Landslide susceptibility evaluation method based on federal learning and UNet

Abstract

The invention relates to the technical field of geological disaster risk analysis, in particular to a landslide susceptibility evaluation method based on federated learning and UNet, and the method comprises the following steps: S1, obtaining landslide influence factor data: collecting a plurality of landslide influence factor data; s2, establishing a federated learning framework: establishing the federated learning framework; s3, designing a UNet deep learning model: feature extraction and segmentation; s4, federal learning model training and parameter integration: updating a global UNet-based deep learning model; s5, performing federated learning iteration and model optimization: optimizing UNet-based deep learning model parameters; s6, generating a landslide susceptibility characteristic graph and probability regression: outputting a landslide susceptibility evaluation result; s7, result verification and disaster prevention and reduction suggestions: providing landslide risk early warning and disaster prevention and reduction suggestions; according to the invention, more efficient and more accurate landslide susceptibility evaluation can be realized, and the model can be updated in time to cope with new data changes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological disaster risk analysis, and particularly relates to a landslide susceptibility evaluation method based on federated learning and UNet. BACKGROUND

[0002] Landslide susceptibility evaluation is a key link in geological disaster prevention. Traditional methods usually rely on field investigation and experience judgment, which is time-consuming and costly. With the development of computer technology and data science, data-driven methods have gradually become an important research direction for landslide susceptibility evaluation. These methods analyze geological environmental factors, historical landslide data, etc. to predict the probability of future landslides and provide decision support.

[0003] Traditional landslide susceptibility evaluation methods, such as experimental models, analytic hierarchy process, and statistical models, can effectively predict landslide risks, but have limitations in handling complex data and multi-source information fusion. In particular, when analyzing image data, traditional convolutional neural network (CNN) methods cannot perform pixel-level classification, resulting in loss of detailed information and affecting the accurate identification of landslide areas. In addition, CNN lacks skip connections and cannot effectively restore high-resolution details of images, and performs poorly and inefficiently when the data volume is small.

[0004] To solve the limitations of existing methods, the present application aims to propose a landslide susceptibility evaluation method combining federated learning and deep learning technology, which can effectively solve the problems of slow data processing speed, insufficient memory, poor security, etc. in centralized training, and realize more efficient and secure landslide susceptibility evaluation. SUMMARY

[0005] The present application provides a landslide susceptibility evaluation method based on federated learning and UNet.

[0006] A landslide susceptibility evaluation method based on federated learning and UNet, comprising the following steps: S1, obtaining landslide influencing factor data: collecting multiple landslide influencing factor data and extracting multiple influencing factor layer data of landslide susceptibility areas; S2, establishing a federated learning framework: establishing a federated learning framework among multiple data holders; S3, designing a UNet deep learning model: designing a UNet-based deep learning model for landslide susceptibility evaluation, and inputting the influencing factor layer data into the model for feature extraction and segmentation; S4, federated learning model training and parameter integration: training the UNet-based deep learning model through the landslide sample data set under the federated learning framework, integrating the model parameters through the federated averaging algorithm, and updating the global UNet-based deep learning model; S5, federated learning iteration and model optimization: through multiple rounds of federated learning iteration, the UNet-based deep learning model parameters are optimized; S6, generating landslide susceptibility feature map and probability regression: applying the optimized UNet-based deep learning model to generate the feature map of landslide susceptibility area, using the Sigmoid layer for probability regression processing, and outputting the landslide susceptibility evaluation result; S7, result verification and disaster prevention and mitigation suggestion: verifying and evaluating the landslide susceptibility evaluation result, and providing landslide risk warning and disaster prevention and mitigation suggestion according to the evaluation result.

[0007] Optionally, the plurality of landslide influence factor data in S1 includes topographic factors, geological factors, hydrological factors, land cover factors and climate factors, wherein; The topographic factors include aspect, slope, elevation and curvature. The geological factors include lithology. The hydrological factors include annual average precipitation and distance from water system. The land cover factors include enhanced vegetation index, normalized difference vegetation index, surface reflectivity and land use. The climate factors include annual average temperature and surface temperature.

[0008] Optionally, the plurality of influence factor layer data in S1 includes elevation, slope, aspect, curvature, lithology, distance from water system and land use.

