A coastal geological stability evaluation system

Abstract

The present invention relates to the technical field of coastal geological data analysis, specifically a coastal geological stability evaluation system, the system includes: a geological data partition identification module collects geological monitoring data, summarizes all geological monitoring data into GIS, extracts features from geological monitoring data, obtains a coastal feature set, divides the coastal feature set into different regions according to location in geographic space, calculates partition purity by conditional information entropy, takes the partition with the highest purity as the judgment standard, gradually refines other partitions with purity lower than the judgment standard, and generates a partition geological structure description set. In the present invention, a refined expression of geological features is achieved through a partition refinement method based on information entropy. The accuracy of geological feature analysis is effectively improved, avoiding possible regional feature confusion problems. In the instability risk classification, the linkage analysis of key features improves the coverage and recognition ability of classification results for various types of geological instability.

Description

Technical Field

[0001] The invention relates to the technical field of coastal zone geological data analysis, and in particular to a coastal zone geological stability evaluation system. Background Art

[0002] The Coastal Zone Geological Stability Assessment System is a system for analyzing geological data in the coastal zone, aiming to assess the geological stability and potential risks of the coastal zone. The system integrates geological survey data, remote sensing information and monitoring data, and combines intelligent algorithms and models to provide accurate geological stability analysis, risk warnings and management recommendations. Its main uses include guiding coastal engineering construction, disaster risk prevention and control, land use planning and the formulation of ecological protection strategies, in order to provide efficient technical support and data services.

[0003] It is difficult for existing technologies to achieve dynamic adjustments for the differences in geological features in regional division, which may lead to fuzzy feature expression or cross-regional phenomena in complex coastal areas. For example, in areas with large changes in geological characteristics, there may be multiple features that are simply attributed to the same area, reducing the accuracy of regional division. In terms of instability type analysis, traditional methods usually use a single indicator or static threshold, which makes it difficult to obtain the dynamic relationship between geological characteristics and time, and is prone to deviations in the identification of instability modes such as landslides, mudslides, and collapses. For example, identifying landslide risks only by the slope change rate may ignore the indirect impact of the rapid increase in soil moisture on instability. In extreme event assessment, it is also difficult to accurately predict the triggering conditions under the combined effects of factors such as rainfall and earthquakes. For example, in some areas, evaluating the rainfall threshold alone may underestimate the actual risk after the superposition of multiple disasters, limiting the comprehensiveness and effectiveness of risk prevention and control. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a coastal zone geological stability evaluation system.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme: A coastal zone geological stability evaluation system comprises:

[0006] The geological data partition identification module collects geological monitoring data, summarizes all geological monitoring data into GIS, extracts features from geological monitoring data, obtains coastal zone feature sets, divides coastal zone feature sets into different regions according to location in geographic space, calculates partition purity through conditional information entropy, takes the partition with the highest purity as the judgment standard, and gradually refines other partitions with purity lower than the judgment standard to generate a partition geological structure description set;

[0007] The instability mode classification module is based on the sub-region geological structure description set, and by monitoring the records of the changes of each feature in the coastal zone feature set over time, identifies and classifies the instability type of the data of each sub-region, obtains the instability mode classification result, and according to the instability mode classification result, refers to the preset risk threshold, conducts risk assessment on the high-risk instability type area, and generates the sub-region instability risk assessment optimization result;

[0008] The extreme event condition assessment module collects historical extreme event data based on the optimization results of the partition instability risk assessment, and performs time series segmentation to obtain an extreme event data set. The frequency and intensity of extreme events in the extreme event data set are modeled through generalized Pareto distribution, and the triggering critical conditions of geological disasters are identified to obtain a triggering condition critical value set. According to the triggering condition critical value set, the joint impact of different extreme events is calculated to generate extreme event impact data analysis results;

[0009] The geological structure impact assessment module conducts a comprehensive evaluation of the overall geological stability of the coastal area based on the analysis results of the extreme event impact data, calibrates the spatial scope and risk sources of each risk level area, and generates a comprehensive stability evaluation result of the coastal geological data.

[0010] As a further solution of the present invention, the steps of obtaining the coastal zone feature set are specifically as follows:

[0011] Based on the geological monitoring data obtained by monitoring equipment, the data scale is unified by recording and clearing abnormal data to generate a standardized geological monitoring data set;

[0012] Based on the standardized geological monitoring data set, characteristic points in the geological monitoring data are extracted, and a coastal zone characteristic set is generated by recording the changes of the target characteristic points in space and time and integrating the characteristic values.

[0013] As a further solution of the present invention, the steps of obtaining the sub-region geological structure description set are specifically as follows:

[0014] Recording the geographic coordinates of each feature point in the coastal zone feature set, mapping the geographic coordinates of the feature points to the geographic space, visually displaying the distribution of the feature points, dividing the regions according to the distribution of the feature points, recording the feature information of each partition, and generating a geographic space data set;

[0015] Set the set of feature points in the geospatial dataset to , using the formula:

[0016]

[0017] Compute partitions Conditional information entropy , generate partition purity information analysis results;

[0018] in, Used to quantify the partitions in geospatial datasets Each feature point category The distribution probability of , and the concentration of category distribution, is the feature point category Partitioning in Geospatial Datasets The conditional probability in Used to measure the amount of information of feature point categories. Is a geospatial dataset partition The category index value of the feature point in , Is a geospatial dataset partition The total number of categories of all feature points in ;

[0019] According to the analysis results of the partition purity information, the partition with the highest purity is used as the judgment standard, the feature points of the partitions with purity lower than the judgment standard are refined, and the regions are re-divided by checking the spatial distribution of the feature point categories within the partitions until the purity of all partitions reaches the target value or the data volume is insufficient, and a partition geological structure description set is generated.

[0020] As a further solution of the present invention, the step of obtaining the instability mode classification result is specifically:

[0021] Based on the sub-area geological structure description set, the characteristic point data in each sub-area are recorded in time series, and the characteristic point data are sorted into time series tables or trend graphs by sub-area, and archived to generate a dynamic coastal zone characteristic record data set;

[0022] Based on the dynamic coastal zone characteristic record data set, by analyzing the temporal variation trend of the characteristic point data, the instability type of the characteristic points in each partition is identified and classified to generate an instability mode classification result.

