, and belongs to the field of landslide disaster assessment, and the method comprises the steps: preprocessing obtained various types of data of a landslide disaster research area, exporting an evaluation factor original value corresponding to a landslide point, obtaining an original data set, importing the original data set into the HistGB reinforcement model for training, and obtaining a landslide disaster risk assessment result. The method comprises the following steps: firstly, selecting an adaptive enhancement model, performing grid search to obtain a HistGB enhancement model of an optimal parameter, and performing adaptive enhancement integration by using the adaptive enhancement model as a meta learning device and the HistGB enhancement model of the optimal parameter as a base learning device to obtain an integrated model; substituting the training set into the integrated model to perform training simulation, importing the grid points into the trained integrated model to perform landslide disaster susceptibility analysis, and outputting a landslide disaster susceptibility prediction map; according to the method, the problems of low prediction performance, low accuracy and low optimal parameter combination searching efficiency in existing different machine learning models are solved.

Description

Technical Field

[0001] The invention belongs to the field of landslide disaster assessment, and in particular relates to a landslide disaster risk assessment method based on a HistGB enhanced model. Background Art

[0002] Due to the frequent occurrence and severity of landslide disasters, researchers are constantly exploring effective prediction methods. Traditional machine learning models face certain challenges when dealing with complex spatial relationships. HistGB, as a new gradient boosting algorithm, can effectively enhance the model's adaptability to data.

[0003] By combining different machine learning models, we can take full advantage of the advantages of each model, such as the interpretability of decision trees and the boundary optimization capabilities of support vector machines. In order to overcome these shortcomings, existing technologies often use an integration method of multiple machine learning models, combined with search algorithms and optimization strategy frameworks to improve the performance of the model. Search algorithms can assist machine learning models to find the best parameter combination in a huge parameter space, thereby improving the model's ability to fit and generalize data, thereby improving prediction performance and accuracy. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a landslide hazard risk assessment method based on the HistGB enhanced model, which solves the problems of low prediction performance, low accuracy and low efficiency in finding the optimal parameter combination in different existing machine learning models.

[0005] In order to achieve the above objectives, the technical solution adopted by the present invention is as follows: On the one hand, the present invention provides a landslide disaster risk assessment method based on the HistGB enhanced model, comprising the following steps:

[0006] S1. Preprocessing the acquired multi-class data of the landslide hazard study area, and deriving the original values ​​of all initial evaluation factors corresponding to all landslide points in the landslide hazard study area through the obtained raster data of the landslide hazard study area to obtain the original data set;

[0007] S2, importing the original data set into the HistGB enhancement model for training, using the grid search algorithm and using the area under the curve as the training index to search for the optimal parameters of the HistGB enhancement model, and obtaining the HistGB enhancement model with the optimal parameters;

[0008] S3, using the adaptive enhancement model as a meta-learner, and taking the HistGB enhancement model with optimal parameters as a base learner for adaptive enhancement integration, to obtain an adaptive enhancement-HistGB integration model;

[0009] S4, processing the original data set to obtain an optimized data set, and using the optimized data set to perform training simulation on the adaptive enhancement-HistGB integrated model to obtain a trained adaptive enhancement-HistGB integrated model;

[0010] S5. Import evaluation indicators to test the accuracy of the trained adaptive enhancement-HistGB integrated model, and import all grid points in the landslide hazard study area into the trained adaptive enhancement-HistGB integrated model to conduct landslide susceptibility analysis. According to the results of the landslide susceptibility analysis, the landslide hazard study area is divided to obtain a landslide susceptibility prediction map.

[0011] The beneficial effects of the present invention are as follows: the present invention obtains multi-source data of a landslide disaster research area, processes the original data, uses a software multi-value extraction to point tool, extracts the original data table of all evaluation factors of a sample set according to the landslide point data, and packages and constructs the original data set; uses a grid search algorithm to optimize the HistGB model parameters, and then performs adaptive enhancement integration on the optimized HistGB model, thereby improving the accuracy of the adaptive enhancement-HistGB integration model; then substitutes the sample set into the adaptive enhancement-HistGB integration model for training, thereby providing an efficient adaptive enhancement-HistGB integration model; then imports the values ​​of all grid points into the trained model to perform landslide disaster susceptibility analysis, grades the research area, and outputs a landslide disaster susceptibility prediction map, thereby improving the performance index of landslide disaster risk assessment to a high level.