[0009] Optionally, the construction of the landslide sample data set includes: Data collection: obtaining historical landslide data and landslide hidden danger point data; Construction of landslide sample data set: according to the historical landslide data and landslide hidden danger point data, the landslide sample data set is constructed, by judging the number of landslide grids in a rectangular region, if the number of landslide grids in the rectangular region exceeds 50%, the rectangular region is marked as a landslide point, if less than 50%, it is marked as a non-landslide point, and the marked landslide sample data set is defined as an experimental data set; Divide the training set and the validation set: divide the experimental data set into training set and validation set according to the ratio of 8:2, wherein the landslide sample is marked as 1, and the non-landslide sample is marked as 0; Data enhancement: data enhancement is performed on the constructed landslide sample data.

[0010] Optionally, the data enhancement includes: Identify the landslide feature grid: in the landslide sample data set, identify the grid of the landslide point; Applying Mixup data enhancement technology: applying Mixup data enhancement technology, the raster of the identified landslide point is randomly spliced to generate an enhanced sample, which is represented as: ; wherein, is the generated enhanced sample, is a weighting coefficient randomly selected in the interval , and and are landslide samples; Enhanced samples are added to the experimental data set: the generated enhanced samples are added to the experimental data set.

[0011] Optionally, the parameter update of the global UNet-based deep learning model is represented as: ; wherein, represents the data volume of the th data holder, represents the total amount of all data, is the learning rate, represents the UNet-based deep learning model in the th round of federated learning, represents the UNet-based deep learning model in the previous round of federated learning, represents the global gradient function.

[0012] Optionally, the training of the UNet-based deep learning model comprises: Setting the activation function: LeakyReLU is selected as the activation function for each convolutional layer in the UNet-based deep learning model, represented as: ; wherein, is 0.01; Model training: applying weight-based learning in the convolutional layer, represented as: ; wherein, is a convolution kernel with a step size of 2, is a bias term, is an activation function; Normalization: multiple landslide influencing factor data are used as input data, a normalization layer is introduced to normalize the input data , and the normalized values are adjusted by scaling and translation parameters, represented as: ; wherein, and are the mean and variance of the current batch, respectively, is a constant; ; where, and are learnable parameters; Dropout regularization: Dropout technique is used to prevent overfitting, denoted as: ; Reflection padding: Reflection padding is used to handle the convolution boundary, denoted as: ; where, is the input feature map, is the feature map after reflection padding, is the index calculation function of reflection padding; Model verification: Binary cross-entropy loss function is used to measure the difference between the probability distribution predicted by the model and the true distribution, denoted as: ; where, is the number of landslide samples, is the true label (0 or 1) of the th landslide sample, is the probability value predicted by the model for the th sample.

[0013] Optionally, the generation of landslide susceptibility feature map and probability regression in S6 comprises: S61, optimization and application of UNet model: applying the optimized UNet-based deep learning model to predict landslide susceptibility areas, extracting the features of landslide areas through multi-layer convolution and operation; S62, generating feature map: generating the feature map of landslide susceptibility area according to the input data , where represents the spatial coordinates; S63, probability regression: processing the generated feature map through Sigmoid layer to calculate the probability of each pixel point belonging to each level of landslide susceptibility, and outputting the landslide susceptibility evaluation result , denoted as: ; where, represents the probability of landslide occurring at coordinate , is the value of the feature map at this position; S64, landslide susceptibility calculation: the probability result calculated through the Sigmoid layer is used to predict the probability value of landslide occurrence corresponding to each pixel point in the image, thereby generating a landslide susceptibility map.

[0014] Optionally, the landslide risk early warning and disaster prevention and mitigation suggestion comprises: Early warning classification: according to the landslide susceptibility evaluation result, a graded risk early warning mechanism is established, when the landslide probability of a certain area is greater than a preset high risk threshold , a red early warning is issued, when the landslide probability of a certain area is between a medium risk threshold and a high risk threshold , a yellow early warning is issued, and when the landslide probability of a certain area is lower than the medium risk threshold , a green early warning is issued. Disaster prevention and mitigation suggestion: for different risk warning areas, corresponding disaster prevention and mitigation suggestions are made, for the red early warning area, it is suggested to strengthen monitoring, evacuate personnel and restrict development activities, for the yellow early warning area, it is suggested to implement engineering control measures and strengthen patrol, and for the green early warning area, it is suggested to carry out routine monitoring and regular evaluation. Advantages of the present application: The present application adopts federated learning technology, each participant can perform joint learning through the locally trained model without sharing the original data, thereby ensuring the privacy and security of the data, which breaks through the bottleneck of traditional centralized data storage and calculation, so that multiple data holders can share knowledge in a distributed environment without exposing sensitive data, the introduction of federated learning enables the method to have strong privacy protection ability and be suitable for fields with high data privacy requirements, such as government agencies and scientific research institutions.