[0023] As a further solution of the present invention, the steps for obtaining the optimization results of the partition instability risk assessment are specifically as follows:

[0024] For the instability mode classification result, the characteristic points in the partition are divided into a low instability risk area and a high instability risk area with reference to a preset risk threshold, and an identification result of the high instability risk area is generated;

[0025] Based on the identification results of the high instability risk areas, the confusion matrix is ​​used to compare and analyze the classification results of the high instability risk areas with the actual instability situation, and the sample data of correct classification, misclassification and missed classification are recorded. The classification standard of the high instability risk areas is adjusted to generate the optimized results of the partitioned instability risk assessment.

[0026] As a further solution of the present invention, the step of acquiring the trigger condition critical value set is specifically:

[0027] Based on the optimization results of the zoning instability risk assessment, historical extreme event data related to high-risk instability types of areas are collected, including rainfall, wave height, and earthquake intensity information, and the historical extreme event data are screened and time series segmented to generate an extreme event data set;

[0028] Based on the extreme event dataset, the frequency and intensity of each type of extreme event are modeled through generalized Pareto distribution. According to the extreme event records in the high-risk instability type area, the starting wave height threshold, magnitude intensity threshold, and starting rainfall threshold are preset to judge the triggering of critical conditions and generate a trigger condition critical value set.

[0029] As a further solution of the present invention, the steps for obtaining the extreme event impact data analysis results are specifically as follows:

[0030] Based on the trigger condition critical value set, the formula is used:

[0031]

[0032] Calculate the trigger condition critical value concentration, rainfall , Waves and earthquake Joint probability of simultaneous occurrence , get the probability data of joint impact;

[0033] in, is the probability of a rainfall event calculated based on the initial rainfall threshold in the trigger condition critical value set. is the probability of a wave triggering event under the condition of a rainfall event calculated based on the initial wave height threshold in the trigger condition critical value set. It is the probability of an earthquake triggering event under the conditions of rainfall and sea wave events calculated based on the starting magnitude intensity threshold in the trigger condition critical value set;

[0034] Based on the probability data of the joint impact and combined with the geographical characteristics of the sub-regions, the potential impact scope of extreme events in each sub-region is evaluated to generate extreme event impact data analysis results.

[0035] As a further solution of the present invention, the steps for obtaining the comprehensive stability evaluation results of the coastal geological data are specifically as follows:

[0036] Based on the joint probability of each partition in the extreme event impact data analysis results, the formula is used:

[0037]

[0038] Calculating the stability score of coastal geology , get the stability score of coastal geology;

[0039] in, The value range is ;

[0040] Based on the stability score of the coastal geology, a comprehensive evaluation is conducted on the overall geological stability of the coastal area, the spatial range and stability level of the sub-areas are calibrated in turn, the geological stability of the sub-areas are represented on the GIS map, and the comprehensive stability evaluation results of the coastal geological data are generated.

[0041] Compared with the prior art, the advantages and positive effects of the present invention are:

[0042] In the present invention, a refined expression of geological features is achieved through a partition refinement method based on information entropy. The accuracy of geological feature analysis is effectively improved, avoiding the problem of regional feature confusion that may be caused. In the classification of instability risk, a multi-mode instability type identification method is adopted for the linkage analysis of key features such as slope change rate, soil moisture content and groundwater velocity change rate, which significantly improves the coverage and recognition ability of the classification results for various types of geological instability, and also optimizes the adjustment strategy of misclassified samples, further improving the reliability of classification. In the analysis of extreme event conditions, the trigger condition modeling is carried out using the generalized Pareto distribution, which reveals the critical conditions of the superposition of different extreme events, and accurately calculates the scope and intensity of the joint impact, making the management and control of high-risk areas more comprehensive. Therefore, the system significantly improves the scientificity of data processing and the accuracy of geological stability evaluation through in-depth processing and comprehensive analysis of multidimensional geological data, providing more effective data support for the identification and management of high-risk areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a system flow chart of the present invention;

[0044] Figure 2 A flow chart for obtaining a coastal zone feature set for the present invention;

[0045] Figure 3 A flow chart for obtaining a set of zonal geological structure descriptions for the present invention;

[0046] Figure 4 A flow chart for obtaining the unstable mode classification result of the present invention;

[0047] Figure 5 A flow chart for obtaining the optimization result of the partition instability risk assessment of the present invention;

[0048] Figure 6 A flowchart of obtaining a trigger condition critical value set for the present invention;

[0049] Figure 7 A flowchart for obtaining the extreme event impact data analysis results for the present invention;

[0050] Figure 8 The present invention is a flow chart for obtaining comprehensive stability evaluation results of coastal geological data. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0053] See also Figure 1 , a coastal zone geological stability evaluation system includes:

[0054] The geological data partition identification module collects geological monitoring data, including coastal slope, soil properties, and groundwater flow rate information, summarizes all geological monitoring data into GIS, removes outliers and noise in the geological monitoring data, and performs standardization processing to extract features from the geological monitoring data, including the slope change rate of the coastal zone, soil moisture content, and groundwater flow rate change rate. The coastal zone feature set is obtained, and the coastal zone feature set is divided into different areas according to location in the geographic space. The initial partitioning conditions are set, and the partition purity is calculated by conditional information entropy. The partition with the highest purity is used as the judgment standard, and other partitions with purity lower than the judgment standard are gradually refined until the purity of each partition reaches a predetermined threshold or the data volume is insufficient. The partition is stopped and a partition geological structure description set is generated;

[0055] The instability mode classification module is based on the zoning geological structure description set. By monitoring the records of the changes of each feature in the coastal zone feature set over time, the instability type of each zoning data is identified and classified. The instability types include landslide, collapse, and mudflow. Among them, the landslide type is closely related to the slope change rate. When the slope change rate exceeds a certain range, it will cause the rock and soil body to slide along the slope as a whole. The collapse type is related to the sharp change of soil moisture content. When the soil moisture content increases rapidly and the soil loses cohesion, it may cause the sudden collapse of the rock and soil body. The mudflow type is related to the groundwater flow rate change rate. When the groundwater flow rate increases significantly in a short period of time, causing the soil to lose support and become a flow state, mudflow type instability may occur. The instability mode classification results are obtained. According to the instability mode classification results, the high-risk instability type areas are risk assessed with reference to the preset risk threshold. The confusion matrix is ​​used to analyze the misclassified samples, adjust the classification standards, and generate the optimization results of the zoning instability risk assessment.