[0012] Furthermore, the S1 comprises the following steps:

[0013] S101. Obtain multiple types of data on the landslide hazard study area;

[0014] S102, unifying the spatial resolution and coordinate system of the multi-category data, and converting the multi-category data after the unified coordinate system into layers of the same grid size by resampling, to obtain converted raster data;

[0015] S103, randomly generating non-landslide points outside a preset diameter of the landslide points according to a preset sample ratio of landslide points to non-landslide points;

[0016] S104, according to the converted raster data, using the software to extract to point tool, and according to the landslide point data, by extracting the original data table of all initial evaluation factors, exporting the original values ​​of all initial evaluation factors, and obtaining the original data set.

[0017] Furthermore, the S102 includes the following steps:

[0018] S1021, importing multiple types of data into the software, unifying the spatial resolution and coordinate system of the multiple types of data based on the data management tool - projection and transformation - definition of projection steps, wherein the first coordinate system is the 1984 World Geodetic Coordinate System - Transverse Mercator - Northern Hemisphere Zone 46;

[0019] S1022. According to the data management tool - raster - raster processing - resampling steps in the software, resample the multi-category data after the unified coordinate system, select the elevation raster as the reference image, set the input raster image to the raster image to be resampled, set the output raster dataset to new raster 1, set the output pixel to the same elevation raster as the layer, set the resampling to nearest, and obtain the converted raster data.

[0020] The beneficial effect of the above further scheme is that the present invention performs grid processing on the acquired multiple types of data to obtain grids with relevant settings, thereby improving the effectiveness and accuracy of the acquired data and increasing the processing speed of the enhanced model on the data.

[0021] Furthermore, the S2 comprises the following steps:

[0022] S201, import the original data set into the HistGB reinforcement model for training, and use the grid search class in the scikit-learn library to perform grid search;

[0023] S202, using the fit method to use the area under the curve as a training indicator, searching for optimal parameters of the HistGB enhancement model, obtaining an optimal parameter combination, and obtaining a HistGB enhancement model with optimal parameters according to the optimal parameter combination.

[0024] Furthermore, the S201 includes the following steps:

[0025] S2011. Create a base learner containing an instance of the HistGB reinforcement model and define a parameter grid containing candidate values ​​for the maximum number of iterations and the learning rate;

[0026] S2012. Create a grid search instance, pass in the HistGB classifier, parameter grid, cross-validation fold, scoring criteria, and parallel processing parameters, and use the grid search class to perform a grid search on the passed in parameters.

[0027] The beneficial effect of the above further scheme is that the present invention utilizes the fit method and uses the area under the curve as a training indicator, thereby improving the efficiency of the machine learning model in finding the optimal parameter combination.

[0028] Furthermore, the specific steps of S3 are as follows:

[0029] The HistGB reinforcement model with optimal parameters is used as the base learner, and the adaptive reinforcement classifier in the scikit-learn library is used to call the adaptive reinforcement model. The adaptive reinforcement model is used as the meta-learner to perform adaptive reinforcement integration on the HistGB reinforcement model with optimal parameters to obtain the adaptive reinforcement-HistGB integration model.

[0030] Furthermore, the specific steps of S4 are as follows:

[0031] The original data set is processed, the evaluation factor values ​​except ID and attribute data Y are set to X, and the attribute data Y is set to training target Y to obtain the optimized data set;

[0032] The optimized data set is randomly shuffled according to the preset set ratio and divided into a training set and a test set. The training set is substituted into the adaptive enhancement-HistGB integrated model for training simulation to obtain the trained adaptive enhancement-HistGB integrated model.

[0033] The beneficial effect of the above further scheme is: the present invention uses the HistGB reinforcement model as a base learner, which effectively enhances the adaptability of the model to data and improves the predictive performance of the machine learning model.

