A multi-scale seismic landslide hazard assessment method based on artificial intelligence

Abstract

The present invention relates to the technical field of geological disaster prediction and evaluation, and specifically discloses a multi-scale seismic landslide hazard assessment method based on artificial intelligence. First, ground motion time histories, high-resolution topography, geotechnical parameters, and monitoring data at the single slope scale, as well as ground motion intensity parameter zoning, medium- and low-resolution digital elevation models, geological structures, etc. at the regional slope scale are collected and sorted out; a regional-scale seismic landslide hazard prediction model is established based on the gradient boosting decision tree algorithm to obtain the probability of regional seismic landslide hazard; for high-risk areas, the improved Newmark slider method is used to analyze the instability of single slopes to obtain the slope instability probability; through regional-scale hazard assessment and single-slope stability assessment, "single body-region" and "region-single body" hierarchical integration mechanisms are respectively constructed to realize the dynamic assessment of single-body-region cross-scale seismic slope hazards.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster prediction and evaluation, and particularly relates to a multi-scale seismic landslide hazard assessment method based on artificial intelligence. Background Technique

[0002] Landslides are one of the main forms of earthquake-induced geological disasters. Especially under the action of strong earthquakes, the distribution and scale of landslide disasters in complex mountainous terrains have a high degree of uncertainty.

[0003] At the regional scale, scholars have conducted a lot of research. Scholars from institutions such as the China Earthquake Administration, the National Institute of Disaster Prevention of the Ministry of Emergency Management, the United States Geological Survey, Southwest Jiaotong University, and Chengdu University of Technology have proposed multiple slope hazard assessment models based on physical mechanics and data analysis methods. In 2000, Jibson et al. (2000) combined GIS to evaluate the slope hazard impact area of the 1994 Northridge earthquake in the United States and proposed to use the Weibull function to analyze the relationship between permanent displacement and slope hazard probability. With the development of artificial intelligence technology, machine learning models have begun to show significant advantages in landslide hazard prediction, especially in the processing ability of large-scale data. However, these data-driven models usually lack an understanding of physical mechanisms and the interpretability of prediction results, which affects their credibility and universality in practical applications.

[0004] In the existing related technical research, the inventor found that seismic landslide assessment models are mainly based on single-scale analysis, lacking the coupled analysis of regional scale and single slope scale, and it is difficult to effectively reflect the comprehensive effects of multi-source data such as earthquake sources, terrain, and geotechnical characteristics. There are still deficiencies in the multi-scale integration of traditional models, and the refined research at the single scale does not match the wide-area research at the regional scale. Therefore, the present invention aims to solve the problems of low efficiency and limitations in landslide prediction in strong earthquake mountainous areas, and proposes a multi-scale seismic landslide hazard assessment method based on artificial intelligence. Summary of the Invention

[0005] To solve the problems existing in the prior art, the present invention provides a multi-scale seismic landslide hazard assessment method based on artificial intelligence, which is a multi-scale seismic landslide hazard intelligent assessment method by integrating a single-slope scale model and a regional-scale model, and is particularly suitable for the dynamic assessment of slope hazard in strong earthquake mountainous areas, solving the problems mentioned in the above background technique.

[0006] To achieve the above object, the present invention provides the following technical solution: A multi-scale seismic landslide hazard assessment method based on artificial intelligence, comprising the following steps:

[0007] S1. Multi-scale data collection and data processing;

[0008] S2. Regional-scale seismic landslide hazard assessment;

[0009] S3. Single-scale seismic slope stability analysis;

[0010] S4. Construct a multi-scale evaluation framework and dynamic correction.

[0011] Preferably, in step S1, historical seismic landslide data worldwide are collected. According to the spatial location of the landslides, data including ground motion data, topography, geology, and deformation are collected respectively from the single-scale and regional scales.

