Landslide susceptibility mapping method and device and medium

Abstract

The invention relates to the field of digital mapping, and discloses a landslide susceptibility mapping method and device and a medium, and the method comprises the steps: obtaining multi-source remote sensing data and historical landslide data, and making a disaster-inducing factor data set and a landslide sample data set; inputting all landslide sample data sets into an AGNES clustering algorithm and a VIIQ feature optimization strategy module to obtain an optimal feature combination; dividing the optimized data features into a training set and a test set, inputting the training set and the test set into a machine learning classifier and a deep learning classifier, and performing model precision evaluation to obtain a preliminary landslide susceptibility map; inputting the landslide susceptibility map into the Blending heterogeneous integrated model to obtain a final landslide susceptibility mapping result; the integrated model is deeply explained in combination with an SHAP algorithm, and a landslide susceptibility result graph is optimized; according to the method, the landslide susceptibility can be predicted more effectively, and a scientific basis is provided for risk assessment, early warning and prevention of geological disasters.

Description

Technical Field

[0001] The invention relates to the field of digital mapping, and in particular to a landslide susceptibility mapping method, equipment and medium. Background Art

[0002] Among natural disasters, landslides occur much more frequently than other types of geological disasters and are extremely destructive. Among them, earthquake-induced landslides are often extremely sudden, posing a huge threat to people's survival and development. Earthquake-induced landslides not only cause direct damage, but may also cause secondary disasters such as dam breaches and floods, further exacerbating the impact of the disaster.

[0003] In order to assist relevant departments in carrying out reasonable and effective disaster prevention and mitigation work, landslide geological disaster susceptibility mapping has become an important research method. By studying the environmental factors related to landslides, the probability of landslides occurring again in similar environments is analyzed, and a landslide geological disaster susceptibility map is drawn. Based on the output landslide susceptibility zoning layer, the danger of geological disasters in the region and the possible impact range can be judged.

[0004] Data-driven models are based on objective and complex geographic environment data (such as elevation, geology, precipitation) and comprehensive and detailed landslide history events, which reduce the influence of subjective factors and uncertainty. Currently, the main types of models used are traditional statistical methods and machine learning algorithms. Traditional statistical models pay more attention to the linear relationship between landslide characteristic factors, while the relationship between landslide events and landslide characteristic factors is mainly nonlinear. Machine learning and deep learning algorithms can better construct nonlinear relationships between landslide characteristic factors, effectively capture and simulate the complex mechanism of landslide occurrence, and their prediction accuracy is significantly improved. Considering the complexity of landslide susceptibility mapping, it is difficult for a single machine learning algorithm to fully and accurately reflect the intrinsic relationship between landslide influencing factors and actual catastrophic events in all scenarios.

[0005] In addition, the causal mechanism of landslides is complex, and the regional characteristics of various hazard factors have a significant impact on the distribution of landslides. At present, the research on landslide susceptibility mainly focuses on the selection and optimization of models, while there is relatively little in-depth research on the prediction principles and algorithm details of the models. Previous methods emphasized the correlation between landslide characteristic factors and landslide events, and insufficient consideration was given to the impact of the spatiotemporal characteristics and spatial heterogeneity of the geographical environment on landslide events.

[0006] Therefore, in landslide susceptibility mapping technology, how to effectively utilize spatiotemporal characteristics and consider spatial heterogeneity are technical issues that need to be solved urgently. Summary of the invention

[0007] The purpose of the present invention is to propose a landslide susceptibility mapping method to solve the technical problems of how to effectively utilize spatiotemporal characteristics and how to consider spatial heterogeneity.

[0008] Specifically, the present invention provides a method for mapping landslide susceptibility, comprising the following steps:

[0009] S1: Acquire multi-source remote sensing data and historical landslide data to produce hazard factor datasets and landslide sample datasets;

[0010] S2: Input all landslide sample data sets into the AGNES clustering algorithm and VIIQ feature optimization strategy module to obtain the optimal feature combination;

[0011] S3: Divide the optimized data features into training sets and test sets, input them into machine learning and deep learning classifiers, evaluate the model accuracy, and obtain a preliminary landslide susceptibility map;

[0012] S4: Input the preliminary landslide susceptibility map of S3 into the Blending heterogeneous integration model to obtain the final landslide susceptibility mapping result;

[0013] S5: The Blending heterogeneous integrated model of S4 is combined with the SHAP algorithm to further interpret the integrated model and optimize the landslide susceptibility result map.

[0014] A storage medium stores instructions and data for implementing a landslide susceptibility mapping method.

[0015] A landslide susceptibility mapping device comprises: a processor and the storage medium; the processor loads and executes instructions and data in the storage medium to implement a landslide susceptibility mapping method.