[0015] The present application has excellent feature extraction capability through the UNet-based deep learning model, which can effectively improve the recognition efficiency and accuracy of landslide susceptible areas, the UNet model extracts the features of topography, geology and other influencing factors through multi-layer convolution and pooling operation, thereby more accurately evaluating the possibility of landslide occurrence, through the combination of these advanced technologies, more efficient and accurate landslide susceptibility evaluation can be realized, and the model can be updated in time to cope with new data changes, which has high application value and social benefits. BRIEF DESCRIPTION OF DRAWINGS

[0016] The present application has excellent feature extraction capability through the UNet-based deep learning model, which can effectively improve the recognition efficiency and accuracy of landslide susceptible areas, the UNet model extracts the features of topography, geology and other influencing factors through multi-layer convolution and pooling operation, thereby more accurately evaluating the possibility of landslide occurrence, through the combination of these advanced technologies, more efficient and accurate landslide susceptibility evaluation can be realized, and the model can be updated in time to cope with new data changes, which has high application value and social benefits. BRIEF DESCRIPTION OF DRAWINGS

[0017] ​In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only illustrate the present application, and other drawings can also be obtained by those skilled in the art without creative effort based on these drawings.

[0018] Figure 1 The flowchart of the evaluation method of the embodiment of the present application is shown in the figure. Figure 2 The geographic location and landslide distribution of the research area of B County in the embodiment of the present application are shown in the figure. Figure 3 The geographic location and landslide distribution of the research area of A County in the embodiment of the present application are shown in the figure. Figure 4 The distributed training landslide susceptibility map of the embodiment of the present application is shown in the figure. Figure 5 The non-distributed training landslide susceptibility map of the embodiment of the present application is shown in the figure. Figure 6 The distributed training landslide susceptibility map of the embodiment of the present application is shown in the figure. Figure 7 The non-distributed training landslide susceptibility map of the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0019] The present application will be described in detail below with reference to the drawings and specific embodiments. It should be noted that in order to make the embodiments more detailed, the following embodiments are the best, preferred embodiments, and other alternative ways can also be used by those skilled in the art to implement them; and the drawings are only used to more specifically describe the embodiments, and are not intended to specifically limit the present application.

[0020] It should be noted that in the specification, "one embodiment", "embodiment", "exemplary embodiment", "some embodiments" and the like indicate that the described embodiments can include specific features, structures or characteristics, but not necessarily every embodiment includes the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in combination with an embodiment, it should be within the knowledge of those skilled in the art to realize this feature, structure or characteristic in combination with other embodiments (whether or not explicitly described).

[0021] In general, terms can be understood, at least partly, from usage in the context. For example, depending at least in part on the context, the term "one or more" as used herein can describe any feature, structure, or characteristic in the singular or can describe combinations of features, structures, or characteristics, in the plural, depending at least in part on the context. Additionally, the term "based on" can be understood as not necessarily requiring exclusively derived factors, but instead can allow for the existence of other non expressly recited factors, depending at least in part on the context.

[0022] As shown in Figures 1-7 A landslide susceptibility evaluation method based on federated learning and UNet includes the following steps: Step one, extract the landslide spatial data of the study area: In this embodiment, a region where landslides frequently occur in a certain area is selected as the research object, and A County and B County are focused on for method verification. These areas are known for their complex topography and geological conditions, and frequent seismic activity and heavy rainfall events have led to frequent landslides. Since the earthquake in A County, the combined effects of changes in geological structure and rainfall have further exacerbated landslide risks.

[0023] As shown in Figure 2 Figure 3 Landslide sample data for B County and A County are collected.

[0024] Step two, extract the impact factor information: Impact factor information is extracted from the multi-source data in step one through the ArcGIS platform.