[0056] The extreme event condition assessment module analyzes the triggering conditions of extreme events in high-risk instability areas based on the optimization results of the zoning instability risk assessment. By collecting historical extreme event data, including rainfall, wave height, and earthquake intensity anomaly information, and performing time series segmentation, an extreme event data set is obtained. The frequency and intensity of extreme events in the extreme event data set are modeled through generalized Pareto distribution to identify the critical triggering conditions of geological disasters. The critical triggering conditions include rainfall thresholds, wave height thresholds, and earthquake intensity levels. The critical value set of triggering conditions is obtained. According to the critical value set of triggering conditions, the joint impact of different extreme events is calculated, including the joint impact of rainfall, waves, and earthquake superposition, and the analysis results of extreme event impact data are generated;

[0057] The geological structure impact assessment module is based on the analysis results of extreme event impact data, and according to the triggering critical conditions of geological hazards in each sub-area and the joint impact data of extreme events, it comprehensively evaluates the overall geological stability of the coastal zone, calibrates the spatial scope and risk sources of each risk level area, and generates comprehensive stability evaluation results of coastal geological data;

[0058] The zoning geological structure description set includes the regional distribution map of slope change rate, the spatial statistical results of soil moisture content and the spatiotemporal evolution trend map of groundwater flow velocity change rate. The zoning instability risk assessment optimization results include the distribution range map of high-risk instability areas, the statistical table of the proportion of instability types and the characteristic comparative analysis of misclassified samples. The extreme event impact data analysis results include the time threshold of rainfall triggering conditions, the spatial distribution map of wave height changes and the calibration of high-risk areas of earthquake intensity level. The comprehensive stability evaluation results of coastal geological data include the boundary demarcation map of high-risk areas, the cause analysis report of higher-risk areas and the list of influencing factors of medium-risk areas.

[0059] See also Figure 2 , the specific steps for obtaining the coastal zone feature set are:

[0060] Based on the geological monitoring data obtained by monitoring equipment, the data scale is unified by recording and clearing abnormal data to generate a standardized geological monitoring data set;

[0061] The geological monitoring data are collected through monitoring equipment, including the use of electronic inclinometers to measure the slope information of the coastal zone, soil samples are collected through soil drilling equipment, and different soil types and their physical properties are recorded. These soil information include soil particle composition, density, clay content and permeability, etc. The particle composition data are recorded as sand, silt and clay through particle size distribution charts, and the permeability is directly recorded through permeability measurement equipment. The combination of these soil information can fully reflect the physical characteristics of coastal geology and its ability to store and flow water. The groundwater flow rate is measured using a portable flow meter, and the flow rate data are recorded at different depths and locations to reflect the dynamic distribution of groundwater. All monitoring data are uploaded to the GIS platform through an automated data acquisition system for centralized management. Outliers are removed by setting reasonable upper and lower limits. For example, the soil permeability coefficient is set within a normal range based on typical geological types. Points exceeding this range will be marked and removed. For the coastal slope, the inclination angle is set from 0° to 90°. Points exceeding the range will be identified as abnormal data and removed. Groundwater velocity data are cleaned by screening out abnormal points that are too high or too low. Statistical software is used to standardize the cleaned data, converting all data into a uniform distribution with a mean of 0 and a standard deviation of 1, and finally generating a standardized geological monitoring data set that can be used for subsequent analysis.

[0062] Based on the standardized geological monitoring data set, the characteristic points in the geological monitoring data are extracted, and the coastal zone characteristic set is generated by recording the changes of the target characteristic points in space and time and integrating the characteristic values;

[0063] By extracting features from the cleaned geological monitoring data, including obtaining information on coastal slope changes, soil moisture content, and groundwater flow rate changes, the time series analysis method is used to determine the changes in the coastal slope. The slope monitoring data at different time points are selected, and the difference between the two monitoring data before and after is calculated and divided by the time interval to characterize the slope change rate. For example, during the natural tidal rise and fall, the erosion and deposition of the tide on the slope may cause slight changes in the slope. Recording data from multiple tidal cycles can reveal the long-term trend of coastal slope changes. The extraction of soil moisture characteristics is completed by comparing the wet weight and dry weight of soil samples in the laboratory. For example, by collecting samples in the dry and wet seasons, it can be found that the moisture content of the soil near the seawater boundary may be higher than that of the inland area. By comparing the sample distribution and laboratory analysis results, the spatial differences in moisture content and seasonal fluctuation trends can be clarified. The rate of change of groundwater flow velocity is obtained by comparing the flow velocity at different time points. For example, the change of groundwater flow velocity at high tide and low tide is observed. Usually, the flow velocity is faster at high tide, while the flow velocity may slow down at low tide due to infiltration. Recording the flow velocity and interval time at different time points can reflect the dynamic law of groundwater flow. These features are integrated into the GIS system in combination with spatial location information to generate a coastal zone feature set to provide support for subsequent geological structure zoning.

[0064] See also Figure 3 , the specific steps for obtaining the sub-region geological structure description set are:

[0065] Record the geographic coordinates of each feature point in the coastal zone feature set, map the geographic coordinates of the feature points to the geographic space, visualize the distribution of the feature points, divide the regions according to the distribution of the feature points, record the feature information of each partition, and generate a geospatial data set;

[0066] First, by recording the geographic coordinates of the feature points, the geographic coordinates of each feature point are mapped to the geographic space, the distribution of the feature points is displayed in a visual way, and the concentrated or sparse areas of the feature points in space are identified. According to the distribution of the feature points, a suitable spatial segmentation method is selected for preliminary division. For example, the region can be segmented according to natural geographical features (such as the curved section of the coastline, the mountain boundary, the river estuary, etc.), and the geographical natural barriers can be used as the regional boundaries; or the partitions can be divided according to the density of the feature points, and smaller partitions can be established in the feature point dense area to accurately describe the local characteristics, and larger partitions can be established in the feature point sparse area to cover the wide area. In the specific operation, by checking the geographic location of each feature point in turn, recording the distance between the feature point and its neighboring points, it is determined whether it belongs to a dense area or a sparse area, and the regional range is delineated according to the number of neighboring points. After the sorting is completed, the coordinate information of the number of feature points, location range, and regional boundaries contained in each area is recorded, and the preliminary partition results are checked to ensure that each feature point is correctly attributed to a certain area and that there is no omission or overlap in the regional boundaries. Finally, a geospatial dataset containing initial zoning conditions is generated, providing a complete preliminary zoning framework for subsequent analysis and refinement.