[0012] Preferably, at the single scale, it specifically includes the following:

[0013] A. Collect historical ground motion time history data, including ground motion acceleration time history, velocity time history, and displacement time history; calculate energy-based ground motion intensity parameters including Arias intensity and pulse energy rate based on the ground motion time history;

[0014] B. Collect high-resolution topographic data through UAV aerial photography or lidar, including slope geometry parameters such as slope, aspect, and slope height;

[0015] C. Collect geological data to obtain geotechnical mechanical parameters of the slope, including cohesion, internal friction angle, and unit weight;

[0016] D. Obtain dynamic change information of stress, displacement, or dip angle through existing on-site monitoring data of slopes.

[0017] Preferably, at the regional scale, it specifically includes the following:

[0018] 1) Conduct spatial interpolation analysis through GIS to obtain the ground motion zoning map of the study area, including peak acceleration and peak velocity;

[0019] 2) Based on the national geospatial database and NASA platform, obtain medium- and low-resolution topographic data, including data on regional slope, aspect, and slope height;

[0020] 3) Obtain regional geological structure information, including fault distribution and lithology grouping;

[0021] 4) Obtain satellite remote sensing data, including data on ground subsidence and surface deformation.

[0022] Preferably, in step S2, it specifically includes the following:

[0023] S21. Extract various types of regional-scale seismic data, topography, geology and deformation data as influencing factors, and perform [0,1] standardization on all data; obtain the correlation values ​​between factors through bivariate correlation analysis, and retain factors with correlations with other influencing factors less than 0.8 as input eigenvalue variables;

[0024] Whether a landslide occurs is taken as the target value, with 1 being the occurrence of a landslide and 0 being the non-occurrence of a landslide; the characteristic value variables and the target values ​​are aggregated to form a data set;

[0025] S22, based on the gradient boosting decision tree algorithm, establish an earthquake landslide hazard assessment model, first select the logarithmic loss function as the algorithm objective function, set the model's hyperparameters, including learning rate, maximum depth, and number of numbers; divide the data set of step S21 into a training set, a validation set, and a test set according to a 6:2:2 ratio, train the model with the test set data, evaluate the model performance with the validation set, adjust the hyperparameters, and calculate the model's evaluation indicators based on the test set, including accuracy, AUC value, and precision; finally output the landslide hazard probability P region .

[0026] Preferably, in step S22, according to the risk probability P region The danger level is divided into two categories: the extremely high danger zone is defined as the danger probability greater than 80%, the high danger zone is defined as 60%-80%, the medium danger zone is defined as 40%-60%, the low danger zone is defined as 20%-40%, and the extremely low danger zone is defined as the danger probability less than 20%.

[0027] Preferably, in step S3, various types of ground motion data, topography, and geological data at a monomer scale are extracted, and the permanent displacement of the slope is calculated based on the improved dynamic slider method in combination with the ground motion time history, the geometric characteristics of the slope, and the mechanical parameters of the rock and soil body. The calculation formula is as follows:

[0028]

[0029] Among them, D N is the permanent displacement of the slope; a(t) is the earthquake acceleration time history; a c is the initial critical acceleration of the slope; t is the time;

[0030] Based on the relationship between the permanent displacement of the slope and the probability of slope instability established by the Weibull function, the slope instability probability P is calculated. instable , and its calculation formula is as follows:

[0031]

[0032] Preferably, in step S4, a multi-scale evaluation framework of "monomer-region" and "region-monomer" is constructed through regional-scale seismic landslide hazard assessment and single-scale seismic slope stability analysis, and the dynamic correction of the evaluation results is realized.

[0033] Preferably, in step S4, it specifically includes the following steps:

[0034] S41. "Monomer-region" cross-scale evaluation:

[0035] Through the regional-scale seismic landslide hazard assessment in step S2, extremely high hazard areas are obtained, and the number of extremely high hazard slopes in this area is identified and used as single slopes respectively.

[0036] Obtain the characteristic values of these single scales, including seismic ground motion acceleration time history, velocity time history, slope, and geotechnical parameters, and then substitute them into the single-scale seismic slope stability analysis in step S3 to obtain the instability probability of these single slopes with higher hazards.

[0037] S42. In a certain research area, the characteristic values of individual single slopes can be obtained, including seismic ground motion acceleration time history, velocity time history, slope, and geotechnical parameters. Based on the single-scale seismic slope stability analysis method in step S3, the instability probability of these single slopes is obtained, and this probability value is normalized.

