A method for evaluating the susceptibility of a seismic landslide and related equipment
By combining the Newmark displacement model and the convolutional neural network hybrid model, the uncertainty and prediction accuracy problems of earthquake landslide susceptibility assessment in existing technologies are solved, and a more accurate and reliable landslide susceptibility assessment is achieved.
Patent Information
- Application Number
- CN202610423499.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-01
- Publication Date
- 2026-06-26
Smart Images
Figure CN122286492A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of landslide disaster risk assessment technology, and in particular to a method and related equipment for evaluating the susceptibility of earthquake-induced landslides. Background Technology
[0002] Earthquake-induced landslides are one of the secondary disasters caused by earthquakes. Affected by the disturbance of seismic waves, slopes deform and break down, which in turn triggers landslides of varying degrees. Because earthquake-triggered landslides are widely distributed and numerous, and often occur in groups, the damage they cause can even exceed that of the earthquake itself in many cases. Therefore, rapid and accurate assessment and mapping of earthquake landslide susceptibility is of great significance for earthquake disaster prevention and risk management.
[0003] Currently, existing solutions for assessing earthquake landslide susceptibility mainly fall into two categories: physical mechanism-based models and data-driven machine learning models. The first category, physical models (such as the Newmark model), while considering the mechanical mechanisms of landslides caused by seismic loads, neglects complex external environmental factors such as elevation, distance from faults, and vegetation cover. Furthermore, the difficulty in obtaining regional soil and rock physical parameters often leads to simplification, resulting in significant uncertainty in the calculation results. The second category, machine learning models (such as logistic regression, random forests, and convolutional neural networks), while capable of uncovering nonlinear relationships between data, suffers from significant drawbacks: ① the models lack physical interpretability and fail to consider the dynamic mechanisms of earthquake landslides; ② the predictive performance of the models is highly dependent on the quality of the sample dataset. Current solutions typically select "non-landslide samples" through random sampling within the study area or at a certain distance from the landslide point. This method lacks physical basis and easily misidentifies areas that are actually in a critically unstable state during earthquakes but have not yet landslided as "safe non-landslide samples," resulting in "noise" in the training data and severely impacting the model's predictive accuracy. Summary of the Invention
[0004] This invention provides a method and related equipment for assessing earthquake landslide susceptibility, with the aim of improving the accuracy and reliability of earthquake landslide susceptibility assessment.
[0005] To achieve the above objectives, the present invention provides a method for evaluating the susceptibility of earthquake-induced landslides, comprising: Step 1: Collect multi-source data for the study area, including geological data, topographic data, hydrological data, seismic data, and image data; Step 2: Select multiple landslide influencing factors from the multi-source data, and perform multicollinearity analysis and Pearson correlation coefficient analysis on all landslide influencing factors to obtain basic environmental factors; Step 3: Calculate the Newmark displacement based on the physical and mechanical parameters and basic environmental factors in the multi-source data; Step 4: Stack the Newmark displacement with the basic environmental factors to obtain multi-channel image data, and input the multi-channel image data into the earthquake landslide susceptibility evaluation model for evaluation to obtain the coseismic landslide susceptibility zoning map of the study area. The earthquake-prone landslide susceptibility assessment model is a hybrid model consisting of the Newmark displacement model and a convolutional neural network, and is obtained by training the hybrid model using a landslide training dataset.
[0006] Furthermore, basic environmental factors include peak ground acceleration, land use type, annual average rainfall, normalized vegetation index, distance from fault, distance from river, slope, aspect, position, topographic relief, and topographic humidity index.
[0007] Furthermore, the physical and mechanical parameters in multi-source data include effective cohesion, effective internal friction angle, and soil-rock weight.
[0008] Furthermore, step 3 includes: The static safety factor of the slope is calculated based on the effective cohesion, effective internal friction angle, and the weight of the soil and rock. The critical acceleration that the slope can withstand when it is in a state of limit equilibrium is calculated based on the static safety factor. The Newmark displacement is obtained by substituting the critical acceleration and the peak ground acceleration in the basic environmental factors into the empirical displacement equation.
[0009] Furthermore, the formula for calculating the static safety factor of a slope based on effective cohesion, effective internal friction angle, and soil-rock weight is as follows: ; in, Indicates the static safety factor. Indicates effective cohesion. Indicates the slope angle. Indicates the effective internal friction angle. Indicates the weight of soil and rock. Indicates the specific gravity of groundwater, and indicates the thickness of the slippery body. This indicates the proportion of saturated potential landslide bodies.