[0067] Set the set of feature points in the geospatial dataset to , using the formula:

[0068]

[0069] Compute partitions Conditional information entropy , generate partition purity information analysis results;

[0070] in, Used to quantify the partitions in geospatial datasets Each feature point category The distribution probability and the concentration of category distribution. A low entropy value (close to 0) indicates that the data distribution of feature points in the partition is concentrated and the purity is high, while a high entropy value indicates that the distribution is dispersed and the purity is low. is the feature point category Partitioning in Geospatial Datasets The conditional probability in Divided by geospatial data, Directly defined through data analysis of feature point collection, for example, the classification of slope change rate, assuming that zone A contains 30 monitoring points, 20 of which belong to "small slope change" and 10 belong to "large slope change", then , is the category of the feature point Partitioning in Geospatial Datasets The base-2 logarithm of the conditional probability is used to measure the amount of information about the feature point category. Is a geospatial dataset partition The category index value of the feature point, such as the first category "small slope change" and the second category "medium slope change" in the slope change category. Is a geospatial dataset partition The total number of categories of all feature points in the graph. For example, there are three types of slope changes: "small slope change", "medium slope change" and "large slope change".

[0071] Assume that the coastal zone is divided into three different zones: Zone A (river estuary area): 30 monitoring points, taking slope change as an example, the slope change categories are "small change" and "large change", containing 20 and 10 feature points respectively. Zone B (curved coastline): 40 monitoring points, the slope change categories are "small change" and "medium change", containing 25 and 15 feature points respectively. Zone C (open beach): 20 monitoring points, the slope change category is "small change", and all feature points belong to this category.

[0072] Calculation of partition A, category probability:

[0073] Small slope changes:

[0074]

[0075] Large slope changes:

[0076]

[0077] Conditional information entropy calculation:

[0078]

[0079] Substituting the probability values:

[0080]

[0081]

[0082] Calculation of partition B, category probability:

[0083] Small slope changes:

[0084]

[0085] Medium slope change:

[0086]

[0087] Conditional information entropy calculation:

[0088]

[0089] Substituting the probability values:

[0090]

[0091]

[0092] Calculation of partition C, category probability:

[0093] Small slope changes:

[0094]

[0095] Conditional information entropy calculation:

[0096]

[0097] Substituting the probability values:

[0098]

[0099]

[0100] The results show that the entropy value of partition A is 0.9166, the entropy value of partition B is 0.9575, and the entropy value of partition C is 0.

[0101] According to the analysis results of the partition purity information, the partition with the highest purity is used as the judgment standard, and the characteristic points of the partitions with purity lower than the judgment standard are refined. The regions are re-divided by checking the spatial distribution of the characteristic point categories in the partitions until the purity of all partitions reaches the target value or the data volume is insufficient, and the partition geological structure description set is generated;

[0102] According to the calculated conditional information entropy results of the three partitions, partition C has the highest purity and the information entropy value is 0, so partition C is selected as the purity judgment standard. Taking the purity of partition C as the goal, the other two partitions (partition A and partition B) with purity below the standard are gradually refined. The specific process of refinement is as follows: Partition C has high purity and the information entropy value is 0, indicating that the feature categories in this partition are completely consistent and no further refinement is required, so it is directly included in the final geological structure description set. Taking the slope change as an example, the refinement of partition A: The information entropy value of partition A is 0.9166, which is significantly higher than the standard of partition C, so refinement is required. First, the distribution of feature points in partition A is checked, and it is found that the number of points in the small slope change category is 20, and the number of points in the large slope change category is 10, which belong to two obvious feature categories. Based on the spatial distribution of points, the points in the small slope change category are divided into a sub-partition (A1) and the points in the large slope change category are divided into another sub-partition (A2). The purity of sub-partitions A1 and A2 was recalculated respectively, and it was found that the feature categories of A1 were completely consistent, and the information entropy was 0; A2 also contained only one category, and the information entropy was also 0. Therefore, partition A was refined into two sub-partitions, A1 and A2, both of which met the purity standard and the refinement was completed. Refinement of partition B: The information entropy value of partition B was 0.9575, which was also higher than the standard of partition C, so it needed to be refined. The distribution of feature points in partition B was checked, and it was found that the number of points in the small slope change category was 25, and the number of points in the medium slope change category was 15, and the feature categories were inconsistent. The spatial distribution analysis of the feature points found that there was an obvious spatial separation of the two categories of points in partition B, and partition B could be divided into two sub-partitions (B1 and B2) according to the geographical location. Sub-partition B1 contains points in the small slope change category (25), and the information entropy is 0; sub-partition B2 contains points in the medium slope change category (15), and the information entropy is also 0. After refinement, partition B was divided into two high-purity sub-partitions B1 and B2. Through the above refinement operation, the original three partitions (A, B, C) are adjusted to five partitions (A1, A2, B1, B2 and C). The information entropy of each partition is 0, which meets the purity standard. The boundaries, number of feature points and category information of these high-purity partitions are recorded to generate the final partition geological structure description set.

[0103] See also Figure 4 , the specific steps for obtaining the unstable mode classification results are:

[0104] Based on the zoning geological structure description set, the characteristic point data in each zone is recorded in time series. The characteristic point data is sorted into time series tables or trend graphs by zone and archived to generate a dynamic coastal zone characteristic record data set.

[0105] First, the time series data is established through the characteristic points in the partition. The content recorded at each characteristic point includes the main characteristics such as slope change rate, soil moisture content, groundwater flow rate, etc. The characteristic data is collected once every fixed time interval (such as every hour or every day). All data are collected by the equipment and uploaded to the GIS platform, and archived and sorted according to the geographical coordinates of the partition and the characteristic point. The recording process includes: storing the characteristic data of each characteristic point in chronological order as a multi-column time series table, for example, the slope change rate of a characteristic point in a certain partition is recorded as a corresponding data pair of time and slope change rate; soil moisture content is recorded as a corresponding data pair of time and moisture content; groundwater flow rate is recorded as a corresponding data pair of time and flow rate, etc. These records are visually managed in units of partitions. For example, the trend of characteristic values ​​changing over time is displayed in the form of a line graph, or superimposed on the partition map in the form of a dynamic point graph, which directly reflects the dynamic changes of each characteristic point. All records are finally summarized to form a complete characteristic time change data set.