[0038] Then, through step S2, the seismic landslide hazard probability of this research area is obtained, and the instability probability of the single slope is used to correct the corresponding landslide hazard probability in space within this area, and the corrected regional seismic landslide hazard probability value can be obtained. The calculation formula is as follows:

[0039]

[0040] Among them, is the corrected seismic landslide hazard probability; α is the correction intensity, taking values between 0 and 1, 1 means directly replacing the hazard probability of the corresponding slope in the area with the instability probability of the single slope, and 0 means no correction.

[0041] Preferably, in step S42, the normalization means that when P instable = 0.335, the normalized probability value is 1.

[0042] The beneficial effect of the present invention is that the present invention combines a single-scale model and a regional-scale model, and through regional-scale hazard assessment and single-slope stability assessment, a hierarchical integration mechanism of "monomer-region" and "region-monomer" is constructed respectively to realize the dynamic evaluation of the cross-scale seismic slope hazard of monomer-region. Description of the Drawings

[0043] Figure 1Schematic flow chart of the multi-scale seismic landslide hazard assessment method based on artificial intelligence in the embodiments of the present invention. Detailed implementation manners

[0044] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0045] The present invention provides a technical solution: a multi-scale seismic landslide hazard assessment method based on artificial intelligence, as Figure 1 shown, including the following steps:

[0046] S1. Multi-scale data collection and data processing.

[0047] In step S1, historical seismic landslide data worldwide is collected, and data including ground motion data, topography, geology, and deformation is collected respectively from the single-body scale and the regional scale according to the spatial location of the landslide. As shown in Table 1:

[0048] Table 1 Data types at the single-body scale and the regional scale

[0049] Data type Single slope scale Regional slope scale Ground motion data Ground motion time history data Ground motion zoning map Topographic data High-resolution topographic data Medium- and low-resolution topographic data Geological data Geomechanical parameters of rock and soil mass Regional geological structure map Deformation data Monitoring data Remote sensing data

[0050] The acquisition methods of the two types of data are as follows:

[0051] At the single-body scale, specifically, it includes the following:

[0052] A. Collect historical ground motion time history data, including ground motion acceleration time history, velocity time history, and displacement time history, based on channels such as the China Earthquake Networks Center and the Pacific Earthquake Engineering Research Center; calculate ground motion intensity parameters based on energy, including Arias intensity and pulse energy rate, based on the ground motion time history;

[0053] B. Collect high-resolution topographic data, including slope geometry parameters such as slope, aspect, and slope height, through unmanned aerial vehicle (UAV) aerial photography or light detection and ranging (LiDAR);

[0054] C. Collect geological data according to literature materials to obtain geotechnical mechanical parameters of the slope, including cohesion, internal friction angle, and unit weight;

[0055] D. Obtain dynamic change information of stress, displacement, or inclination angle through existing on-site monitoring data of slopes.

[0056] At the regional scale, specifically, it includes the following:

[0057] 1) Based on seismic monitoring stations, spatial interpolation analysis is carried out through GIS to obtain the seismic ground motion zoning map of the study area, including peak ground acceleration (PGA), peak ground velocity (PGV), etc.;

[0058] 2) Based on platforms such as the national geospatial database and NASA, medium- and low-resolution terrain data are obtained: such as digital elevation model (DEM). Based on GIS software, the DEM data are processed, including data on regional slope, aspect, and slope height;

[0059] 3) Regional geological structure information, including fault distribution and lithology grouping, can be obtained through the National Geological Archives of China and the One geology Global platform;

[0060] 4) Through public platforms such as USGS Earth Explorer and ESA Copernicus Open Access Hub, satellite remote sensing data such as Landsat and Sentinel are obtained; based on ENVI (Environment for Visualizing Images) software, data processing is carried out to obtain data such as land subsidence and surface deformation.

[0061] For single-body data, the time history data are time-aligned based on the seismic ground motion time; for regional data, the regional data are spatially aligned using GIS based on longitude and latitude coordinates to ensure that all data have the same projection coordinate system and the same spatial resolution.