[0010] Furthermore, by substituting the critical acceleration and the peak ground acceleration from the basic environmental factors into the empirical displacement equation, the calculation expression for the Newmark displacement is obtained as follows: ; in, Indicates the Newmark displacement. Indicates the critical acceleration. This represents the peak ground acceleration.
[0011] Furthermore, before training the hybrid model using the landslide training dataset, the following steps are required: A displacement threshold is set within the study area. Areas within the study area where the Newmark displacement is less than the displacement threshold are defined as stable areas, while areas within the study area where the Newmark displacement is greater than or equal to the displacement threshold are defined as landslide areas. Random sampling was conducted in both stable and landslide areas to obtain landslide samples and non-landslide samples, with the number of landslide samples being equal to the number of non-landslide samples; The landslide samples and non-landslide samples are merged to obtain the landslide training dataset.
[0012] The present invention also provides an earthquake landslide susceptibility assessment device, comprising: The data collection module is used to collect multi-source data of the study area, including geological data, topographic data, hydrological data, seismic data, and image data. The analysis module is used to select multiple landslide influencing factors from multi-source data and perform multicollinearity analysis and Pearson correlation coefficient analysis on all landslide influencing factors to obtain basic environmental factors; The calculation module is used to calculate the Newmark displacement based on the physical and mechanical parameters and basic environmental factors in the multi-source data; The evaluation module is used to stack Newmark displacement with basic environmental factors to obtain multi-channel image data, and input the multi-channel image data into the earthquake landslide susceptibility evaluation model for evaluation, so as to obtain the coseismic landslide susceptibility zoning map of the study area. The earthquake-prone landslide susceptibility assessment model is a hybrid model consisting of the Newmark displacement model and a convolutional neural network, and is obtained by training the hybrid model using a landslide training dataset.
[0013] The present invention also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement an earthquake landslide susceptibility assessment method.
[0014] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a method for evaluating the susceptibility of earthquakes and landslides.
[0015] The above-described solution of the present invention has the following beneficial effects: This invention selects multiple landslide influencing factors from multi-source data of the study area and performs multicollinearity analysis and Pearson correlation coefficient analysis on all landslide influencing factors to obtain basic environmental factors. Newmark displacement is calculated based on the physical and mechanical parameters in the multi-source data and the basic environmental factors. The Newmark displacement is stacked with the basic environmental factors to obtain multi-channel image data, which is then input into an earthquake landslide susceptibility assessment model for evaluation, resulting in a coseismic landslide susceptibility zoning map of the study area. Compared with existing technologies, this invention uses Newmark displacement as an independent feature input, compensating for the lack of physical mechanism support in traditional pure data-driven models. It achieves complementary advantages between the dynamic mechanism of geological disasters and the feature extraction capabilities of deep learning, improving the accuracy and reliability of earthquake landslide susceptibility assessment.
[0016] Other beneficial effects of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0017] Figure 1 This is a flowchart illustrating an embodiment of the present invention; Figure 2 This is a schematic diagram of the sampling results of non-landslide samples in an embodiment of the present invention; Figure 3 This is a comparison curve diagram of the three models in the embodiments of the present invention; Figure 4 This is a schematic diagram of the structure of the earthquake landslide susceptibility assessment device in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of the terminal device in an embodiment of the present invention. Detailed Implementation
[0018] To make the technical problems, solutions, and advantages of this invention clearer, a detailed description will be provided below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0019] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0020] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a locking connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.
[0021] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0022] This invention addresses existing problems by providing a method and related equipment for evaluating the susceptibility of earthquake-induced landslides.
[0023] like Figure 1 As shown, an embodiment of the present invention provides a method for evaluating the susceptibility of earthquake-induced landslides, comprising: Step 1: Collect multi-source data for the study area, including geological data, topographic data, hydrological data, seismic data, and image data; Step 2: Select multiple landslide influencing factors from the multi-source data, and perform multicollinearity analysis and Pearson correlation coefficient analysis on all landslide influencing factors to obtain basic environmental factors; Step 3: Calculate the Newmark displacement based on the physical and mechanical parameters and basic environmental factors in the multi-source data; Step 4: Stack the Newmark displacement with the basic environmental factors to obtain multi-channel image data, and input the multi-channel image data into the earthquake landslide susceptibility evaluation model for evaluation to obtain the coseismic landslide susceptibility zoning map of the study area. The earthquake-prone landslide susceptibility assessment model is a hybrid model consisting of the Newmark displacement model and a convolutional neural network, and is obtained by training the hybrid model using a landslide training dataset.
[0024] Specifically, geological data includes lithological data and distance from faults; topographic data includes elevation data, slope data, aspect data, slope position data, and topographic relief; hydrological data includes distance from rivers, average annual rainfall, topographic humidity index, and water flow intensity index; seismic data includes peak ground acceleration and seismic intensity; and imagery data includes vegetation data, land use data, and distance from roads.
