Rainfall-based landslide geological disaster early warning system and method

Abstract

The application relates to the technical field of disaster early warning, in particular to a landslide geological disaster early warning system and method based on rainfall, which comprises the following steps: arranging a plurality of rainfall monitoring points in a target region based on historical landslide disaster data and historical precipitation data; determining a real-time rainfall risk distribution map of the target region by a real-time rainfall early warning threshold based on a spatial interpolation method; superimposing and analyzing a real-time landslide high-risk cluster and the real-time rainfall risk distribution map to obtain a real-time landslide-prone index of each sub-region in the target region; correcting the landslide-prone labels corresponding to each sub-region in the target region based on geological parameters of the target region to obtain a landslide-prone map; and determining landslide geological disaster early warning information based on the landslide-prone map. The landslide-prone labels are corrected based on the geological parameters of the target region, the accuracy and reliability of the prediction result can be further improved, and the influence of the geological environment is avoided to be neglected due to excessive dependence on the precipitation data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of disaster early warning, in particular to a landslide geological disaster early warning system and method based on rainfall. BACKGROUND

[0002] Traditional systems often rely on historical data and static early warning models, lacking integration of real-time rainfall and real-time disaster data; the lack of real-time data updates makes it difficult for traditional early warning systems to timely reflect sudden rainfall events or new landslide disaster risks, resulting in delayed early warning responses and difficulty in taking effective preventive measures in a timely manner; and traditional landslide early warning systems usually use fixed rainfall thresholds as early warning criteria, but geological conditions, rainfall intensity, and landslide history in different regions may differ greatly; fixed thresholds may cause the early warning system to be overly conservative in some cases, missing critical early warning times, or prematurely issuing warnings in other cases, resulting in wasted resources; and traditional systems may rely solely on precipitation data to predict landslide risks, ignoring the impact of geological features (such as soil type, slope, vegetation cover, etc.) on landslide susceptibility; changes in the geological environment have a significant impact on the occurrence of landslide disasters, and relying solely on precipitation data may result in inaccurate predictions, especially in complex geological environments; and traditional systems often use global risk assessment, lacking fine-grained division for different sub-regions; due to geographical conditions and rainfall differences, landslide risks in different regions may vary greatly. SUMMARY

[0003] The technical problem to be solved by the present application is to overcome the shortcomings of the above-mentioned prior art and provide a landslide geological disaster early warning system and method based on rainfall.

[0004] The technical solution adopted to solve the above technical problems is: a landslide geological disaster early warning system based on rainfall, comprising:

[0005] A rainfall monitoring unit, the rainfall monitoring unit is used to arrange a plurality of rainfall monitoring points in a target area based on historical landslide disaster data and historical precipitation data; select a plurality of historical landslide disaster points based on historical landslide disaster data; each historical landslide disaster point corresponds to a preset geographic coordinate and geological parameter;

[0006] A rainfall collection unit, the rainfall collection unit is used to collect real-time rainfall data based on the rainfall monitoring points; determine the real-time rainfall warning threshold corresponding to each historical landslide disaster point based on the real-time rainfall data and the geological parameters of each historical landslide disaster point through a dynamic threshold model;

[0007] a risk early warning unit, configured to determine a real-time rainfall risk distribution map of the target area based on a spatial interpolation method through the real-time rainfall early warning threshold; and determine a real-time landslide high-risk cluster of the target area based on a clustering algorithm through the real-time rainfall risk distribution map and geographical coordinates of the historical landslide disaster points;

[0008] a landslide analysis unit, configured to perform superimposed analysis on the real-time landslide high-risk cluster and the real-time rainfall risk distribution map to obtain a real-time landslide susceptibility index of each sub-area in the target area; and perform landslide susceptibility division on each sub-area in the target area based on the real-time landslide susceptibility index to obtain a susceptibility label corresponding to each sub-area in the target area;

[0009] a region division unit, configured to correct the susceptibility label corresponding to each sub-area in the target area based on geological parameters of the target area to obtain a landslide susceptibility map; and determine landslide geological disaster early warning information based on the landslide susceptibility map.

[0010] Preferably, the rainfall early warning threshold includes an hourly rainfall intensity threshold, a cumulative 24-hour rainfall threshold and a cumulative 72-hour rainfall threshold; the susceptibility label includes an extremely low susceptibility area, a low susceptibility area, a medium susceptibility area, a high susceptibility area and an extremely high susceptibility area; and the geological parameters include a terrain slope, a soil type and a land use type.

[0011] Preferably, a plurality of rainfall monitoring points are arranged in the target area based on historical landslide disaster data and historical precipitation data, including:

[0012] a digital elevation model of the target area is obtained; terrain humidity index calculation is performed based on the digital elevation model and the historical precipitation data to obtain a historical regional humidity distribution map corresponding to the target area;

[0013] kernel density estimation is performed on the historical landslide disaster data to obtain a historical landslide disaster density cloud map corresponding to the target area;

[0014] the historical regional humidity distribution map and the historical landslide disaster density cloud map are superimposed by weighting to obtain a historical landslide sensitivity comprehensive index map;

[0015] landslide sensitivity division is performed on each sub-area in the target area based on the historical landslide sensitivity comprehensive index map to obtain a sensitivity label of each sub-area; and the sensitivity label includes a high sensitivity area, a medium sensitivity area and a low sensitivity area.

[0016] Based on the sensitivity labels of the sub-regions, a gradient planning of monitoring point density is performed, rain monitoring points are arranged at a first interval in the high-sensitivity region, at a second interval in the medium-sensitivity region, and at a third interval in the low-sensitivity region, to obtain a rain monitoring point distribution map; wherein the first interval < the second interval < the third interval.

