Landslide susceptibility evaluation method and system based on multi-source data and deep learning

Abstract

The invention discloses a landslide susceptibility evaluation method and system based on multi-source data and deep learning. The landslide susceptibility evaluation method combines an SBAS-InSAR technology, remote sensing image analysis, a deep learning algorithm, a TRIIGRS-SCOOPS3D coupling model and MASSFLOW simulation. The method is used for high-precision landslide prone area identification, potential landslide position prediction and three-dimensional landslide process simulation, and is especially suitable for landslide disaster risk management and emergency response in mountainous areas.

Description

Technical Field

[0001] The present invention belongs to the field of landslide disaster assessment, and in particular relates to a landslide susceptibility assessment method and system based on multi-source data and deep learning. Background Art

[0002] Although existing landslide monitoring technologies can effectively obtain surface deformation information over a wide range, traditional methods have limitations in accurately identifying potential landslide areas. Especially in complex terrains, there is still a lack of efficient automated methods for identifying potential landslide points through surface deformation data. Existing technologies generally rely on manual selection and manual marking of potential landslide points, and cannot accurately and efficiently extract potential landslide information from massive remote sensing data.

[0003] Moreover, the existing landslide process simulation technology mainly focuses on the volume, path and stability analysis of the landslide body, but the accuracy is still insufficient in simulating the distribution of dangerous areas after landslides occur at all potential landslide points. Existing technologies can usually only simulate a single landslide event, and it is difficult to fully consider the risk distribution after landslides occur at multiple potential landslide points under different environmental conditions. Especially in the case of complex terrain and multiple influencing factors, the existing model cannot accurately predict the landslide consequences and expansion areas of each potential landslide point. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a landslide susceptibility assessment method and system based on multi-source data and deep learning to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, the present invention provides a landslide susceptibility assessment method based on multi-source data and deep learning, comprising the following steps: Obtain high-resolution remote sensing images and digital elevation model data of the study area, and obtain surface deformation characteristics and potential landslide point information through SBAS-InSAR technology, deep convolutional neural network and YOLO algorithm; Acquire geological environment data of potential landslide points, and screen out the characteristics of geological environment data with landslide influencing factors, and construct a landslide susceptibility assessment model through quantum Bayesian optimization based on the surface deformation characteristics and the screened characteristics; The TRIGRS-SCOOPS3D coupled model was used to analyze the characteristics of rainfall-induced landslides and obtain the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides. According to the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides, the three-dimensional sliding surface of the potential landslide area was simulated by MASSFLOW model, the landslide volume and potential landslide path were calculated, and the landslide susceptibility assessment results were obtained.

[0006] Preferably, obtaining surface deformation characteristics and potential landslide point information includes: The surface deformation of the study area in the satellite image is calculated by SBAS-InSAR technology to obtain the surface deformation information of the study area; Obtain high-resolution remote sensing images and digital elevation model data of the study area, perform feature extraction through pre-trained deep convolutional neural networks, and obtain convolution extraction features; According to the surface deformation information and convolution extraction features, the potential landslide points are detected and located through the YOLO algorithm.

[0007] Preferably, constructing a landslide susceptibility assessment model includes: Obtain geological environment data of potential landslide sites, including slope, aspect, soil type, vegetation coverage, earthquake intensity, rainfall and groundwater level; Screening out features having landslide influencing factors from the geological environment data by using an Elastic Net regression model to obtain screening features; According to the surface deformation characteristics and screening features, a landslide susceptibility assessment model is constructed through quantum Bayesian optimization and adaptive deep reinforcement learning.

[0008] Preferably, the method further comprises: converting the landslide susceptibility assessment results into a spatial distribution map, presenting potential landslide areas and high-risk areas, and issuing a warning message when an increase in landslide risk is detected.