[0016] The beneficial effects provided by the present invention are:

[0017] (1) The AGNES clustering algorithm and VIIQ (VIF-IGR-Importance-Qvalue) feature optimization strategy module provided by the present invention are helpful to consider and deal with the spatial heterogeneity problem in landslide susceptibility evaluation. The AGNES clustering method can capture the characteristics of the local area by dividing the global grid unit of the study area into several local sub-areas, thereby laying the foundation for selecting the optimal combination of landslide condition factors for each sub-area. The VIIG feature combination method is used to screen the optimal spatial features of each sub-area, reduce feature redundancy and improve the efficiency of landslide susceptibility evaluation. Therefore, through the AGNES clustering algorithm and the VIIQ (VIF-IGR-Importance-Qvalue) feature optimization strategy module, the spatial characteristics of different disaster factors can be better understood in an all-round way to better analyze the landslide susceptibility in the region.

[0018] (2) The present invention predicts landslide events by constructing machine learning and deep learning models, covering a variety of advanced classifiers to improve the accuracy and generalization ability of landslide susceptibility assessment. Specifically, the machine learning models include decision trees, random forests (RF), support vector machines (SVM), gradient boosted regression trees (GBRT), and K nearest neighbors (KNN), while the deep learning models include artificial neural networks (ANN), convolutional neural networks (CNN), and recurrent neural networks (RNN). These models perform well in processing the optimal feature combinations obtained by the AGNES clustering algorithm and the VIIQ (VIF-IGR-Importance-Qvalue) feature optimization strategy module, and can further perform classification tasks. In addition, the present invention constructs a heterogeneous integrated model based on the VIIQ feature combination by combining the Blending algorithm with random forests (RF), gradient boosted trees (GBRT), and K nearest neighbors (KNN). This integration method not only improves the accuracy of the model, but also enhances the generalization ability of the model, enabling it to better adapt to different landslide susceptibility assessment scenarios. In this way, the present invention can more effectively predict the susceptibility of landslides, provide a scientific basis for risk assessment, early warning and prevention of geological disasters, thereby protecting people's lives and property and reducing losses caused by disasters.

[0019] (3) The SHAP algorithm provided by the present invention makes the decision-making process of the model more transparent and improves the interpretability of the model by quantifying the contribution of each feature to the model prediction. The SHAP value can reveal which features have the greatest impact on the model prediction results, providing a quantitative method for identifying key factors in landslide susceptibility assessment. The SHAP algorithm helps to analyze whether the model prediction is fair and unbiased, which is crucial for high-risk decision-making and ensures the reliability and fairness of the model prediction.

[0020] (4) The technology of landslide susceptibility mapping that combines the spatiotemporal characteristics and spatial heterogeneity of the geographical environment provided by the present invention can take into account the particularity and diversity of landslide events in specific areas, supplement the shortcomings of existing machine learning and deep learning technologies applied to landslide susceptibility mapping, and more comprehensively discover areas with landslide tendencies, providing assistance for landslide geological disaster prevention and control work in the region. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic flow chart of the method of the present invention;

[0022] Figure 2 It is an AGNES algorithm structure diagram of a landslide susceptibility mapping method integrating spatiotemporal characteristics and spatial heterogeneity of the present invention;

[0023] Figure 3It is a schematic diagram and flow chart of an optimal combination method of VIIQ features integrating spatiotemporal features and spatial heterogeneity of the present invention;

[0024] Figure 4 It is a structural diagram of a landslide susceptibility mapping method of a blending heterogeneous integrated model combining machine learning and deep learning in the present invention;

[0025] Figure 5 It is a landslide susceptibility result diagram of a blending heterogeneous integrated model of the present invention;

[0026] Figure 6 It is a post-global interpretation result diagram of landslide susceptibility results based on the blending heterogeneous integrated model of the present invention;

[0027] Figure 7 It is a schematic diagram of the working of the hardware device of an embodiment of the present invention. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0029] Before formally describing the present invention, the scheme of the present invention is first generally described for easy understanding.

[0030] Please refer to Figure 1 The present invention provides a method for mapping landslide susceptibility, comprising the following steps:

[0031] S1: Acquire multi-source remote sensing data and historical landslide data to produce hazard factor datasets and landslide sample datasets;

[0032] As an example, multi-source remote sensing data includes but is not limited to remote sensing image data, and hazard factor data includes but is not limited to the following according to the selected research area: lithology, elevation, curvature, plane curvature, profile curvature, slope, aspect, surface roughness, terrain moisture index, normalized vegetation index, precipitation, distance from faults, distance from rivers, distance from roads, and surface cover data. The landslide sample data set is derived from the accumulated landslide historical data in the research area, as well as the landslide data and non-landslide data marked by Google Earth based on remote sensing data, to ensure that the ratio of landslide samples to non-landslide samples is balanced and close to 1:1.