[0034] Furthermore, the specific steps of S5 are as follows:

[0035] S501, using the test set to draw a receiver operating characteristic curve, obtain the area under the curve value, and import the area under the curve function code into the adaptive enhancement-HistGB integrated model, and use the area under the curve value to test the accuracy of the trained adaptive enhancement-HistGB integrated model;

[0036] S502, using the trained adaptive enhancement-HistGB integrated model to predict the landslide susceptibility of the study area, outputting the susceptibility probability value corresponding to each grid unit, and arranging the obtained susceptibility probability values ​​in ascending order;

[0037] S503: using the natural breakpoint method to classify the susceptibility probability values, and outputting a landslide disaster susceptibility prediction map.

[0038] In order to achieve the above object, according to a second aspect of the present invention, there is provided an electronic device, characterized in that it comprises a processor and a memory for storing executable instructions of the processor;

[0039] The processor is configured to execute the above-mentioned landslide hazard risk assessment method.

[0040] In order to achieve the above-mentioned purpose, according to the third aspect of the present invention, a computer-readable storage medium is provided, characterized in that a plurality of classification programs are stored on the computer-readable storage medium, and the plurality of classification programs are used to be called by a processor and execute the above-mentioned landslide hazard risk assessment method.

[0041] The beneficial effect of the above further scheme is: the present invention obtains the area under the curve by drawing the receiver operating characteristic curve, and uses the area under the curve to improve the prediction performance of the machine learning model and the accuracy of the machine learning model prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 The figure is a flow chart of the method of the present invention.

[0043] Figure 2 Schematic diagram of the ROC curve in this embodiment.

[0044] Figure 3 Schematic diagram of performance indicators of each model in this embodiment.

[0045] Figure 4 This is a landslide disaster susceptibility prediction map in this embodiment. DETAILED DESCRIPTION

[0046] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0047] Before describing this embodiment, the following terms are explained:

[0048] AdaBoost: Adaptive Boosting;

[0049] ArcGIS: geospatial platform;

[0050] ROC curve: receiver operating characteristic curve;

[0051] AUC: area under the curve;

[0052] NDVI: Normalized Difference Vegetation Index;

[0053] DEM: Digital Elevation Model;

[0054] TWI: Topographic Wetness Index.

[0055] Example 1

[0056] like Figure 1 As shown, the present invention provides a landslide disaster risk assessment method based on the HistGB enhanced model, and its implementation method is as follows:

[0057] S1. Preprocess the multi-category data of the landslide hazard study area. Through the obtained raster data of the landslide hazard study area, derive the original values ​​of all initial evaluation factors corresponding to all landslide points in the landslide hazard study area to obtain the original data set. The specific steps are as follows:

[0058] S101. Obtain multiple types of data on the landslide hazard study area;

[0059] S102, unifying the spatial resolution and coordinate system of the multi-class data, and converting the multi-class data after the unified coordinate system into layers of the same grid size by resampling to obtain converted raster data. The specific steps are as follows:

[0060] S1021, importing multiple types of data into the software, unifying the spatial resolution and coordinate system of the multiple types of data based on the data management tool - projection and transformation - definition of projection steps, wherein the first coordinate system is the 1984 World Geodetic Coordinate System - Transverse Mercator - Northern Hemisphere Zone 46;

[0061] S1022, according to the data management tool-raster-raster processing-resampling step in the software, resample the multi-class data after the unified coordinate system, select the elevation grid as the reference image, set the input grid image to the grid image to be resampled, set the output grid dataset to a new grid, set the output pixel to the same elevation grid as the layer, and set the resampling to the nearest, so as to obtain the converted raster data;

[0062] S103, randomly generating non-landslide points outside a preset diameter of the landslide points according to a preset sample ratio of landslide points to non-landslide points;

[0063] S104, according to the converted raster data, using the software to extract to point tool, and according to the landslide point data, by extracting the original data table of all initial evaluation factors, exporting the original values ​​of all initial evaluation factors, and obtaining the original data set.

[0064] In this embodiment, multiple types of data of the landslide disaster research area in Yuanling County, Hunan Province are obtained;

[0065] Preprocess the multi-class data of the landslide hazard study area, and randomly generate non-landslide points at a preset diameter of 1 km outside the landslide points according to the preset sample ratio of 1:1 between landslide points and non-landslide points;

[0066] Before processing the multi-class data, the coordinate system of the collected multi-class data needs to be converted into WGS_1984_UTM_Zone_46N (World Geodetic Coordinate System of 1984 - Transverse Mercator - Zone 46 of the Northern Hemisphere). Therefore, the multi-class data is imported into ArcGIS, and the coordinate system of the multi-class data is unified based on Data Management Tool—Projections and Transformations—Define Projection.