[0062] S2. Regional-scale seismic landslide hazard assessment.

[0063] In step S2, it specifically includes the following:

[0064] S21. Based on the historical seismic landslide data collected in step S1, various types of seismic ground motion data, terrain, geology, and deformation data at the regional scale are extracted as influencing factors, and all data are normalized to [0,1]; through bivariate correlation analysis, the correlation values between the factors are obtained, and the factors with a correlation less than 0.8 with other influencing factors are retained as the input characteristic value variables;

[0065] Whether a landslide occurs is used as the target value, where a landslide occurrence is 1 and no landslide is 0; the characteristic value variables and the target value are summarized to form a data set;

[0066] S22. Based on the Gradient Boosting Decision Tree (GBDT) algorithm, establish a seismic landslide hazard assessment model. First, select the Logarithmic Loss function as the algorithm objective function, and set the hyperparameters of the model, including the learning rate, maximum depth, and number of trees. Divide the dataset in step S21 into a training set, a validation set, and a test set according to the ratio of 6:2:2. Use the test set data for model training, evaluate the model performance with the validation set, adjust the hyperparameters, and calculate the evaluation metrics of the model based on the test set, including accuracy, AUC value, and precision. Finally, output the landslide hazard probability P region .

[0067] According to the hazard probability P region conduct a hazard level division. Set the hazard probability greater than 80% as the extremely high hazard area, 60%-80% as the high hazard area, 40%-60% as the medium hazard area, 20%-40% as the low hazard area, and less than 20% as the extremely low hazard area.

[0068] S3. Analysis of the seismic slope stability at the single - scale level.

[0069] In step S3, extract various ground motion data, topographic, and geological data at the single - scale level, including ground motion time history, detailed slope geometric features (slope, aspect, height, etc.), and geotechnical mechanical parameters (cohesion, internal friction angle, unit weight, etc.). Based on the improved dynamic sliding block method, combine the ground motion time history, slope geometric features, and geotechnical mechanical parameters to calculate the permanent displacement of the slope. The calculation formula is as follows:

[0070]

[0071] where D N is the permanent displacement value of the slope, in cm; a(t) is the ground motion acceleration time history, in g; a c is the initial critical acceleration of the slope, in g; t is the time, in s;

[0072] Based on the relationship between the permanent displacement of the slope and the slope instability probability established by the Weibull function, calculate the slope instability probability P instable , and its calculation formula is as follows:

[0073]

[0074] In the formula, 0.335 is the maximum value of the slope instability probability, and - 0.048 and 1.565 are coefficients; this value may change according to the different historical landslide data used.

[0075] S4. Construct a multi - scale evaluation framework and dynamic correction.

[0076] The requirements for data refinement at the monomer scale and regional scale are different, see Table 2:

[0077] Table 2 Comparison of data at the monomer scale and regional scale

[0078] Single slope scale Regional slope scale Ground motion acceleration time history Peak acceleration Ground motion velocity time history Peak velocity Slope gradient and aspect (refined) Slope gradient and aspect (10m resolution) Geomechanical parameters of rock and soil mass Lithological grouping Probability of slope instability Hazard level

[0079] The calculation of single slopes is more sophisticated and complex, and its evaluation results are more accurate. However, if a single-scale earthquake slope stability analysis is to be performed on all slopes in a large area, it will take a lot of time and computing resources. On the contrary, for the regional scale, its data acquisition is easier and rougher, and the evaluation results are less accurate than those of single slopes, but its efficiency is higher. Therefore, in order to ensure both calculation accuracy and efficiency. Through regional-scale earthquake landslide hazard evaluation and single-scale earthquake slope stability analysis, a multi-scale evaluation framework of "single-region" and "region-single" is constructed, and dynamic correction of evaluation results is achieved. Specifically, it includes the following:

[0080] S41. “Single-region” cross-scale evaluation:

[0081] Through the regional-scale earthquake landslide hazard assessment in step S2, an extremely high-hazard area (hazard probability greater than 80%) is obtained, and the number of extremely high-hazard slopes in the area is identified as individual slopes;

[0082] Obtain these single-scale characteristic values, including earthquake acceleration time history, velocity time history, slope and rock and soil parameters, and then bring them into the single-scale seismic slope stability analysis in step S3 to obtain the instability probability of these highly dangerous single slopes. Through the real-time update of remote sensing data, seismic load data, etc. at the regional scale, the regional scale seismic slope hazard map can be updated at the same time, thereby completing the refined dynamic evaluation of single slopes.