[0106] Based on the dynamic coastal zone characteristic record data set, the instability type of the characteristic points in each partition is identified and classified by analyzing the time variation trend of the characteristic point data, and the instability mode classification results are generated;

[0107] According to the recorded temporal change data of the partition feature points, the instability types of each partition data in the coastal geological scene are identified and classified. The specific operations are as follows: First, the time series of slope change rate, soil moisture content, and groundwater flow rate are extracted according to the feature point data in each partition, and the range assessment and dynamic change analysis of these feature data are performed. For example, in partition A, by analyzing the time record of the slope change rate, it is found that the slope change rate of a certain feature point rises rapidly from 1.2° / h to 6.5° / h within two consecutive hours. Assuming that the slope change rate risk threshold is 5° / h, it exceeds the set safety range, and it is determined that the feature point has a landslide-type instability risk; in partition B, through the time series analysis of soil moisture content, it is found that the moisture content of a certain feature point increases sharply from 18% to 45% within two hours after rainfall. Assuming that the soil moisture content change threshold is 25% (that is, when the soil moisture content changes by more than 25% within two hours, it exceeds the cohesion limit value, and the feature point is determined to have a collapse-type instability risk; in partition C, through the record of groundwater flow rate, it is found that The velocity of a certain feature point increases from 0.2m / s to 1.8m / s in a short period of time. Assuming that the threshold of the groundwater velocity change rate is 1.5m / s, that is, when the velocity increases by more than 1.5m / s in a short period of time, the soil particles are suspended and loose, and it is determined to be a mudflow type instability risk. Through the classification and identification of feature points in each partition, the instability type is marked and sorted according to the spatial position of the feature point. The instability type classification results (such as landslide type, collapse type, mudflow type) of the feature point are superimposed on the regional map using a geographic information system (such as ArcGIS, QGIS). Different types of unstable areas are distinguished by color or symbol, and a classification result map containing landslide type, collapse type and mudflow type instability risks is constructed to obtain the classification results of the instability mode.

[0108] See also Figure 5 , the specific steps for obtaining the optimization results of the partition instability risk assessment are as follows:

[0109] For the instability mode classification results, the feature points in the partition are divided into low instability risk areas and high instability risk areas with reference to the preset risk threshold, and the identification results of the high instability risk areas are generated;

[0110] According to the risk thresholds of slope change rate, soil moisture content and groundwater velocity, the characteristic points in each partition are divided into low instability risk areas and high instability risk areas, and a detailed assessment is conducted on the high instability risk areas. The specific thresholds are as follows: the slope change rate of 0 to 5° / h is low instability risk, and more than 5° / h is high instability risk; the soil moisture change rate of 0 to 25% is low instability risk, and more than 25% is high instability risk; the groundwater velocity change rate of 0 to 1.5m / s is low instability risk, and more than 1.5m / s is high instability risk. According to the recorded time change data of the characteristic points of the partition, by extracting the time series change values ​​of the characteristic points in the partition, directly comparing whether each characteristic point exceeds the set threshold range, the characteristic point and its surrounding area are determined to be a high instability risk area or a low instability risk area, and their specific information is recorded. The specific analysis is as follows: In partition A, the slope change rate of a certain feature point rapidly increased from 1.2° / h to 6.5° / h, exceeding the landslide threshold of 5° / h, and was divided into a landslide-type high instability risk area. The specific range includes the feature point and the surrounding 50-meter area, and the geographical coordinates and impact range of the area are recorded; in partition B, the soil moisture content of a certain feature point increased from 18% to 45%, with a change of 27% within two hours, exceeding the collapse threshold of 25%, and was divided into a collapse-type high instability risk area, covering a 30-meter area around the feature point, and the regional boundary and feature change value were recorded; in partition C, the groundwater flow velocity of a certain feature point increased from 0.2m / s to 1.8m / s, with a change rate of 1.6m / s, exceeding the mudflow threshold of 1.5m / s, and was divided into a mudflow-type high instability risk area, covering a 20-meter area around the feature point, and the spatial coordinates and range of mudflow distribution were recorded. The information of these high instability risk areas is organized into zoning risk assessment tables, superimposed on zoning maps through geographic information systems, and displayed in a visual form to form identification results of high instability risk areas.

[0111] Based on the identification results of high instability risk areas, the confusion matrix is ​​used to compare and analyze the classification results of high instability risk areas with the actual instability situation, and the sample data of correct classification, misclassification and missed classification are recorded. The classification standard of high instability risk areas is adjusted to generate the optimization results of zoning instability risk assessment;

[0112] The accuracy of the instability type classification is analyzed in detail using the confusion matrix. The specific operation is as follows: First, the classification results and actual conditions of the three instability types of landslide, collapse and mudslide are collected, and the high-risk points in each partition are compared with the actual instability type. For example, in partition A, a feature point is classified as a landslide high-risk area, but the actual instability type is collapse; in partition B, a feature point is actually a collapse high-risk area, but the classification result is mudslide instability; in partition C, a feature point is classified as a mudslide high-risk area, and the actual situation is consistent with the classification. These comparison data are input into the confusion matrix, and the amount of data correctly classified, misclassified, missed classified and unclassified is recorded respectively. The specific operation of the confusion matrix is ​​as follows: For each instability type, such as landslide, all high-risk points classified as landslide are listed as positive examples, and high-risk points that actually experience landslide instability are listed as actual positive examples. By crossing the rows and columns of the matrix, the following values ​​are calculated: For the correct classification: the number of points correctly classified as landslide instability. For example, in partition A, 8 out of 10 high-risk points are actually landslide-type instability. For misclassification: the number of points that are misclassified as landslide-type but are not actually landslide-type. For example, 2 feature points are misclassified as landslide-type instability, but are actually collapse-type. For missed classification: the number of points that are actually landslide-type but are not classified as landslide-type. For example, 1 landslide-type feature point is misclassified as mudslide-type. For unclassified: the number of points that are not classified as landslide-type and are not actually landslide-type. After completing the above operations for each instability type in turn, the confusion matrix of the three instability types is constructed. The classification accuracy, precision and recall are calculated based on the confusion matrix. For example, the accuracy of landslide type is 85% (that is, the proportion of TP to all actual positive examples), collapse type is 70%, and mudslide type is 65%. Through the analysis of the matrix results, it is found that the misclassification is mainly concentrated in the area where the feature point data is close to the threshold range. For example, the slope change rate of landslide type is 4.8° / h close to 5° / h, but it does not actually meet the instability standard, resulting in classification errors. Combined with the analysis results, the classification criteria were optimized. For example, the threshold of slope change rate for landslide was adjusted from 5° / h to 4.5° / h to improve the ability to identify areas close to instability; the threshold of soil moisture change for collapse was adjusted from 25% to 23% to enhance sensitivity to the impact of rapid rainfall; the threshold of groundwater velocity change rate for mudflow was adjusted from 1.5m / s to 1.4m / s to improve the ability to identify groundwater fluctuation areas. The optimized classification criteria were reapplied to the zoning instability risk assessment.