[0067] Import the multi-category data of the unified coordinate system into ArcGIS, resample the multi-category data of the unified coordinate system based on Data Management Tools—Raster—Raster Processing—Resample, select the elevation raster as the reference image, set Input Raster to the raster image to be resampled, set Output Raster Dataset to "newraster1", that is, the raster image after resampling, set Output Cell Size to "Same as layer (same as layer) elevation raster", set Resample to "NEAREST", click OK to get the converted raster data;

[0068] Based on the converted raster data and combined with the multi-value extraction to point tool in ArcGIS 10.5 software, the original data table of all initial evaluation factors was extracted according to the landslide point data, and the original numerical value export of the initial evaluation factors was completed.

[0069] S2. Import the original data set into the HistGB enhanced model for training. Use the grid search algorithm and the area under the curve as the training index to search for the optimal parameters of the HistGB enhanced model to obtain the HistGB enhanced model with the optimal parameters. The specific steps are as follows:

[0070] S201. Import the original data set into the HistGB enhanced model for training. Use the grid search class in the scikit-learn library to perform grid search. The specific steps are as follows:

[0071] S2011. Create a base learner containing an instance of the HistGB reinforcement model and define a parameter grid containing candidate values ​​for the maximum number of iterations and the learning rate;

[0072] S2012, create a grid search instance, pass in the HistGB classifier, parameter grid, cross-validation fold, scoring criteria, and parallel processing parameters, and use the grid search class to perform a grid search on the passed in parameters;

[0073] S202, using the fit method to use the area under the curve as a training indicator, searching for optimal parameters of the HistGB enhancement model, obtaining an optimal parameter combination, and obtaining a HistGB enhancement model with optimal parameters according to the optimal parameter combination.

[0074] In this embodiment, the data set is imported into the HistGB model for training, and the AUC is used as the training indicator. The grid search algorithm is used to search for the optimal parameters of the HistGB model to obtain the HistGB model with the optimal parameters, as follows:

[0075] Use the GridSearchCV (grid search) class in the scikit-learn library to perform a grid search to optimize the parameters of the HistGB model. Code: from sklearn.model_selection import GridSearchCV;

[0076] The grid search algorithm is used to search for the best parameters of the HistGB model. AUC is used as the evaluation index to perform grid search on the two parameters of max_iter (maximum number of iterations) and learning_rate (learning rate) to obtain the best parameter combination; the parameter ranges of max_iter (maximum number of iterations) and learning_rate (learning rate) are (50, 600) and (0.01, 1) respectively. The best parameters after optimization using the grid search algorithm are max_iter and learning_rate (learning rate) are 230 and 0.6 respectively, as follows:

[0077] Create a HistGBClassifier instance as a base learner and create a HistGB classifier instance; code: HistGB = HistGBClassifier(random_state = 42);

[0078] Define a parameter grid param_grid, containing a series of candidate values ​​of max_iter and learning_rate; code: param_grid = {'max_iter': (50, 600), 'learning_rate': (0.1, 1)};

[0079] Create a GridSearchCV (grid search) instance, passing in the HistGB classifier, parameter grid, cross-validation fold (cv = 5), scoring criterion (scoring = 'auc'), and parallel processing parameters (n_jobs = -1); code: grid_search = GridSearchCV (param_grid = param_grid, cv = 5, scoring = 'auc', n_jobs = -1);

[0080] Use the fit method to perform grid search on the training set and find the best parameter combination through the AUC evaluation index; code: grid_search.fit(X_train,y_train);

[0081] The best parameters found and the corresponding best model score are output; Output the best parameters; code: print("Best parameters found:",grid_search.best_params_); Output the score of the best model; code: print("Best model score:",grid_search.best_score_);

[0082] A HistGB enhanced model with optimal parameters was created using the optimal parameters, and predictions were made on the test set to calculate the AUC; code: y_pred = best_model.predict(X_test); The accuracy of the HistGB enhanced model with optimal parameters on the test set was calculated; code: test_auc = (y_pred == y_test).mean(), print("Test set auc of best model:",test_auc).