[0083] S42. In a certain study area, the characteristic values ​​of individual single slopes can be obtained, including earthquake acceleration time history, velocity time history, slope, and rock and soil parameters. Based on the single-scale earthquake slope stability analysis method in step S3, the instability probability of these single slopes is obtained, and the probability value is normalized (when P instable =0.335, the normalized probability value is 1);

[0084] Then, the earthquake landslide hazard probability of the study area is obtained through step S2, and the landslide hazard probability corresponding to the space in the area is corrected by the normalized instability probability of the single slope, so that the corrected regional earthquake landslide hazard probability value can be obtained. The calculation formula is as follows:

[0085]

[0086] in, It is the probability of earthquake landslide hazard after correction; α is the correction intensity, with a value between 0 and 1. 1 means directly replacing the hazard probability of the corresponding slope in the area with the instability probability of a single slope, and 0 means no correction.

[0087] The present invention combines a single - scale model and a regional - scale model, and through regional - scale hazard assessment and single - slope stability assessment, respectively constructs a hierarchical integration mechanism of "single - region" and "region - single", to achieve dynamic assessment of cross - scale earthquake slope hazard of single - region.

[0088] It should be noted that in this text, the term "including", "comprising" or any other variant thereof is intended to cover non - exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the said element.

[0089] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise.

[0090] It should be understood that the term "and / or" used herein is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this text generally represents an "or" relationship between the front and rear associated objects.

[0091] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0092] The "first / second" mentioned in the embodiments is only used to distinguish similar objects and does not represent a specific order for the objects. It can be understood that the "first / second" can be interchanged in a specific order or sequence when permitted. It should be understood that the objects distinguished by the "first / second" can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0093] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A multi-scale seismic landslide hazard assessment method based on artificial intelligence, characterized in that, It includes the following steps: S1. Multi-scale data collection and data processing; S2. Regional-scale seismic landslide hazard assessment; S3. Single-scale seismic slope stability analysis; S4. Construct a multi-scale evaluation framework and dynamic correction; through the regional-scale seismic landslide hazard assessment and single-scale seismic slope stability analysis, construct a multi-scale evaluation framework of "single body-region" and "region-single body", and realize the dynamic correction of the evaluation results; specifically including the following steps: S41. "Single body-region" cross-scale evaluation: Through the regional-scale seismic landslide hazard assessment in step S2, obtain the extremely high hazard areas, identify the number of extremely high hazard slopes in this area, and take them as single slopes respectively; Obtain the characteristic values of these single scales, including the seismic ground motion acceleration time history, velocity time history, slope and geotechnical parameters, and then substitute them into the single-scale seismic slope stability analysis in step S3, that is, obtain the instability probability of these single slopes with higher hazards; S42. In a certain study area, the characteristic values of individual single slopes can be obtained, including the seismic ground motion acceleration time history, velocity time history, slope, and geotechnical parameters. Based on the single-scale seismic slope stability analysis method in step S3, obtain the instability probability of these single slopes, and normalize this probability value; Then, through step S2, obtain the seismic landslide hazard probability of this study area, and correct the landslide hazard probability corresponding to the space in this area with the normalized instability probability of the single slope, and then the corrected regional seismic landslide hazard probability value can be obtained. The calculation formula is as follows: Among them, is the probability of earthquake-induced landslide hazard after correction; P region is the probability of landslide hazard; P instable is the probability of slope instability; α is the correction intensity, with a value between 0 and 1. 1 means directly replacing the hazard probability of the corresponding slope in the area with the probability of single slope instability, and 0 means no correction.