[0025] In this embodiment of the invention, the data with the greatest impact on earthquake landslides are initially selected from multi-source data as landslide impact factors. The multicollinearity value and Pearson correlation coefficient of each landslide impact factor are calculated to obtain the multicollinearity value and Pearson correlation coefficient of each landslide impact factor. Landslide impact factors with multicollinearity values greater than 5 or absolute correlation coefficient values greater than 0.5 are removed to obtain the basic environmental factors.
[0026] Specifically, basic environmental factors include peak ground acceleration, land use type, annual average rainfall, normalized vegetation index, distance from fault, distance from river, slope, aspect, position, topographic relief, and topographic humidity index.
[0027] Specifically, the physical and mechanical parameters in multi-source data include effective cohesion, effective internal friction angle, and soil-rock weight.
[0028] Specifically, step 3 includes: Based on the Mohr-Coulomb criterion, the static safety factor of the slope is calculated according to the effective cohesion, effective internal friction angle, and soil-rock weight. The critical acceleration that a slope can withstand when it is in a state of limit equilibrium is calculated based on the static safety factor. The critical acceleration is the maximum seismic acceleration that a slope can withstand when it is in a state of limit equilibrium. The Newmark displacement is obtained by substituting the critical acceleration and the peak ground acceleration in the basic environmental factors into the empirical displacement equation.
[0029] Specifically, the formula for calculating the static safety factor of a slope based on effective cohesion, effective internal friction angle, and soil-rock weight is as follows: ; in, Indicates the static safety factor. Indicates effective cohesion. Indicates the slope angle. Indicates the effective internal friction angle. Indicates the weight of soil and rock. Indicates the specific gravity of groundwater, and indicates the thickness of the slippery body. This indicates the proportion of saturated potential landslide bodies.
[0030] Specifically, the formula for calculating the critical acceleration that a slope can withstand when it is in a limit equilibrium state, based on the static safety factor, is as follows: ; in, Indicates the critical acceleration. Represents gravitational acceleration. This indicates the inclination angle of the sliding surface.
[0031] Specifically, by substituting the critical acceleration and the peak ground acceleration from the basic environmental factors into the empirical displacement equation, the calculation expression for the Newmark displacement is obtained as follows: ; in, Indicates the Newmark displacement. Indicates the critical acceleration. This represents the peak ground acceleration.
[0032] In this embodiment of the invention, a smaller Newmark displacement indicates that the slope is more stable under seismic action.
[0033] Specifically, to address the low sample quality problem caused by traditional random sampling, this embodiment of the invention constructs a landslide training dataset before training the hybrid model using the landslide training dataset. The specific process includes: A displacement threshold is set within the study area. Areas within the study area where the Newmark displacement is less than the displacement threshold are defined as stable areas, while areas within the study area where the Newmark displacement is greater than or equal to the displacement threshold are defined as landslide areas. Random sampling was conducted in both stable and landslide areas to obtain landslide samples and non-landslide samples, with the number of landslide samples being equal to the number of non-landslide samples; The landslide samples and non-landslide samples are merged to obtain the landslide training dataset.
[0034] In the training process of the model, this embodiment of the invention uses a Bayesian optimization algorithm to automatically optimize hyperparameters such as convolution kernel size, learning rate, number of filters, and Dropout rate to ensure that the model achieves the best performance.
[0035] Specifically, the hybrid model's network structure mainly consists of sequentially connected convolutional layers, pooling layers, fully connected layers, and an output layer. The input to the convolutional layers is the input to the hybrid model itself. The input data is a multi-channel image data with 12 feature channels, which is a stack of all basic environmental factors and Newmark displacements. The convolutional layers perform operations on the multi-channel image data through convolutional kernels to extract deep nonlinear interaction features between topographic, geological, seismic motion parameters, and physical displacement indices. The pooling layers use a max pooling strategy to compress the size of deep nonlinear interaction features, reduce the number of parameters, and prevent overfitting. The fully connected layers flatten the extracted high-dimensional features and perform nonlinear combinations. Finally, the output layer, which contains two neurons, outputs the Landslide Susceptibility Index (LSI, ranging from 0 to 1). Using statistical grading methods such as the natural breakpoint method, the LSI values are divided into five susceptibility levels: extremely low, low, medium, high, and extremely high, thereby generating a coseismic landslide susceptibility zoning map for the entire region.
[0036] The above sampling strategy can effectively eliminate some potential danger points that, although not sliding, are actually in a critically unstable state, thus significantly improving the reliability of negative samples.