[0083] S3. Using the adaptive enhancement model as a meta-learner, the HistGB enhancement model with optimal parameters is used as a base learner for adaptive enhancement integration to obtain an adaptive enhancement-HistGB integration model, as follows:

[0084] The HistGB reinforcement model with optimal parameters is used as the base learner, and the adaptive reinforcement classifier in the scikit-learn library is used to call the adaptive reinforcement model. The adaptive reinforcement model is used as the meta-learner to perform adaptive reinforcement integration on the HistGB reinforcement model with optimal parameters to obtain the adaptive reinforcement-HistGB integration model.

[0085] In this embodiment, the Adaboost model is used as the meta-learner, and the HistGB model with optimized parameters is used as the base learner to obtain the AdaBoost integrated model with the optimized HistGB as the base learner, namely Adaboost-HistGB, which is as follows:

[0086] Use the AdaBoostClassifier in the scikit-learn library to call the AdaBoost model and perform adaptive boost integration on the optimized HistGB model, from sklearn.ensemble importAdaBoostClassifier, the expression is AdaBoostClassifie(HistGBClassifier(max_iter=230,learning_rate=0.6)).

[0087] S4. Process the original data set to obtain an optimized data set, and use the optimized data set to perform training simulation on the adaptive enhancement-HistGB integrated model to obtain a trained adaptive enhancement-HistGB integrated model. The specific steps are as follows:

[0088] The original data set is processed, the evaluation factor values ​​except ID and attribute data Y are set to X, and the attribute data Y is set to training target Y to obtain the optimized data set;

[0089] The optimized data set is randomly shuffled according to the preset set ratio and divided into a training set and a test set. The training set is substituted into the adaptive enhancement-HistGB integrated model for training simulation to obtain the trained adaptive enhancement-HistGB integrated model.

[0090] In this embodiment, the data set is processed based on Python software, the numerical value of the evaluation factor except the ID and attribute data Y is set to X, and the attribute data Y is the training target Y (positive sample is 1, negative sample is 0), and the optimized data set is obtained. The optimized data set is randomly shuffled according to the preset set ratio of 7:3, and divided into a training set and a test set, and the training set is substituted into the AdaBoost-HistGB integrated model for training simulation.

[0091] Import the evaluation index, test the accuracy of the trained adaptive enhancement-HistGB integrated model, and import all grid points in the landslide hazard study area into the trained adaptive enhancement-HistGB integrated model to analyze the susceptibility of landslide disasters. According to the results of the landslide hazard susceptibility analysis, divide the landslide hazard study area to obtain the landslide hazard susceptibility prediction map. The specific steps are as follows:

[0092] S501, using the test set to draw a receiver operating characteristic curve, obtain the area under the curve value, and import the area under the curve function code into the adaptive enhancement-HistGB integrated model, and use the area under the curve value to test the accuracy of the trained adaptive enhancement-HistGB integrated model;

[0093] S502, using the trained adaptive enhancement-HistGB integrated model to predict the landslide susceptibility of the study area, outputting the susceptibility probability value corresponding to each grid unit, and arranging the obtained susceptibility probability values ​​in ascending order;

[0094] S503: using the natural breakpoint method to classify the susceptibility probability values, and outputting a landslide disaster susceptibility prediction map.

[0095] In this embodiment, the test set data is used to verify the model accuracy and draw the ROC curve to obtain the following Figure 2 The area under the curve AUC value shown in the figure shows that the AdaBoost ensemble model with HistGB as the base learner can significantly increase the AUC value, and the AUC reaches 0.8396, which is better than HistGB's 0.8243 and Adaboost's 0.6858. At the same time, the performance tests of the four indicators of AUC, ACC, Precision and F1 were also carried out, and the results are as follows Figure 3 The schematic diagram of the four performance indicators shown in the figure shows that the Adaboost-HistGB ensemble model has the best performance in each performance indicator.