[0025] Step three, build a landslide sample dataset: Obtain historical landslide data and landslide hazard point data; According to the historical landslide data and landslide hazard point data, a landslide sample dataset is constructed. Specifically, by judging the number of landslide grids within a rectangular region, if the number of landslide grids within the region exceeds 50%, the region is marked as a landslide point; if it is less than 50%, it is marked as a non-landslide point; The experimental dataset is randomly divided into a training set and a validation set in a ratio of 8:2, with landslide samples labeled as 1 and non-landslide samples labeled as 0.

[0026] Step four, data augmentation on the landslide sample dataset: The landslide sample dataset is augmented, with the following specific steps: In the landslide sample dataset, identify the grid containing the landslide feature; Apply the Mixup data augmentation technique to randomly splice the selected landslide grid. Specifically, set two landslide samples and , the new sample is generated by the following formula : ; wherein, is a weighting coefficient randomly selected in the interval , used to control the mixing ratio of the two samples; The generated augmented sample is added to the experimental data set to improve the generalization ability and robustness of the model.

[0027] Step five, build a UNet deep learning model and train it: A deep learning model based on UNet is designed to better extract landslide image features. Specifically, the LeakyRelU activation function is used, whose mathematical expression is: ; where is set to 0.01, which ensures the continuous propagation of gradients in the deep network and improves the learning ability of the model. Convolution down-sampling is used instead of max-pooling operation, whose expression is: where is a convolution kernel with a step size of 2, is the bias term, is the activation function, which reduces the feature resolution while retaining more spatial information. In the decoder part, adjacent interpolation up-sampling is used, combined with 1x1 convolution to adjust the number of channels: where is the up-sampling factor, which avoids the checkerboard effect that may be caused by transposed convolution, ensuring the quality of the output feature map. In the Unet network, a normalization layer is introduced, and for input , the normalization formula is: wherein, and are the mean and variance of the current batch, is a small constant, and the normalized value is adjusted by scaling and shifting parameters wherein and are learnable parameters, and Dropout regularization is used: .

[0028] The convolution boundary is handled using reflection padding, and the formula for reflection padding is: wherein is the input feature map, is the feature map after reflection padding, is the index calculation function of reflection padding.

[0029] The binary cross-entropy loss function is used to measure the difference between the predicted probability distribution of the model and the true distribution. Specifically, the loss function is defined as: ; where, is the number of landslide samples, is the true label (0 or 1) of the th landslide sample, is the probability value (between 0 and 1) predicted by the model for the th sample.

[0030] The above UNet model is trained on the landslide data sets of A County and B County for 5 Epochs, and the gradient parameters of the two places are obtained and .

[0031] Step six, establish a secure federated learning framework to ensure data privacy and security: Specifically, a secure communication protocol is established between the two data holders, and federated learning training is performed using landslide data to obtain updated local Unet gradient parameters. During the training process, the gradient parameter update formula of the global Unet model is as follows: ; where, represents the data volume of the th data holder, represents the total amount of all data, is the learning rate, represents the global Unet model in the th round of federated learning, represents the global Unet model in the previous round of federated learning, represents the global gradient function, which performs multiple gradient descent according to the computing power of different data holder devices; During the entire process, the servers of A County and B County always retain the original data, only transmit encrypted model parameters and gradient information, and ensure data privacy and security.

[0032] Step seven: model application and result output The optimized Unet model is applied to the multiple influence factor layer data of landslide susceptibility areas, and high-dimensional features are extracted through multi-layer convolution operation to generate feature maps , where represents the spatial coordinates, then the sigmod layer is used to perform probability regression processing on the feature maps, calculate the probability of each pixel point belonging to each level of landslide susceptibility, and output the landslide susceptibility evaluation results , specifically, the Sigmod function is defined as: where represents the probability of landslide occurring at coordinate , and is the value of the feature map at this location. Finally, a landslide susceptibility map is generated according to these probability values, with the gray value of each pixel corresponding to the landslide probability at that location.

[0033] Table 1 summarizes the distribution of each level in the susceptibility zoning map predicted by the two training methods. In the distribution training prediction results of A county and B county, the distribution training shows certain advantages in landslide susceptibility evaluation, especially in B county, the distribution training significantly improves the prediction accuracy of low susceptibility level areas and reduces the misjudgment of medium and high susceptibility level areas. This is because the distribution training can better utilize the data characteristics of each sub-region, improve the generalization ability of the model, and thus improve the accuracy and reliability of the prediction as a whole.