[0009] The present invention also provides a landslide susceptibility assessment system based on multi-source data and deep learning, comprising: Potential landslide point information acquisition module, which is used to obtain high-resolution remote sensing images and digital elevation model data of the study area, and obtain surface deformation characteristics and potential landslide point information through SBAS-InSAR technology, deep convolutional neural network and YOLO algorithm; A landslide susceptibility assessment model construction module is used to obtain geological environment data of potential landslide points, and screen out the characteristics of geological environment data with landslide influencing factors, and based on the surface deformation characteristics and the screened characteristics, a landslide susceptibility assessment model is constructed through quantum Bayesian optimization; Rainfall factor analysis module, which is used to analyze the characteristics of rainfall-induced landslides using the TRIGRS-SCOOPS3D coupling model, and obtain the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides; The evaluation module is used to simulate the three-dimensional sliding surface of the potential landslide area through the MASSFLOW model according to the stability of the landslide under the different rainfall conditions and the spatial distribution of the potential landslide, calculate the landslide volume and the potential landslide path, and obtain the landslide susceptibility evaluation result.

[0010] Preferably, the potential landslide point information acquisition module includes: A surface deformation information calculation unit is used to calculate the surface deformation of the study area in the satellite image through SBAS-InSAR technology to obtain the surface deformation information of the study area; Convolutional extraction feature acquisition unit, used to obtain high-resolution remote sensing images and digital elevation model data of the study area, and extract features through pre-trained deep convolutional neural network to obtain convolutional extraction features; The positioning unit is used to detect and locate potential landslide points through the YOLO algorithm according to the surface deformation information and convolution extraction features.

[0011] Preferably, the landslide susceptibility assessment model building module includes: A geological environment data acquisition unit, used to acquire geological environment data of potential landslide points, wherein the geological environment data includes slope, slope aspect, soil type, vegetation coverage, earthquake intensity, rainfall and groundwater level; A screening unit, used to screen out features having landslide influencing factors from the geological environment data by using an Elastic Net regression model to obtain screening features; A construction unit is used to construct a landslide susceptibility assessment model through quantum Bayesian optimization and adaptive deep reinforcement learning based on surface deformation characteristics and screening features.

[0012] Preferably, the system further comprises: a display platform for converting the landslide susceptibility assessment results into a spatial distribution map, presenting potential landslide areas and high-risk areas, and issuing early warning information when an increase in landslide risk is detected.

[0013] The present invention also provides a computer device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0014] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method are implemented.

[0015] Compared with the prior art, the present invention has the following advantages and technical effects: The present invention proposes a landslide susceptibility assessment method and system based on multi-source data and deep learning, including: obtaining high-resolution remote sensing images and digital elevation model data of a study area, obtaining surface deformation characteristics and potential landslide point information through SBAS-InSAR technology, deep convolutional neural network and YOLO algorithm; obtaining geological environment data of potential landslide points, and screening out the characteristics of geological environment data with landslide influencing factors, and constructing a landslide susceptibility assessment model through quantum Bayesian optimization based on surface deformation characteristics and screened characteristics; using the TRIGRS-SCOOPS3D coupling model to perform feature analysis on rainfall-induced landslides, and obtain the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides; according to the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides, the three-dimensional sliding surface of the potential landslide area is simulated through the MASSFLOW model, the landslide volume and the potential landslide path are calculated, and the landslide susceptibility assessment result is obtained. The present invention integrates SBAS-InSAR, satellite imagery, deep learning, TRIGRS-SCOOPS3D and MASSFLOW technologies, and can realize the comprehensive analysis of global susceptibility assessment of landslide disasters, local stability analysis and landslide process deduction, which has great innovation and application prospects. The present invention provides new technical means and theoretical support for the prediction, assessment and prevention of landslide disasters. The method can be widely used in the risk management of landslide disasters in mountainous areas, and provides an important reference for promoting the progress and development of disaster prevention and control technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flow chart of a landslide susceptibility assessment method based on multi-source data and deep learning according to an embodiment of the present invention; Figure 2 is a flow chart of region identification according to an embodiment of the present invention; Figure 3 is a flow chart of susceptibility assessment according to an embodiment of the present invention; Figure 4 The landslide process simulation flow chart of the embodiment of the present invention. DETAILED DESCRIPTION

[0017] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0018] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here. Embodiment 1