[0037] This invention takes a region in Southwest Asia as an example and conducts an experiment using the method provided in this invention. The experiment takes a region in Southwest Asia as the research area and collects multi-source data including digital elevation model (DEM), geological map, peak ground acceleration (PGA), etc. All spatial data are uniformly resampled into 30m×30m grid cells.
[0038] In the key parameter calculation and model building stage, lithology is first classified and physical and mechanical parameters are assigned based on the geological map, as shown in Table 1 below: Table 1 Physical and mechanical parameters of different rock formations
[0039] The Newmark displacement (Dn) distribution across the entire area was calculated using physical and mechanical parameters. This layer reflects both the physical stability of the slope and serves as an important input feature for the model. Subsequently, negative sample sampling was performed based on the Newmark displacement to obtain the following... Figure 2 The sampling results shown indicate that non-landslide sample points are mainly distributed in physically stable areas with small Dn values, effectively avoiding potential landslide hazard zones. Based on this, a hybrid model N_CNN is constructed, and the hyperparameters are optimized using a Bayesian optimization algorithm.
[0040] To verify the superiority of this invention, a multi-dimensional comparative analysis was conducted. First, the ROC curves of the N_CNN model proposed in this invention were compared with those of traditional logistic regression (N_LR) and random forest (N_RF) models. The comparison results are as follows: Figure 4 As shown in Table 2 below, the comparison results of the performance indicators are as follows: Table 2 Comparison of Predictive Performance of Three Models with Different Standards
[0041] Depend on Figure 4 As can be seen, the AUC value of the N_CNN model reaches 0.933, which is better than N_RF (0.913) and N_LR (0.895). Table 2 above also shows that N_CNN is superior in accuracy (0.848), sensitivity (0.827) and specificity (0.868). The above experimental data fully demonstrate that the method proposed in this invention is significantly better than the existing technology in terms of prediction accuracy, sample quality and model stability.
[0042] This invention selects multiple landslide influencing factors from multi-source data of the study area and performs multicollinearity analysis and Pearson correlation coefficient analysis on all landslide influencing factors to obtain basic environmental factors. Newmark displacement is calculated based on the physical and mechanical parameters in the multi-source data and the basic environmental factors. The Newmark displacement is stacked with the basic environmental factors to obtain multi-channel image data, which is then input into an earthquake landslide susceptibility assessment model for evaluation, resulting in a coseismic landslide susceptibility zoning map of the study area. Compared with existing technologies, this invention uses Newmark displacement as an independent feature input, compensating for the lack of physical mechanism support in traditional pure data-driven models. This achieves a complementary advantage between the dynamic mechanism of geological disasters and the feature extraction capabilities of deep learning, improving the accuracy and reliability of earthquake landslide susceptibility assessment.
[0043] Corresponding to the earthquake landslide susceptibility assessment method described in the above embodiments, such as Figure 4 As shown, this embodiment of the invention also provides an earthquake landslide susceptibility assessment device 100, which includes: The collection module 101 is used to collect multi-source data of the study area, including geological data, topographic data, hydrological data, seismic data and image data; Analysis module 102 is used to select multiple landslide influencing factors from multi-source data, and to perform multicollinearity analysis and Pearson correlation coefficient analysis on all landslide influencing factors to obtain basic environmental factors; Calculation module 103 is used to calculate the Newmark displacement based on the physical and mechanical parameters and basic environmental factors in the multi-source data; Evaluation module 104 is used to stack Newmark displacement with basic environmental factors to obtain multi-channel image data, and input the multi-channel image data into the earthquake landslide susceptibility evaluation model for evaluation to obtain a coseismic landslide susceptibility zoning map of the study area. The earthquake-prone landslide susceptibility assessment model is a hybrid model consisting of the Newmark displacement model and a convolutional neural network, and is obtained by training the hybrid model using a landslide training dataset.
[0044] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.
[0045] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0046] This invention also provides a terminal device, such as... Figure 5 As shown, the terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 5 The diagram shows only one processor, a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100. When the processor D100 executes the computer program D102, it implements the above-described earthquake landslide susceptibility assessment method.
[0047] The terminal device D10 can be a desktop computer, laptop, handheld computer, server, server cluster, or cloud server, etc. This terminal device may include, but is not limited to, a processor D100 and a memory D101. Those skilled in the art will understand that... Figure 5This is merely an example of terminal device D10 and does not constitute a limitation on terminal device D10. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.
[0048] The processor D100 can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.
[0049] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may be an external storage device of the terminal device D10, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal device D10. Furthermore, the memory D101 may include both internal and external storage units of the terminal device D10. The memory D101 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory D101 can also be used to temporarily store data that has been output or will be output.