[0033] S2: Input all landslide sample data sets into the AGNES clustering algorithm and VIIQ feature optimization strategy module to obtain the optimal feature combination;

[0034] As an example, all landslide samples are input into the AGNES clustering algorithm to obtain different partitions. Figure 2 As shown in the figure, it aggregates data points into clusters by stepwise merging. This method starts with each data point as a separate cluster and then iteratively merges the most similar cluster pairs until all data points are aggregated into a large cluster or the number of preset clusters is reached. The application of the AGNES clustering algorithm can effectively identify landslide areas with similar characteristics, which may be affected by similar geological conditions and environmental factors. The advantages and disadvantages of different clustering schemes are evaluated by calculating the CH index, which is an indicator to measure the clustering effect, which is based on intra-cluster similarity and inter-cluster dissimilarity.

[0035] In each cluster, the landslide samples were classified based on the VIIQ (VIF-IGR-Importance-Qvalue) method. Figure 3 As shown, the most characteristic combination is performed.

[0036] In the feature selection process, the variance inflation factor (VIF) was used to test the multicollinearity of the characteristic factors to ensure the stability of the model. Then the information gain ratio (IGR) was calculated to assist in determining which factors contribute most to the model prediction effect. Subsequently, the Importance algorithm was introduced to calculate the importance of landslide features and further determine the features that are helpful for the landslide susceptibility assessment model. Finally, the geographic detector Qvalue was used for further optimization operations. By dividing the study area space and fitting the local linear model, the most discriminative and explanatory features can be screened out.

[0037] S3: Divide the optimized data features into training sets and test sets, input them into machine learning and deep learning classifiers, evaluate the model accuracy, and obtain a preliminary landslide susceptibility map;

[0038] As an embodiment, the model process of machine learning and deep learning classifier is to obtain the spatial characteristics of landslide by AGNES clustering algorithm and VIIQ feature optimization strategy module, and divide all data into landslide and non-landslide by decision tree, random forest (RF), support vector machine (SVM), gradient boosting regression tree (GBRT), K nearest neighbor (KNN), artificial neural network (ANN), convolutional neural network (CNN), recurrent neural network (RNN). Finally, the possibility of landslide occurrence is output to obtain landslide susceptibility mapping of a single model.

[0039] S4: Input the preliminary landslide susceptibility map of S3 into the Blending heterogeneous integration model to obtain the final landslide susceptibility mapping result;

[0040] It should be noted that in order to construct the optimal landslide susceptibility model, the invention adopts a method that combines machine learning and deep learning models. First, the machine learning model and the deep learning model are compared and analyzed to determine the performance of each. Figure 4 As shown in the figure, the best three learning models were selected for heterogeneous integration. This process involves an in-depth understanding of different models to ensure that the integrated model can maximize the accuracy of landslide susceptibility prediction. Subsequently, this paper compares the integrated model with a single learning model to verify the effectiveness of the blending integration strategy to couple multiple machine learning or deep learning algorithms. The blending integration strategy aims to improve the generalization ability and prediction accuracy of the model by combining the prediction results of different models. Through this integration method, the advantages of each model can be fully utilized to make up for the shortcomings of a single model, thereby obtaining more reliable results in landslide susceptibility evaluation.

[0041] In this example, in order to test the performance of the proposed landslide susceptibility mapping model, the area of ​​Nepal that suffered from the Gorkha earthquake was selected as the research object to illustrate the model performance and mapping results. In order to comprehensively measure the reliability of each method in landslide susceptibility mapping, so as to select the best method for accurate mapping, the present invention adopts five evaluation methods to evaluate each model. They are Accuracy, Precision, Recall, F1 score and AUC value.

[0042] First, the positive sample P (Positive) is recorded as 1, and the negative sample (Negative) is recorded as 0. TP (True Positive) means that the predicted value and the actual value are the same, both 1, that is, the classification is correct; FP (False Positive) means that the predicted value is 1 and the actual value is 0, that is, the prediction is wrong; FN (False Negative) means that the predicted value is 0 and the actual value is 1, that is, the prediction is wrong; TN (True Negative) means that the predicted value and the actual value are both 0, that is, the prediction is correct.

[0043] The performance comparison of the model of the method of the present invention is shown in Table 1. The Blending ensemble model based on the feature optimization combination has achieved a 3.65% improvement in AUC, a 3.71% improvement in accuracy, a 0.72% improvement in precision, a 1.98% improvement in recall, and a 0.41% improvement in F1-Score. This shows that after adding VIIQ for feature optimization, the performance of the model has been further improved.