[0019] like Figure 1-4 As shown, in this embodiment, a landslide susceptibility assessment method based on multi-source data and deep learning is provided, comprising the following steps: Obtain high-resolution remote sensing images and digital elevation model data of the study area, and obtain surface deformation characteristics and potential landslide point information through SBAS-InSAR technology, deep convolutional neural network and YOLO algorithm; Obtain geological environment data of potential landslide points, and screen out the characteristics of geological environment data with landslide influencing factors. Based on the surface deformation characteristics and the screened characteristics, a landslide susceptibility assessment model is constructed through quantum Bayesian optimization; The TRIGRS-SCOOPS3D coupled model was used to analyze the characteristics of rainfall-induced landslides and obtain the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides. According to the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides, the three-dimensional sliding surface of the potential landslide area was simulated by MASSFLOW model, the landslide volume and potential landslide path were calculated, and the landslide susceptibility assessment results were obtained.

[0020] The specific steps include: 1. Data preprocessing and landslide area identification: SBAS-InSAR data processing: Through SBAS-InSAR technology, using Sentinel-1 or other high-resolution satellite data, the surface deformation information of the study area is extracted. Through time series image analysis, the surface deformation speed and its changing trend of each pixel are calculated.

[0021] Data preprocessing steps include image registration, removal of atmospheric effects, differential interferometry of time series, and phase unwrapping. The SBAS-InSAR method is used to calculate the surface deformation over a continuous time period, with a special focus on high deformation areas where landslides may occur.

[0022] Combination of remote sensing images and DEM data: Obtain high-resolution remote sensing images (such as Google Earth images) and digital elevation model (DEM) data of the study area, and combine the surface features of the remote sensing images to assess potential landslide areas.

[0023] Deep Learning and Visual Interpretation: A pre-trained deep convolutional neural network (ResNet-34) was used to extract features from remote sensing images, and the YOLO algorithm was used to detect and locate potential landslide points.

[0024] By fusing SAR images with remote sensing image data and using deep learning models to perform fine interpretation of surface deformation areas, potential landslide points can be accurately identified.

[0025] (1) CNN architecture: A ResNet deep convolutional neural network architecture is selected for feature extraction. Multiple convolutional layers and pooling layers are used to extract high-level features in the image, such as the texture, shape, and color of the landslide area.

[0026] Input layer: input remote sensing optical image.

[0027] Convolutional layer: Multi-layer convolution operations gradually extract from low-level features (edges, textures) to high-level features (landslide morphology, deformation areas, etc.).

[0028] Pooling layer: The pooling operation is used to reduce the size of the feature map, reduce the computational complexity, and retain key features.

[0029] Fully connected layer: The features extracted by the convolution and pooling layers are fully connected to generate landslide prediction results.

[0030] (2) YOLO architecture: YOLO is a deep learning-based object detection algorithm that can predict the location (bounding box) and category of objects in an image. This method is suitable for the localization and detection of landslide areas.

[0031] ① Input layer: The features extracted by CNN and SBAS-InSAR surface deformation images are used as input.

[0032] ② Feature map generation: YOLO connects the image in series with multiple grid units, and each unit is responsible for predicting the bounding box and category of the object in the area.

[0033] ③ Landslide detection: The model predicts the location of the landslide area in the image (through the bounding box) and the type of landslide (such as shallow landslide, deep landslide, etc.). YOLO can simultaneously locate and classify the target in one forward propagation, with high efficiency.

[0034] SAR and optical images can provide different information. Image SAR mainly provides surface deformation information, while optical images can provide richer surface texture and color information. Through deep model learning, these two types of information can be integrated to improve the accuracy of landslide detection.

[0035] 2. Screening of landslide susceptibility assessment factors and model establishment: Selection of landslide susceptibility factors: Combined with the geological environment of the study area, factors related to landslide susceptibility were selected, including: slope, slope aspect, soil type, vegetation coverage, earthquake intensity, rainfall, groundwater level, etc. Based on existing literature and expert opinions, other factors closely related to the occurrence of regional landslides, such as the impact of human activities, were further supplemented.

[0036] Factor screening and correlation analysis: Data preprocessing and model training: Standardize the data, use the Elastic Net regression model, set the alpha and l1_ratio parameters, balance L1 and L2 regularization, and train the model.

[0037] Factor screening and result analysis: Screen out the most influential features based on the model coefficients and evaluate the relationship between each feature and the target variable.