[0113] See also Figure 6 , the specific steps for obtaining the trigger condition critical value set are:

[0114] Based on the optimization results of the zoning instability risk assessment, historical extreme event data related to high-risk instability areas are collected, including rainfall, wave height, and earthquake intensity information. The historical extreme event data are screened and time series segmented to generate extreme event data sets.

[0115] Analyze the triggering conditions of extreme events for the unstable areas with medium and high risks in coastal geology. The specific process is as follows: lock the partition A (high-risk area for landslide), partition B (high-risk area for collapse) and partition C (high-risk area for mudslide), and collect historical extreme event data related to these areas. For example, collect daily rainfall data in the past ten years in partition A, and screen extreme records with rainfall greater than 50 mm; collect wave height data in partition B, extract events with peak values ​​greater than 3 meters; collect earthquake intensity data in partition C, and select abnormal events with magnitude greater than 4.5. Perform time series segmentation on the above data. For example, for the rainfall data in partition A, segment the records 24 hours before and after each rainfall event; for the wave data in partition B, segment the fluctuations 48 hours before and after the peak; for the earthquake data in partition C, use the change data 1 hour before the earthquake and 6 hours after the earthquake as independent time periods. By completing the time segmentation, a time series segmented data set containing rainfall, wave height and earthquake intensity is generated.

[0116] Based on the extreme event data set, the frequency and intensity of each type of extreme event are modeled through the generalized Pareto distribution. According to the extreme event records in the high-risk instability type area, the initial wave height threshold, magnitude intensity threshold, and initial rainfall threshold are preset to determine the triggering of critical conditions and generate a set of trigger condition critical values.

[0117] The frequency and intensity in the extreme event data set are modeled by generalized Pareto distribution to identify the critical triggering conditions of geological disasters. The fitting process includes: extracting rainfall data from partition A, screening out event records exceeding 50 mm / day, and forming an extreme rainfall data set including event date and rainfall. For example, daily rainfalls of 52 mm and 110 mm were recorded on May 12 and June 18, respectively. Similarly, wave height exceeding 3 meters is selected as the starting wave height threshold, and event data with wave height exceeding 3 meters (such as 3.5 meters and 4.2 meters) are extracted from partition B, and magnitude exceeding 4.5 is selected as the starting magnitude intensity threshold, and earthquake events with magnitude exceeding 4.5 (such as 4.8 and 5.3) are extracted from partition C. The data are fitted with distribution using analytical tools (such as Python's SciPy library). For example, for the rainfall data in partition A, 50 mm is selected as the starting rainfall threshold, and rainfall data exceeding 50 mm is input into the fitting function to calculate the shape parameter and scale parameter of the generalized Pareto distribution. These parameters are used to establish the relationship between rainfall intensity and event frequency. Similar operations are performed to fit the wave and earthquake data. Assume that after fitting, in partition A, the results of the generalized Pareto distribution are as follows: the event recurrence period of rainfall reaching 70 mm is 5 years; the event recurrence period of rainfall reaching 90 mm is 10 years; the event recurrence period of rainfall reaching 110 mm is 20 years. In partition B, the fitting results of the wave height data are: the event recurrence period of wave height reaching 3.5 meters is 8 years; the event recurrence period of wave height reaching 4 meters is 15 years. In partition C, the fitting results of the earthquake data are: the event recurrence period of magnitude reaching 4.8 is 12 years; the event recurrence period of magnitude reaching 5.3 is 25 years. Taking the landslide-type instability in partition A as an example, the recurrence period of rainfall reaching 90 mm / 24 hours is 10 years, indicating that a heavy rainfall event may occur in this area every 10 years. If the heavy rainfall exceeds the critical condition for triggering landslides, the landslide risk will be significantly increased. Similarly, in Zone B, the recurrence period for wave heights of 3.8 meters is about 12 years, which indicates that a high wave event may occur every 12 years, which may lead to collapse-type instability. In Zone C, the recurrence period for earthquakes with a magnitude of more than 5.0 is 15 years, indicating that a moderate-intensity earthquake may occur in this area every 15 years. If the magnitude reaches the triggering condition of mudflow (such as 5.5), the risk of mudflow will increase significantly.

[0118] See also Figure 7 , the specific steps for obtaining the analysis results of extreme event impact data are as follows:

[0119] Based on the trigger condition critical value set, the formula is used:

[0120]

[0121] Calculate the trigger condition critical value concentration, rainfall , Waves and earthquake Joint probability of simultaneous occurrence , get the probability data of joint impact;

[0122] in, It is the probability of a rainfall event calculated based on the starting rainfall threshold in the trigger condition critical value set. For example, assuming that the trigger condition critical value set indicates that in partition A, the rainfall exceeding 50 mm is the starting point of an extreme event, 150 rainfall events are recorded, and the total number of time periods is 1825 days, then , It is the probability of a wave triggering event under the condition of a rainfall event, calculated based on the starting wave height threshold in the trigger condition critical value set. For example, assuming that there are 30 events with waves exceeding 3.5m during the rainfall period, then , It is the probability of earthquake triggering events under the conditions of rainfall and sea wave events calculated based on the starting magnitude intensity threshold in the trigger condition critical value concentration. Assuming that there are 30 events of rainfall and sea wave occurring at the same time, and 3 of them have earthquake intensity exceeding 4.8, then .