[0050] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.
[0051] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0052] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a method for evaluating the susceptibility of earthquakes and landslides.
[0053] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a building device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.
[0054] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. A method for evaluating the susceptibility of a seismic landslide, characterized by, include: Step 1: Collect multi-source data for the study area, including geological data, topographic data, hydrological data, seismic data, and image data; Step 2: Select multiple landslide influencing factors from the multi-source data, and perform multicollinearity analysis and Pearson correlation coefficient analysis on all landslide influencing factors to obtain basic environmental factors; Step 3: Calculate the Newmark displacement based on the physical and mechanical parameters and basic environmental factors in the multi-source data; Step 4: Stack the Newmark displacement with the basic environmental factors to obtain multi-channel image data, and input the multi-channel image data into the earthquake landslide susceptibility evaluation model for evaluation to obtain the coseismic landslide susceptibility zoning map of the study area. The earthquake-prone landslide susceptibility assessment model is a hybrid model consisting of the Newmark displacement model and a convolutional neural network, and is trained using a landslide training dataset.
2. The seismic landslide susceptibility assessment method according to claim 1, characterized in that, The basic environmental factors include peak ground acceleration, land use type, annual average rainfall, normalized vegetation index, distance from fault, distance from river, slope, aspect, position, topographic relief, and topographic humidity index.
3. The seismic landslide susceptibility assessment method according to claim 1, characterized in that, The physical and mechanical parameters in the multi-source data include effective cohesion, effective internal friction angle, and soil-rock weight.
4. The seismic landslide susceptibility assessment method according to claim 3, characterized in that, Step 3 includes: The static safety factor of the slope is calculated based on the effective cohesion, the effective internal friction angle, and the weight of the soil and rock. Calculate the critical acceleration that the slope can withstand when it is in a state of limit equilibrium based on the static safety factor. The Newmark displacement is obtained by substituting the critical acceleration and the peak ground acceleration in the basic environmental factors into the empirical displacement equation.
5. The seismic landslide susceptibility assessment method according to claim 4, characterized in that, The formula for calculating the static safety factor of the slope based on the effective cohesion, the effective internal friction angle, and the weight of the soil and rock is as follows: ； wherein, denotes the static safety factor, denotes the effective cohesion, denotes the slope angle, denotes the effective internal friction angle, denotes the weight of the rock-soil mass, denotes the weight of the groundwater, denotes the thickness of the sliding mass, denotes the proportion of the saturated potential sliding mass.
6. The seismic landslide susceptibility assessment method according to claim 5, characterized in that, Substituting the critical acceleration and the peak ground acceleration in the basic environmental factors into the empirical displacement equation, the calculation expression for the Newmark displacement is obtained as follows: ； wherein, denotes the Newmark displacement, denotes the critical acceleration, denotes the peak ground acceleration.
7. The seismic landslide susceptibility assessment method according to claim 1, characterized in that, Before training the hybrid model using the landslide training dataset, the following steps are included: A displacement threshold is set within the study area. Regions within the study area with a Newmark displacement less than the displacement threshold are defined as stable regions, and regions within the study area with a Newmark displacement greater than or equal to the displacement threshold are defined as landslide regions. Random sampling is performed in the stable region and the landslide region respectively to obtain landslide samples and non-landslide samples, wherein the number of landslide samples and the number of non-landslide samples are equal; The landslide samples and the non-landslide samples are merged to obtain the landslide training dataset.
8. A device for evaluating the susceptibility to earthquake-induced landslides, characterized in that, include: The collection module is used to collect multi-source data of the study area, including geological data, topographic data, hydrological data, seismic data, and image data. The analysis module is used to select multiple landslide influencing factors from the multi-source data, and to perform multicollinearity analysis and Pearson correlation coefficient analysis on all landslide influencing factors to obtain basic environmental factors. The calculation module is used to calculate the Newmark displacement based on the physical and mechanical parameters and basic environmental factors in the multi-source data; The evaluation module is used to stack the Newmark displacement with the basic environmental factors to obtain multi-channel image data, and input the multi-channel image data into the earthquake landslide susceptibility evaluation model for evaluation to obtain the coseismic landslide susceptibility zoning map of the study area. The earthquake-prone landslide susceptibility assessment model is a hybrid model consisting of the Newmark displacement model and a convolutional neural network, and is trained using a landslide training dataset.
9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the earthquake landslide susceptibility assessment method as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. When the computer program is executed by the processor, it implements the earthquake landslide susceptibility assessment method as described in any one of claims 1 to 7.