[0044] Table 1 Comparison of performance of the model of the method of the present invention

[0045]

[0046]

[0047] The preliminary mapping results of the present invention using the VIIQ and Blending heterogeneous integrated model are as follows Figure 5 As shown, all landslide susceptibility values ​​are classified into very low (0 to 0.2), low (0.2 to 0.4), medium (0.4 to 0.6), high (0.6 to 0.8) and very high (0.8 to 1).

[0048] S5: The Blending heterogeneous integrated model of S4 is combined with the SHAP algorithm to further interpret the integrated model and optimize the landslide susceptibility result map.

[0049] The present invention takes the area of ​​Nepal that suffered from the Gorkha earthquake as the object, uses the SHAP algorithm, selects the landslide condition factors based on this paper, and combines the Blending integrated model to study the factor contribution degree, the local interpretation and the global interpretation of the model. The results of SHAP in the method of the present invention are as follows Figure 6 shown.

[0050] See also Figure 7 , Figure 7 4 is a schematic diagram of the working of the hardware device of an embodiment of the present invention, wherein the hardware device specifically comprises: a landslide susceptibility mapping device 401, a processor 402 and a storage medium 403.

[0051] A landslide susceptibility mapping device 401: The landslide susceptibility mapping device 401 implements the landslide susceptibility mapping method.

[0052] Processor 402: The processor 402 loads and executes the instructions and data in the storage medium 403 to implement the landslide susceptibility mapping method.

[0053] Storage medium 403: the storage medium 403 stores instructions and data; the storage medium 403 is used to implement the landslide susceptibility mapping method.

[0054] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for mapping landslide susceptibility, characterized in that: The method comprises the following steps: S1: Acquire multi-source remote sensing data and historical landslide data to produce hazard factor datasets and landslide sample datasets; S2: Input all landslide sample data sets into the AGNES clustering algorithm and VIIQ feature optimization strategy module to obtain the optimal feature combination; S3: Divide the optimized data features into training sets and test sets, input them into machine learning and deep learning classifiers, evaluate the model accuracy, and obtain a preliminary landslide susceptibility map; S4: Input the preliminary landslide susceptibility map of S3 into the Blending heterogeneous integration model to obtain the final landslide susceptibility mapping result; S5: The Blending heterogeneous integrated model of S4 is combined with the SHAP algorithm to further interpret the integrated model and optimize the landslide susceptibility result map.

2. A landslide susceptibility mapping method as claimed in claim 1, characterized in that: Step S1 is specifically as follows: the data set in step S2 is divided into discrete data and continuous data, and input into the AGNES clustering algorithm and VIIQ feature optimization strategy module.

3. A landslide susceptibility mapping method as claimed in claim 1, characterized in that: The AGNES clustering algorithm determines the distance measurement criteria between clusters and the optimal number of clusters based on the CH index. The CH index calculation formula is: Among them, B k is the sum of the distances between classes, i.e., the inter-cluster dispersion; W k is the sum of the intra-class distances, i.e., the intra-cluster dispersion; n is the total number of samples, k is the number of clusters, n q is the number of samples in the qth cluster; c q is the center point of the qth cluster; x is the sample point.

4. A landslide susceptibility mapping method as claimed in claim 1, characterized in that: The working process of the VIIQ feature optimization strategy module in step S2 is as follows: Variance inflation factor (VIF) was used to test the multicollinearity of characteristic factors. The information gain ratio IGR is used to assist in determining the contribution to the model prediction effect. The information gain ratio IGR is used to assist in determining the optimal feature factor group that contributes to the model prediction effect. Importance algorithm is introduced to calculate the importance of landslide features, and the feature combination is optimized according to the importance; The optimized feature combination is further screened out using geographic detector Qvalue to obtain the final feature combination.

5. A landslide susceptibility mapping method according to claim 1, characterized in that: The blending heterogeneous ensemble model in step S4 consists of a base learner and a meta learner.

6. A method for mapping landslide susceptibility according to claim 5, characterized in that: The base learners include random forest, GBRT and KNN; the meta learner adopts logistic regression.

7. A method for mapping landslide susceptibility according to claim 1, characterized in that: In step S5, the SHAP method explains the prediction results of the model by decomposing the prediction value of the evaluation model into the sum of the contribution values ​​of each input feature. The calculation formula is: Among them, g i (val) is the shap value of feature i; A is the set of all features; S is the feature subset that does not contain feature i, val(S) is the predicted value of the model under feature subset S; val(SU{i} is the predicted value of the model after adding feature i to feature subset S. |S| is the number of features in feature subset S; n is the total number of features.

8. A storage medium, characterized in that: The storage medium stores instructions and data for implementing a landslide susceptibility mapping method as described in any one of claims 1 to 7.

9. A landslide susceptibility mapping device, characterized in that: include: A processor and a storage medium; the processor loads and executes instructions and data in the storage medium to implement a landslide susceptibility mapping method as described in any one of claims 1 to 7.

Images