[0034] Table 1 Statistical analysis of landslide susceptibility zoning Step eight, susceptibility mapping: The specific standards for dividing the initial landslide susceptibility distribution map according to the probability values are as follows: ① Probability value < 50%, indicating low susceptibility area; ② 50% ≤ probability value ≤ 70%, indicating medium susceptibility area; ③ Probability value > 70%, indicating high susceptibility area; According to the results of landslide susceptibility evaluation, a hierarchical early warning mechanism is established: when the landslide probability of a certain area is greater than the preset high-risk threshold , a red warning is issued; between the medium-risk threshold and the high-risk threshold , a yellow warning is issued; below the medium-risk threshold , a green warning is issued. For different risk level areas, corresponding disaster prevention and mitigation suggestions are made: for red warning areas, it is recommended to strengthen monitoring, evacuate personnel, and restrict development activities; for yellow warning areas, it is recommended to implement engineering control measures and strengthen patrol; for green warning areas, it is recommended to carry out routine monitoring and regular assessment. At the same time, the evaluation results are integrated into the geographic information system, providing scientific basis for regional disaster prevention and mitigation planning and decision-making.

[0035] The present application encompasses any alternatives, modifications, equivalent methods and solutions made to the essence and scope of the present application. In order to make the public have a thorough understanding of the present application, specific details are described in the following preferred embodiments of the present application, and the present application can also be fully understood without the description of these details to those skilled in the art. In addition, in order to avoid unnecessary confusion to the essence of the present application, well-known methods, processes, procedures, elements and circuits, etc. are not described in detail.

[0036] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can also be made, which should be considered as the protection scope of the present application.

Claims

1. A landslide susceptibility assessment method based on federated learning and UNet, characterized in that, Includes the following steps: S1, Obtain landslide impact factor data: Collect multiple landslide impact factor data and extract multiple impact factor layer data for landslide-prone areas; S2, Establish a federated learning framework: Establish a federated learning framework among multiple data holders; S3, Design UNet Deep Learning Model: Design a UNet-based deep learning model for landslide susceptibility assessment, and input the data from the influencing factor layer into the model for feature extraction and segmentation; S4, Federated Learning Model Training and Parameter Integration: Under the federated learning framework, a UNet-based deep learning model is trained using a landslide sample dataset, and the model parameters are integrated using a federated averaging algorithm to update the global UNet-based deep learning model. S5, Federated Learning Iteration and Model Optimization: Optimize the parameters of the UNet-based deep learning model through multiple rounds of federated learning iterations; S6, Generate landslide susceptibility feature map and probabilistic regression: Apply the optimized UNet-based deep learning model to generate feature maps of landslide-prone areas, use the Sigmoid layer for probabilistic regression processing, and output the landslide susceptibility evaluation results. S7, Results Verification and Disaster Prevention and Mitigation Recommendations: Verify and evaluate the landslide susceptibility assessment results, and provide landslide risk warnings and disaster prevention and mitigation recommendations based on the assessment results.

2. The landslide susceptibility assessment method based on federated learning and UNet according to claim 1, characterized in that, The multiple landslide influencing factor data in S1 include topographic factors, geological factors, hydrological factors, land cover factors, and climatic factors, among which; The topographical factors include aspect, slope, elevation, and curvature; The geological factors include lithology; The hydrological factors include average annual precipitation and distance from the river system; The land cover factors include enhanced vegetation index, normalized difference vegetation index, surface reflectance, and land use; The climate factors include annual average temperature and surface temperature.

3. The landslide susceptibility assessment method based on federated learning and UNet according to claim 2, characterized in that, The multiple influencing factor layer data in S1 include elevation, slope, aspect, curvature, lithology, distance from water system, and land use.

4. The landslide susceptibility assessment method based on federated learning and UNet according to claim 3, characterized in that, The construction of the landslide sample dataset includes: Data collection: Acquire historical landslide data and data on potential landslide sites; Constructing a landslide sample dataset: Based on historical landslide data and landslide hazard point data, a landslide sample dataset is constructed. By judging the number of landslide grids in a rectangular area, if the number of landslide grids in the rectangular area exceeds 50%, the rectangular area is marked as a landslide point; if it is less than 50%, it is marked as a non-landslide point. The marked landslide sample dataset is defined as the experimental dataset. Divide the dataset into training and validation sets: Randomly divide the experimental dataset into training and validation sets in an 8:2 ratio, with landslide samples labeled as 1 and non-landslide samples labeled as 0. Data augmentation: Data augmentation is performed on the constructed landslide sample data.