[0123] Assume that the coastal zone is divided into three zones: Zone A (river estuary area), reference the trigger condition critical value set: Total number of time periods: 1825 days. Records of events with rainfall exceeding 50 mm: 150 times. Events of sea wave height exceeding 3.5 m during rainfall: 30 times. Events of rainfall and sea waves occurring simultaneously and earthquake intensity exceeding 4.8: 3 times.

[0124] Probability of rainfall events :

[0125]

[0126] Conditional Probability (Probability of wave height exceeding 3.5m during rainfall):

[0127]

[0128] Conditional Probability (The probability of an earthquake intensity exceeding 4.8 when rain and waves occur simultaneously):

[0129]

[0130] Joint Probability :

[0131]

[0132] In zone A, the probability of a joint extreme event is 0.001644, indicating that an extreme event jointly triggered by rainfall, waves, and earthquakes may occur approximately every 608 days.

[0133] Zone B (curved coastline), assuming that the topography of the curved coastline causes a more significant impact of waves, the proportion of events with wave heights exceeding 3.5m during rainfall increases, and the frequency of earthquake events is relatively higher.

[0134] Assumptions: (Rainfall event probability): Same as Partition A, . : The proportion of sea wave height exceeding 3.5m during rainfall is 40%, that is: ; : When rainfall and waves occur simultaneously, the probability of an earthquake intensity exceeding 4.8 is 15%, that is: , joint probability calculation:

[0135]

[0136] In zone B, the probability of a joint extreme event is 0.004932, indicating that an extreme event jointly triggered by rainfall, waves, and earthquakes may occur approximately every 203 days.

[0137] Zone C (open beach), assuming that the open beach has a smaller impact on the linkage between rainfall and waves, but the probability of earthquake triggering mudflow type disasters is higher. Assumption data: (Rainfall event probability): Same as Partition A, . : The proportion of sea wave height exceeding 3.5m during rainfall is 15%, that is: ; : When rainfall and waves occur simultaneously, the probability of an earthquake intensity exceeding 4.8 is 20%, that is: , joint probability calculation:

[0138]

[0139] In zone C, the probability of a combined extreme event is 0.002466, indicating that an extreme event triggered by rainfall, waves, and earthquakes may occur approximately every 406 days. This reflects how topographic and environmental characteristics in different zones affect the probability of triggering combined extreme events, providing a quantitative reference for zone disaster risk management.

[0140] Based on the probability data of joint impacts and the geographical characteristics of the sub-regions, the potential impact range of extreme events in each sub-region is evaluated to generate data analysis results on the impact of extreme events;

[0141] The joint impacts calculated for different zones are integrated. For example, in zone A (river estuary area), the joint extreme event probability is 0.001644, indicating that an extreme event triggered by rainfall, waves and earthquakes may occur approximately every 608 days during the 1825-day observation period. By analyzing this probability, it can be inferred that the potential impact range of such events is concentrated in the estuary area. Due to the convergence of water flow and low-lying terrain, the joint extreme events in this area may cause large-scale mudslides and infrastructure damage. In zone B (curved coastline), the joint probability is 0.004932, indicating that an extreme event may occur approximately every 203 days. The integrated analysis shows that the joint extreme events in this area are mainly affected by the superposition of heavy rainfall and high waves. Waves may pose a greater threat to the structural stability of the curved coastline, further exacerbating the risk of collapse. By further extracting the geographical and historical disaster data of the zone, the possible affected range and its environmental characteristics are marked, and a regional impact assessment report is generated. In zone C (open beach), the joint probability is 0.002466, indicating that an extreme event may occur approximately every 406 days. The main risk of such events comes from beach landslides or mudslides caused by earthquakes. The integrated analysis content provides basic support for disaster warning and response in each zone.

[0142] See also Figure 8 , the specific steps for obtaining the comprehensive stability evaluation results of coastal geological data are as follows:

[0143] Based on the joint probability of each partition in the extreme event impact data analysis results, the formula is used:

[0144]

[0145] Calculating the stability score of coastal geology , get the stability score of coastal geology;

[0146] in, The value range is The larger the value, the higher the geological stability.

[0147] For partition A:

[0148]

[0149]

[0150] For partition B:

[0151]

[0152]

[0153] For partition C:

[0154]

[0155]

[0156] The results show that the stability score of the coastal geology in Zone A is 0.998356, the stability score of the coastal geology in Zone B is 0.995068, and the stability score of the coastal geology in Zone C is 0.997534. In addition, since the triggering critical conditions directly determine the frequency and linkage relationship of extreme events, for example, increasing the triggering thresholds of rainfall, wave height and earthquake intensity will significantly reduce the joint probability, thereby indirectly affecting the geological stability score.

[0157] Based on the stability score of coastal geology, the overall geological stability of the coastal area is comprehensively evaluated, the spatial range and stability level of the sub-areas are calibrated in turn, the geological stability of the sub-areas is represented on the GIS map, and the comprehensive stability evaluation results of the coastal geological data are generated;

[0158] First, the stability scores of sub-areas A, B, and C are divided into two risk levels: high (0.99 and above) and medium (0.95-0.99). The stability scores of all sub-areas are higher than 0.95, so there is no low stability area. The stability score of sub-area A is 0.998356, which belongs to the high stability area. The stability score of sub-area B is 0.995068, which belongs to the high stability area. However, due to the low score, its potential local risks need to be paid attention to in the regional evaluation. The stability score of sub-area C is 0.997534, which also belongs to the high stability area. Secondly, according to the main geological characteristics of each sub-area, the stability of sub-area A is calibrated. The main risk source is sediment flow caused by rainfall greater than 90 mm. The main risk source of zone B is the risk of slope slippage caused by wave height greater than 3.8 m due to the curved coastline terrain. The main risk source of zone C is local sediment instability caused by earthquake intensity greater than 4.8. Then, the spatial range data of the zones and their corresponding stability scores are imported into GIS, and color marking is used. High stability areas are represented by green, and the specific spatial ranges and risk sources of zones A, B and C are marked. Finally, a comprehensive geological stability evaluation map of the coastal zone is generated, which provides a clear spatial reference for the monitoring and management of geological disaster risks in each zone.