[0038] Construction of landslide susceptibility assessment model: Factor screening and model building: Based on the screened factors, a landslide susceptibility assessment model is established using quantum Bayesian optimization and adaptive deep reinforcement learning (Deep Q Network, DQN). The deep neural network learns complex nonlinear relationships and adaptively adjusts strategies to optimize landslide prediction results.

[0039] DQN framework: Input layer: The number of nodes in the input layer is equal to the number of screened landslide influencing factors. Output layer: The nodes in the output layer represent the deformation rate of the landslide point as the prediction result of the model.

[0040] State space and action space: State space (State): input landslide characteristic factors (e.g., slope, precipitation, etc.), which reflect the current geological environment and external factors. Action space (Action): learning strategies through reinforcement learning to adjust the weights of input characteristic factors and ultimately optimize the prediction results.

[0041] Reward function: The reward function is set by the error between the predicted result and the actual observed value. If the predicted deformation rate is close to the actual observed value, a positive reward is given; if the error is large, a negative reward is given.

[0042] Training deep neural networks: Use DQN to update the weights of the neural network through the back-propagation algorithm. During the training process, the network learns the complex nonlinear relationship between feature factors and deformation rate through interaction with the environment.

[0043] Experience Replay and Target Network: During training, an experience replay mechanism is used to store past state-action pairs (S, A) to avoid overfitting, and a target network is used to stabilize the training process.

[0044] Strategy update: Continuously adjust the strategy according to the reward function and improve the accuracy of the prediction results through multiple training.

[0045] Weighted decision-making and optimization: Introduce quantum Bayesian optimization to automatically adjust the model's hyperparameters (such as DQN's learning rate, discount factor (gamma), number of network layers, number of nodes, exploration rate (epsilon)), optimize model parameters according to the weights and influence of different factors, and improve the accuracy of evaluation results. Quantum computing accelerates the parameter optimization process and improves the efficiency of high-dimensional space search.

[0046] Initialize the optimization space: Define the optimization objective and hyperparameter space, such as the learning rate, number of layers, number of nodes per layer, etc. in a deep neural network (DNN).

[0047] Accelerating Bayesian Optimization with Quantum Computing: Leveraging quantum computing methods such as quantum convolutional neural networks or quantum support vector machines to accelerate the hyperparameter tuning process to optimize the prediction accuracy of landslide susceptibility assessment models. Model stability and performance evaluation: To ensure the stability of the model, cross validation and AUC (Area Under Curve) were used to evaluate the model performance. A landslide susceptibility zoning map was generated based on the model training results.

[0048] 3. Analysis of rainfall-induced landslide characteristics and simulation of landslide process: TRIGRS-SCOOPS3D coupled model: The TRIGRS model is used to analyze the stability of rainfall-induced landslides in the study area. The rainfall forecast information, soil type, groundwater level and other data of the area are input, and the stability of the slope under different rainfall conditions is calculated through the model.

[0049] The SCOOPS3D module was used to search for three-dimensional landslides, study the changing process of rainfall-induced landslides, and obtain the spatial distribution of potential landslides in the region.

[0050] MASSFLOW model applications: According to the output results of the TRIGRS-SCOOPS3D model, the MASSFLOW model is used to simulate the three-dimensional sliding surface of the potential landslide area in the region. The MASSFLOW model can simulate the flow process of mass landslides under the action of rainfall, and calculate the volume, flow velocity, landslide path, and dangerous areas of the landslide.

[0051] The dynamic process of rainfall-induced mass landslides can be predicted through model simulation, providing early warning data for subsequent disaster prevention and control.

[0052] Model parameter optimization and simulation verification: The simulation results of the model are verified by using field observation data and historical landslide events, and the reliability of the model prediction results is ensured by adjusting the parameters.

[0053] Combined with real-time rainfall forecasts and meteorological data, the model is dynamically adjusted to achieve real-time prediction of the landslide process.

[0054] 4. Real-time presentation of landslide risk areas and disaster warning: Spatial Visualization of Landslide Prone Areas: The results of the landslide susceptibility assessment model are converted into a spatial distribution map through the ArcGIS platform, showing potential landslide areas and high-risk areas. The spatial accuracy of the risk area is further improved by combining geological data and remote sensing images.