5. The landslide susceptibility assessment method based on federated learning and UNet according to claim 4, characterized in that, The data enhancements include: Identify landslide feature grids: Identify the grids for landslide points in the landslide sample dataset; Applying Mixup data augmentation technology: Mixup data augmentation technology is applied to randomly stitch together the grids of the identified landslide points to generate augmented samples, represented as follows: ； in, For the generated enhanced samples, It is in the interval Weighting coefficients selected randomly within the range, and For landslide samples; Add augmented samples to the experimental dataset: Add the generated augmented samples to the experimental dataset.

6. The landslide susceptibility assessment method based on federated learning and UNet according to claim 5, characterized in that, The parameter update of the global UNet-based deep learning model is represented as follows: ； in, Indicates the first The amount of data held by each data holder This represents the total amount of all data. For learning rate, Indicates the first UNet-based deep learning models in federated learning rounds This refers to the UNet-based deep learning model from the previous round of federated learning. This represents the global gradient function.

7. The landslide susceptibility assessment method based on federated learning and UNet according to claim 6, characterized in that, The training of the UNet-based deep learning model includes: Setting the activation function: LeakyReLU is selected as the activation function for each convolutional layer in the UNet-based deep learning model, expressed as: ； in, It is 0.01; Model training: Applying weight-based learning in the convolutional layers, represented as: ； in, A convolution kernel with a stride of 2. For bias terms, For activation functions; Normalization: Multiple landslide influencing factor data are used as input data, and a normalization layer is introduced to normalize the input data. Normalization is performed, and the normalized values ​​are adjusted using scaling and translation parameters, as follows: ； in, and These are the mean and variance of the current batch, respectively. It is a constant; ； in, and These are learnable parameters; Dropout regularization: Uses the Dropout technique to prevent overfitting, expressed as: ； Reflection padding: Reflection padding is used to handle convolution boundaries, represented as: ； in, For the input feature map, This is the feature map after reflection filling. It is the index calculation function for reflection fill; Model validation: The binary cross-entropy loss function is used to measure the difference between the model's predicted probability distribution and the true distribution, expressed as: ； in, It is the number of landslide samples. It is the first The true label of a landslide sample It is the model's prediction of the first The probability value of each sample.

8. The landslide susceptibility assessment method based on federated learning and UNet according to claim 7, characterized in that, The generation of landslide susceptibility feature maps and probability regression in S6 includes: S61, Optimization and Application of UNet Model: The optimized UNet-based deep learning model is applied to predict landslide-prone areas, and features of landslide areas are extracted through multi-layer convolution and operations. S62, Generate Feature Map: Based on the input data, generate feature maps of landslide-prone areas. ,in Represents spatial coordinates; S63, Probabilistic Regression: The generated feature map is processed through a Sigmoid layer to calculate the probability of each pixel belonging to each level of landslide susceptibility, and the landslide susceptibility assessment result is output. , represented as: ； in, Representing coordinates The probability of a landslide occurring at a certain location. The value of the feature map at that location; S64, Calculate landslide susceptibility: Using the probability results calculated by the Sigmoid layer, predict the probability value of landslide occurrence for each pixel in the image, thereby generating a landslide susceptibility map.

9. The landslide susceptibility assessment method based on federated learning and UNet according to claim 8, characterized in that, The landslide risk warning and disaster prevention and mitigation recommendations include: Early warning tiers: Based on the landslide susceptibility assessment results, a tiered risk early warning mechanism is established. When the probability of a landslide in a certain area... Greater than the preset high-risk threshold A red alert is issued when the probability of a landslide in a certain area is high. Between medium risk threshold and high risk threshold A yellow alert is issued when the probability of a landslide in a certain area is between [a certain point in time]. Below the medium risk threshold A green alert will be issued at that time; Disaster prevention and mitigation recommendations: For different risk warning areas, corresponding disaster prevention and mitigation recommendations are formulated. For red warning areas, it is recommended to strengthen monitoring, evacuate people, and restrict development activities. For yellow warning areas, it is recommended to implement engineering control measures and strengthen patrols. For green warning areas, it is recommended to carry out routine monitoring and periodic assessments.

Images