2. The multi-scale seismic landslide hazard assessment method based on artificial intelligence according to claim 1, wherein: In step S1, collect historical seismic landslide data worldwide, and collect data including seismic ground motion data, topography, geology, and deformation from the single-scale and regional scales respectively according to the spatial location of the landslides.

3. The multi-scale seismic landslide hazard assessment method based on artificial intelligence according to claim 2, wherein: At the single scale, specifically including the following: A. Collect historical seismic ground motion time history data, including seismic ground motion acceleration time history, velocity time history, and displacement time history; calculate the energy-based seismic ground motion intensity parameters including Arias intensity and pulse energy rate based on the seismic ground motion time history; B. Collect high-resolution topographic data through UAV aerial photography or lidar, including slope geometric parameters such as slope, aspect, and slope height; C. Collect geological data and obtain the geotechnical mechanical parameters of the slope, including cohesion, internal friction angle, and unit weight; D. Obtain the dynamic change information of stress, displacement, or dip angle through the existing on-site monitoring data of the slope.

4. The multi-scale seismic landslide hazard assessment method based on artificial intelligence according to claim 2, characterized in that: At the regional scale, specifically including the following: 1) Through GIS spatial interpolation analysis, obtain the seismic ground motion zoning map of the study area, including peak acceleration and peak velocity; 2) Based on the national geospatial database and NASA platform, obtain medium- and low-resolution topographic data, including data on regional slope, aspect, and slope height; 3) Obtain regional geological structure information, including fault distribution and lithology grouping; 4) Obtain satellite remote sensing data, including data on ground settlement and surface deformation.

5. The multi-scale seismic landslide hazard assessment method based on artificial intelligence according to claim 1, wherein: In step S2, specifically including the following: S21. Extract various seismic ground motion data, topography, geology, and deformation data at the regional scale as influencing factors, and perform [0,1] standardization processing on all data; Through bivariate correlation analysis, the correlation values between factors are obtained, and the factors with a correlation less than 0.8 with other influencing factors are retained as the input eigenvalue variables; Whether a landslide occurs is taken as the target value, where a landslide occurrence is 1 and no landslide is 0; the eigenvalue variables and the target value are summarized to form a data set; S22. Based on the gradient boosting decision tree algorithm, an earthquake landslide hazard assessment model is established. First, the logarithmic loss function is selected as the algorithm objective function, and the hyperparameters of the model are set, including the learning rate, maximum depth, and number of trees; Divide the dataset in step S21 into a training set, a validation set, and a test set according to a ratio of 6:2:

2. Use the test set data for model training, evaluate the model performance using the validation set, perform hyperparameter tuning, and calculate the evaluation metrics of the model based on the test set, including accuracy, AUC value, and precision. Finally, output the landslide hazard probability P region 。 6. The multi-scale seismic landslide hazard assessment method based on artificial intelligence according to claim 5, wherein: In step S22, according to the risk probability P region perform risk level classification. Set the risk probability greater than 80% as the extremely high risk area, 60% - 80% as the high risk area, 40% - 60% as the medium risk area, 20% - 40% as the low risk area, and less than 20% as the extremely low risk area.

7. The multi-scale seismic landslide hazard assessment method based on artificial intelligence according to claim 1, characterized in that: In step S3, various types of ground motion data, topographic, and geological data at the single - body scale are extracted. Based on the improved dynamic slider method, the permanent displacement of the slope is calculated by combining the ground motion time history, slope geometric characteristics, and geotechnical mechanical parameters. The calculation formula is as follows: Among them, D N is the permanent displacement value of the slope; a(t) is the acceleration time history of ground motion; a c is the initial critical acceleration of the slope; t is the time; Based on the relationship between the permanent displacement of the slope and the probability of slope instability established by the Weibull function, the probability of slope instability \(P\) is calculated instable , and its calculation formula is as follows:

8. The multi-scale seismic landslide hazard assessment method based on artificial intelligence according to claim 1, characterized in that: In step S42, the normalization means that when P instable = 0.335, the normalized probability value is 1.

Images