[0096] The constructed and trained Adaboost-HistGB integrated model is used to predict the landslide susceptibility of the study area, and the susceptibility probability value corresponding to each grid unit is output, and the obtained susceptibility probability values ​​are arranged in ascending order;

[0097] The natural breakpoint method is used to divide the probability value of susceptibility into 5 levels: lower, low, medium, higher and high. The susceptibility levels of lower, low, medium, higher and high are divided and judged according to the actual situation. Figure 4 The landslide susceptibility prediction diagram is shown. In general, the landslide susceptibility evaluation performance of the model of the present invention is better. On the one hand, the extremely low, low, medium, high and extremely high susceptibility areas of the model account for 1.4%, 25.0%, 36.7%, 25.5% and 11.7% of the total area of ​​the study area respectively. In the landslide geological disasters that have occurred, the landslide frequency ratio reaches 3.78; on the other hand, the AUC value of the model is 0.8396, indicating that the prediction effect of the model is excellent.

[0098] Example 2

[0099] In this embodiment, the present invention provides a landslide hazard risk assessment method based on the HistGB enhanced model, which has been successfully applied to the landslide disaster prediction in Yuanling County, Hunan Province. With its robustness and autonomous learning ability, it provides a new and efficient model for the landslide susceptibility evaluation in Yuanling County. By optimizing the parameters of the HistGB model search algorithm and further adaptively enhancing the integration, the accuracy of the geological disaster susceptibility assessment results is improved.

[0100] In this embodiment, the present invention takes Yuanling County as the research area, integrates the local geological bureau data, the Resource and Environmental Science and Data Center of the Chinese Academy of Sciences, and Landslides_SL to obtain a total of 289 landslides, and uses the code to randomly divide them into two groups of training data and verification data, with a preset ratio of 7:3. In this study, environmental factors were selected according to professional knowledge, and 16 environmental factors were studied: elevation, slope, aspect, surface cutting coefficient, profile curvature, elevation variation coefficient, ground roughness, curvature, TWI, river distance, distance from the road, distance from the fault, normalized difference vegetation index, land use type, lithology and rainfall. The digital elevation model data comes from the geospatial data cloud, and the environmental factors directly obtained from the DEM are elevation, slope, aspect, surface cutting coefficient, profile curvature, elevation variation coefficient, ground roughness, curvature and TWI. Among them, lithology and fault distance come from the geological cloud of the China Geological Survey, road and hydrological data, rainfall, NDVI come from the geospatial data cloud, and land use type data comes from the data published by Wuhan University.

Claims

1. A landslide hazard risk assessment method based on the HistGB enhanced model, characterized in that: The following steps are involved: S1. Preprocessing the acquired multi-class data of the landslide hazard study area, and deriving the original values ​​of all initial evaluation factors corresponding to all landslide points in the landslide hazard study area through the obtained raster data of the landslide hazard study area to obtain the original data set; S2, importing the original data set into the HistGB enhancement model for training, using the grid search algorithm and using the area under the curve as the training index to search for the optimal parameters of the HistGB enhancement model, and obtaining the HistGB enhancement model with the optimal parameters; S3, using the adaptive enhancement model as a meta-learner, and taking the HistGB enhancement model with optimal parameters as a base learner for adaptive enhancement integration, to obtain an adaptive enhancement-HistGB integration model; S4, processing the original data set to obtain an optimized data set, and using the optimized data set to perform training simulation on the adaptive enhancement-HistGB integrated model to obtain a trained adaptive enhancement-HistGB integrated model; S5. Import evaluation indicators to test the accuracy of the trained adaptive enhancement-HistGB integrated model, and import all grid points in the landslide hazard study area into the trained adaptive enhancement-HistGB integrated model to conduct landslide susceptibility analysis. According to the results of the landslide susceptibility analysis, the landslide hazard study area is divided to obtain a landslide susceptibility prediction map.

2. The landslide hazard risk assessment method based on the HistGB enhanced model according to claim 1 is characterized in that: The S1 comprises the following steps: S101. Obtain multiple types of data on the landslide hazard study area; S102, unifying the spatial resolution and coordinate system of the multi-category data, and converting the multi-category data after the unified coordinate system into layers of the same grid size by resampling, to obtain converted raster data; S103, randomly generating non-landslide points outside a preset diameter of the landslide points according to a preset sample ratio of landslide points to non-landslide points; S104, according to the converted raster data, using the software to extract to point tool, and according to the landslide point data, by extracting the original data table of all initial evaluation factors, exporting the original values ​​of all initial evaluation factors, and obtaining the original data set.