[0055] Dynamically update and display the distribution of landslide-prone areas to support regional landslide risk management and emergency response.

[0056] Real-time landslide disaster warning system: Based on deep learning models and big data analysis, a real-time disaster warning system is established, which can predict the occurrence of potential landslides based on real-time meteorological data and surface deformation information.

[0057] When the early warning system detects an increased landslide risk, it will promptly issue warning information and provide real-time risk assessment to relevant departments and the public to facilitate the adoption of disaster prevention measures.

[0058] 5. System architecture and implementation environment: Data platform and computing environment: The implementation of the method of the present invention requires the combination of remote sensing image data, geographic information system (GIS), meteorological data and large-scale computing platform. The data collection, preprocessing and analysis process requires the use of cloud computing platform and high-performance computing environment to handle large data volumes and complex computing models.

[0059] Establish a unified data storage and management system to support real-time updating and automated processing of data.

[0060] Software tools and technical support: The deep learning model and landslide assessment model used in this method can be implemented using programming languages ​​such as Python. The deep learning model can be trained based on frameworks such as TensorFlow and PyTorch, and ArcGIS can be used for spatial data processing and visualization.

[0061] By integrating the calculation results of TRIGRS-SCOOPS3D and MASSFLOW models, a landslide risk assessment and disaster warning system is established to ensure the real-time and high efficiency of the model.

[0062] This embodiment further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0063] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method are implemented. Embodiment 2

[0064] This embodiment provides a landslide susceptibility assessment system based on multi-source data and deep learning, including: Potential landslide point information acquisition module, which is used to obtain high-resolution remote sensing images and digital elevation model data of the study area, and obtain surface deformation characteristics and potential landslide point information through SBAS-InSAR technology, deep convolutional neural network and YOLO algorithm; The landslide susceptibility assessment model construction module is used to obtain the geological environment data of potential landslide points and screen out the characteristics of geological environment data with landslide influencing factors. Based on the surface deformation characteristics and the screened characteristics, the landslide susceptibility assessment model is constructed through quantum Bayesian optimization; Rainfall factor analysis module, which is used to analyze the characteristics of rainfall-induced landslides using the TRIGRS-SCOOPS3D coupling model, and obtain the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides; The assessment module is used to simulate the three-dimensional sliding surface of the potential landslide area through the MASSFLOW model according to the stability of the landslide under different rainfall conditions and the spatial distribution of potential landslides, calculate the landslide volume and potential landslide path, and obtain the landslide susceptibility assessment results.

[0065] Furthermore, the potential landslide point information acquisition module includes: A surface deformation information calculation unit is used to calculate the surface deformation of the study area in the satellite image through SBAS-InSAR technology to obtain the surface deformation information of the study area; Convolutional extraction feature acquisition unit, used to obtain high-resolution remote sensing images and digital elevation model data of the study area, and extract features through pre-trained deep convolutional neural network to obtain convolutional extraction features; The positioning unit is used to detect and locate potential landslide points through the YOLO algorithm based on the surface deformation information and convolution extraction features.

[0066] Furthermore, the landslide susceptibility assessment model building modules include: A geological environment data acquisition unit, used to acquire geological environment data of potential landslide points, wherein the geological environment data includes slope, slope aspect, soil type, vegetation coverage, earthquake intensity, rainfall and groundwater level; A screening unit, used to screen out features with landslide influencing factors from geological environment data through an Elastic Net regression model to obtain screening features; A construction unit is used to construct a landslide susceptibility assessment model through quantum Bayesian optimization and adaptive deep reinforcement learning based on surface deformation characteristics and screening features.

[0067] Furthermore, the system also includes: a display platform for converting the landslide susceptibility assessment results into a spatial distribution map, presenting potential landslide areas and high-risk areas, and issuing early warning information when an increase in landslide risk is detected.