[0159] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A coastal zone geological stability evaluation system, characterized in that: The system comprises: The geological data partition identification module collects geological monitoring data, summarizes all geological monitoring data into GIS, extracts features from geological monitoring data, obtains coastal zone feature sets, divides coastal zone feature sets into different regions according to location in geographic space, calculates partition purity through conditional information entropy, takes the partition with the highest purity as the judgment standard, and gradually refines other partitions with purity lower than the judgment standard to generate a partition geological structure description set; The instability mode classification module is based on the sub-region geological structure description set, and by monitoring the records of the changes of each feature in the coastal zone feature set over time, identifies and classifies the instability type of the data of each sub-region, obtains the instability mode classification result, and according to the instability mode classification result, refers to the preset risk threshold, conducts risk assessment on the high-risk instability type area, and generates the sub-region instability risk assessment optimization result; The extreme event condition assessment module collects historical extreme event data based on the optimization results of the partition instability risk assessment, and performs time series segmentation to obtain an extreme event data set. The frequency and intensity of extreme events in the extreme event data set are modeled through generalized Pareto distribution, and the triggering critical conditions of geological disasters are identified to obtain a triggering condition critical value set. According to the triggering condition critical value set, the joint impact of different extreme events is calculated to generate extreme event impact data analysis results; The geological structure impact assessment module conducts a comprehensive evaluation of the overall geological stability of the coastal area based on the analysis results of the extreme event impact data, calibrates the spatial scope and risk sources of each risk level area, and generates a comprehensive stability evaluation result of the coastal geological data.

2. The coastal zone geological stability evaluation system according to claim 1, characterized in that: The steps for obtaining the coastal zone feature set are specifically as follows: Based on the geological monitoring data obtained by monitoring equipment, the data scale is unified by recording and clearing abnormal data to generate a standardized geological monitoring data set; Based on the standardized geological monitoring data set, characteristic points in the geological monitoring data are extracted, and a coastal zone characteristic set is generated by recording the changes of the target characteristic points in space and time and integrating the characteristic values.

3. The coastal zone geological stability evaluation system according to claim 1, characterized in that: The steps for obtaining the sub-region geological structure description set are specifically as follows: Recording the geographic coordinates of each feature point in the coastal zone feature set, mapping the geographic coordinates of the feature points to the geographic space, visually displaying the distribution of the feature points, dividing the regions according to the distribution of the feature points, recording the feature information of each partition, and generating a geographic space data set; Set the set of feature points in the geospatial dataset to , using the formula: Compute partitions Conditional information entropy , generate partition purity information analysis results; in, Used to quantify the partitions in geospatial datasets Each feature point category The distribution probability of , and the concentration of category distribution, is the feature point category Partitioning in Geospatial Datasets The conditional probability in Used to measure the amount of information of feature point categories. Is a geospatial dataset partition The category index value of the feature point in , Is a geospatial dataset partition The total number of categories of all feature points in ; According to the analysis results of the partition purity information, the partition with the highest purity is used as the judgment standard, the feature points of the partitions with purity lower than the judgment standard are refined, and the regions are re-divided by checking the spatial distribution of the feature point categories within the partitions until the purity of all partitions reaches the target value or the data volume is insufficient, and a partition geological structure description set is generated.

4. The coastal zone geological stability evaluation system according to claim 1, characterized in that: The steps for obtaining the instability mode classification result are specifically as follows: Based on the sub-area geological structure description set, the characteristic point data in each sub-area are recorded in time series, and the characteristic point data are sorted into time series tables or trend graphs by sub-area, and archived to generate a dynamic coastal zone characteristic record data set; Based on the dynamic coastal zone characteristic record data set, by analyzing the temporal variation trend of the characteristic point data, the instability type of the characteristic points in each partition is identified and classified to generate an instability mode classification result.

5. The coastal zone geological stability evaluation system according to claim 1, characterized in that: The steps for obtaining the optimization results of the partition instability risk assessment are specifically as follows: For the instability mode classification result, the characteristic points in the partition are divided into a low instability risk area and a high instability risk area with reference to a preset risk threshold, and an identification result of the high instability risk area is generated; Based on the identification results of the high instability risk areas, the confusion matrix is ​​used to compare and analyze the classification results of the high instability risk areas with the actual instability situation, and the sample data of correct classification, misclassification and missed classification are recorded. The classification standard of the high instability risk areas is adjusted to generate the optimized results of the partitioned instability risk assessment.

6. The coastal zone geological stability evaluation system according to claim 1, characterized in that: The steps for obtaining the trigger condition critical value set are specifically as follows: Based on the optimization results of the zoning instability risk assessment, historical extreme event data related to high-risk instability types of areas are collected, including rainfall, wave height, and earthquake intensity information, and the historical extreme event data are screened and time series segmented to generate an extreme event data set; Based on the extreme event dataset, the frequency and intensity of each type of extreme event are modeled through generalized Pareto distribution. According to the extreme event records in the high-risk instability type area, the starting wave height threshold, magnitude intensity threshold, and starting rainfall threshold are preset to judge the triggering of critical conditions and generate a trigger condition critical value set.

7. The coastal zone geological stability evaluation system according to claim 1, characterized in that: The steps for obtaining the analysis results of the extreme event impact data are specifically as follows: Based on the trigger condition critical value set, the formula is used: Calculate the trigger condition critical value concentration, rainfall , Waves and earthquake Joint probability of simultaneous occurrence , get the probability data of joint impact; in, is the probability of a rainfall event calculated based on the initial rainfall threshold in the trigger condition critical value set. is the probability of a wave triggering event under the condition of a rainfall event calculated based on the initial wave height threshold in the trigger condition critical value set. It is the probability of an earthquake triggering event under the conditions of rainfall and sea wave events calculated based on the starting magnitude intensity threshold in the trigger condition critical value set; Based on the probability data of the joint impact and combined with the geographical characteristics of the sub-regions, the potential impact scope of extreme events in each sub-region is evaluated to generate extreme event impact data analysis results.

8. The coastal zone geological stability evaluation system according to claim 1, characterized in that: The steps for obtaining the comprehensive stability evaluation results of the coastal geological data are specifically as follows: Based on the joint probability of each partition in the extreme event impact data analysis results, the formula is used: Calculating the stability score of coastal geology , get the stability score of coastal geology; in, The value range is ; Based on the stability score of the coastal geology, a comprehensive evaluation is conducted on the overall geological stability of the coastal area, the spatial range and stability level of the sub-areas are calibrated in turn, the geological stability of the sub-areas are represented on the GIS map, and the comprehensive stability evaluation results of the coastal geological data are generated.

Images