3. The landslide disaster risk assessment method based on the HistGB enhanced model according to claim 2 is characterized in that: The S102 comprises the following steps: S1021, importing multiple types of data into the software, unifying the spatial resolution and coordinate system of the multiple types of data based on the data management tool - projection and transformation - definition of projection steps, wherein the first coordinate system is the 1984 World Geodetic Coordinate System - Transverse Mercator - Northern Hemisphere Zone 46; S1022. According to the data management tool - raster - raster processing - resampling steps in the software, resample the multi-category data after the unified coordinate system, select the elevation raster as the reference image, set the input raster image to the raster image to be resampled, set the output raster dataset to a new raster, set the output pixel to the same elevation raster as the layer, set the resampling to the nearest, and obtain the converted raster data.

4. The landslide disaster risk assessment method based on the HistGB enhanced model according to claim 1 is characterized in that: The S2 comprises the following steps: S201, import the original data set into the HistGB reinforcement model for training, and use the grid search class in the scikit-learn library to perform grid search; S202, using the fit method to use the area under the curve as a training indicator, searching for optimal parameters of the HistGB enhancement model, obtaining an optimal parameter combination, and obtaining a HistGB enhancement model with optimal parameters according to the optimal parameter combination.

5. The landslide disaster risk assessment method based on the HistGB enhanced model according to claim 4 is characterized in that: The S201 includes the following steps: S2011. Create a base learner containing an instance of the HistGB reinforcement model and define a parameter grid containing candidate values ​​for the maximum number of iterations and the learning rate; S2012. Create a grid search instance, pass in the HistGB classifier, parameter grid, cross-validation fold, scoring criteria, and parallel processing parameters, and use the grid search class to perform a grid search on the passed in parameters.

6. The landslide disaster risk assessment method based on the HistGB enhanced model according to claim 1 is characterized in that: The specific steps of S3 are as follows: The HistGB reinforcement model with optimal parameters is used as the base learner, and the adaptive reinforcement classifier in the scikit-learn library is used to call the adaptive reinforcement model. The adaptive reinforcement model is used as the meta-learner to perform adaptive reinforcement integration on the HistGB reinforcement model with optimal parameters to obtain the adaptive reinforcement-HistGB integration model.

7. The landslide disaster risk assessment method based on the HistGB enhanced model according to claim 1 is characterized in that: The specific steps of S4 are as follows: The original data set is processed, the evaluation factor values ​​except ID and attribute data Y are set to X, and the attribute data Y is set to training target Y to obtain the optimized data set; The optimized data set is randomly shuffled according to the preset set ratio and divided into a training set and a test set. The training set is substituted into the adaptive enhancement-HistGB integrated model for training simulation to obtain the trained adaptive enhancement-HistGB integrated model.

8. The landslide disaster risk assessment method based on the HistGB enhanced model according to claim 7 is characterized in that: The specific steps of S5 are as follows: S501, using the test set to draw a receiver operating characteristic curve, obtain the area under the curve value, and import the area under the curve function code into the adaptive enhancement-HistGB integrated model, and use the area under the curve value to test the accuracy of the trained adaptive enhancement-HistGB integrated model; S502, using the trained adaptive enhancement-HistGB integrated model to predict the landslide susceptibility of the study area, outputting the susceptibility probability value corresponding to each grid unit, and arranging the obtained susceptibility probability values ​​in ascending order; S503: using the natural breakpoint method to classify the susceptibility probability values, and outputting a landslide disaster susceptibility prediction map.

9. An electronic device, characterized in that: comprising a processor and a memory for storing executable instructions of the processor; The processor is configured to implement the landslide hazard risk assessment method according to any one of claims 1 to 8 by executing executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of classification programs, and the plurality of classification programs are used to be called by a processor and execute the landslide hazard risk assessment method according to any one of claims 1 to 8.

Images