[0068] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A landslide susceptibility assessment method based on multi-source data and deep learning, characterized in that: The following steps are involved: Obtain high-resolution remote sensing images and digital elevation model data of the study area, and obtain surface deformation characteristics and potential landslide point information through SBAS-InSAR technology, deep convolutional neural network and YOLO algorithm; Acquire geological environment data of potential landslide points, and screen out the characteristics of geological environment data with landslide influencing factors, and construct a landslide susceptibility assessment model through quantum Bayesian optimization based on the surface deformation characteristics and the screened characteristics; The TRIGRS-SCOOPS3D coupled model was used to analyze the characteristics of rainfall-induced landslides and obtain the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides. According to the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides, the three-dimensional sliding surface of the potential landslide area was simulated by MASSFLOW model, the landslide volume and potential landslide path were calculated, and the landslide susceptibility assessment results were obtained.

2. The method according to claim 1, characterized in that Obtaining information on surface deformation characteristics and potential landslide points includes: The surface deformation of the study area in the satellite image is calculated by SBAS-InSAR technology to obtain the surface deformation information of the study area; Obtain high-resolution remote sensing images and digital elevation model data of the study area, perform feature extraction through pre-trained deep convolutional neural networks, and obtain convolution extraction features; According to the surface deformation information and convolution extraction features, the potential landslide points are detected and located through the YOLO algorithm.

3. The method according to claim 1, characterized in that The construction of landslide susceptibility assessment model includes: Obtain geological environment data of potential landslide sites, including slope, aspect, soil type, vegetation coverage, earthquake intensity, rainfall and groundwater level; Screening out features having landslide influencing factors from the geological environment data by using an Elastic Net regression model to obtain screening features; According to the surface deformation characteristics and screening features, a landslide susceptibility assessment model is constructed through quantum Bayesian optimization and adaptive deep reinforcement learning.

4. The method according to claim 1, characterized in that The method also includes: converting the landslide susceptibility assessment results into a spatial distribution map, presenting potential landslide areas and high-risk areas, and issuing early warning information when an increased landslide risk is detected.

5. A landslide susceptibility assessment system based on multi-source data and deep learning, characterized in that: include: Potential landslide point information acquisition module, which is used to obtain high-resolution remote sensing images and digital elevation model data of the study area, and obtain surface deformation characteristics and potential landslide point information through SBAS-InSAR technology, deep convolutional neural network and YOLO algorithm; A landslide susceptibility assessment model construction module is used to obtain geological environment data of potential landslide points, and screen out the characteristics of geological environment data with landslide influencing factors, and based on the surface deformation characteristics and the screened characteristics, a landslide susceptibility assessment model is constructed through quantum Bayesian optimization; Rainfall factor analysis module, which is used to analyze the characteristics of rainfall-induced landslides using the TRIGRS-SCOOPS3D coupling model, and obtain the stability of landslides under different rainfall conditions and the spatial distribution of potential landslides; The evaluation module is used to simulate the three-dimensional sliding surface of the potential landslide area through the MASSFLOW model according to the stability of the landslide under the different rainfall conditions and the spatial distribution of the potential landslide, calculate the landslide volume and the potential landslide path, and obtain the landslide susceptibility evaluation result.

6. The system according to claim 5, characterized in that The potential landslide point information acquisition module includes: A surface deformation information calculation unit is used to calculate the surface deformation of the study area in the satellite image through SBAS-InSAR technology to obtain the surface deformation information of the study area; Convolutional extraction feature acquisition unit, used to obtain high-resolution remote sensing images and digital elevation model data of the study area, and extract features through pre-trained deep convolutional neural network to obtain convolutional extraction features; The positioning unit is used to detect and locate potential landslide points through the YOLO algorithm according to the surface deformation information and convolution extraction features.

7. The system according to claim 5, characterized in that The landslide susceptibility assessment model building module includes: A geological environment data acquisition unit, used to acquire geological environment data of potential landslide points, wherein the geological environment data includes slope, slope aspect, soil type, vegetation coverage, earthquake intensity, rainfall and groundwater level; A screening unit, used to screen out features having landslide influencing factors from the geological environment data by using an Elastic Net regression model to obtain screening features; A construction unit is used to construct a landslide susceptibility assessment model through quantum Bayesian optimization and adaptive deep reinforcement learning based on surface deformation characteristics and screening features.

8. The system according to claim 5, characterized in that The system also includes: a display platform for converting the landslide susceptibility assessment results into a spatial distribution map, presenting potential landslide areas and high-risk areas, and issuing early warning information when an increase in landslide risk is detected.

9. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images