[0017] Preferably, the process of constructing the dynamic threshold model comprises:

[0018] Collecting rainfall data before historical landslide events, and extracting the corresponding hourly rainfall, cumulative 24-hour rainfall, and cumulative 72-hour rainfall of each landslide event;

[0019] Based on the geological data of each landslide event, the rainfall data is divided into several geological condition groups; wherein the geological data includes rock-soil permeability coefficient, slope, and vegetation coverage;

[0020] Statistical analysis is performed on the rainfall data in each of the geological condition groups to determine the corresponding hourly rainfall threshold, cumulative 24-hour rainfall threshold, and cumulative 72-hour rainfall threshold of each geological condition group;

[0021] Based on the support vector machine algorithm, a nonlinear mapping relationship between the geological data and the rainfall thresholds is established to obtain the dynamic threshold model.

[0022] Preferably, the real-time rainfall risk distribution map of the target region is determined based on the real-time rainfall warning threshold through the spatial interpolation method, comprising:

[0023] The real-time rainfall data collected by the rain monitoring points is preprocessed, wherein the preprocessing includes outlier rejection and data smoothing processing;

[0024] Based on the Kriging interpolation algorithm, combined with terrain elevation data and land use type data, spatial interpolation is performed on the preprocessed rainfall data to obtain the real-time rainfall risk distribution map of the target region.

[0025] Preferably, the real-time landslide high-risk cluster group of the target region is determined based on the real-time rainfall risk distribution map and the geographical coordinates of the historical landslide disaster points through the clustering algorithm, comprising:

[0026] The geographical coordinates of the historical landslide disaster points and the rainfall risk values of the corresponding positions in the real-time rainfall risk distribution map are extracted;

[0027] Based on the density peak clustering algorithm, the landslide disaster points are clustered and analyzed with the rainfall risk values as weights to obtain several initial cluster groups;

[0028] Boundary optimization is performed on each of the initial clusters to obtain real-time high-risk landslide clusters in the target area; wherein the boundary optimization includes cluster segmentation and merging based on terrain fault data.

[0029] Preferably, the calculation formula of the landslide susceptibility index is as follows:

[0030] ;

[0031] in, represents the landslide susceptibility index, Indicates the The weight coefficient corresponding to the rainfall warning threshold is: Indicates the The number of times the rainfall warning threshold exceeds the limit, represents the terrain slope correction coefficient, Indicates the stability coefficient corresponding to the soil type.

[0032] Preferably, the susceptibility labels corresponding to the sub-regions in the target region are modified based on the geological parameters of the target region to obtain a landslide susceptibility map, including:

[0033] Acquiring geographic information of the target area and performing standardization processing on the geographic information; wherein the geographic information includes terrain slope, soil type, and land use type;

[0034] Determine the susceptibility label corresponding to the geographic information based on the hierarchical analysis method;

[0035] Based on the weighted superposition method, the standardized geographic information and the landslide susceptibility index are fused to obtain a landslide susceptibility map.

[0036] Preferably, determining landslide geological disaster warning information based on the landslide susceptibility map includes:

[0037] updating the real-time rainfall risk distribution map based on the real-time rainfall data, and extracting the rainfall risk value of each sub-region in the updated rainfall risk distribution map;

[0038] performing coupling analysis on the rainfall risk value and the landslide susceptibility index of the corresponding sub-region in the landslide susceptibility map to obtain a comprehensive landslide risk index;

[0039] Based on the comprehensive landslide risk index, the target area is divided into five warning levels through the natural break method to obtain landslide geological disaster warning information.

[0040] The beneficial effects of the present application are as follows: The technical scheme adopted to solve the above technical problems is: a landslide geological disaster early warning method based on rainfall, which is applicable to the landslide geological disaster early warning system based on rainfall, and comprises:

[0041] Based on historical landslide disaster data and historical precipitation data, a plurality of rainfall monitoring points are arranged in the target area; based on historical landslide disaster data, a plurality of historical landslide disaster points are selected; each historical landslide disaster point corresponds to a preset geographic coordinate and a geological parameter;

[0042] Based on the rainfall monitoring points, real-time rainfall data are collected; based on a dynamic threshold model, real-time rainfall early warning thresholds corresponding to each historical landslide disaster point are determined through the real-time rainfall data and the geological parameters of each historical landslide disaster point;

[0043] Based on a spatial interpolation method, a real-time rainfall risk distribution map of the target area is determined through the real-time rainfall early warning thresholds; based on a clustering algorithm, a real-time landslide high-risk cluster group of the target area is determined through the real-time rainfall risk distribution map and the geographic coordinates of the historical landslide disaster points;

[0044] The real-time landslide high-risk cluster group and the real-time rainfall risk distribution map are superimposed and analyzed to obtain a real-time landslide susceptibility index of each sub-region in the target area; based on the real-time landslide susceptibility index, the sub-regions in the target area are classified in terms of landslide susceptibility to obtain the susceptibility labels corresponding to the sub-regions in the target area;

[0045] Based on the geological parameters of the target area, the susceptibility labels corresponding to the sub-regions in the target area are corrected to obtain a landslide susceptibility map; based on the landslide susceptibility map, landslide geological disaster early warning information is determined.

[0046] The beneficial effects of the present application are as follows:

[0047] (1) The present application generates a real-time rainfall risk distribution map and a landslide susceptibility map based on real-time rainfall data, historical precipitation data and landslide disaster data through the system, which can provide immediate landslide risk early warning for disaster management personnel through real-time data updating, so that preventive measures can be taken before landslide disasters occur, thereby improving the timeliness and accuracy of early warning; and through the arrangement of rainfall monitoring points and the combination of a dynamic threshold model and a clustering algorithm, a landslide high-risk cluster group in the target area can be accurately determined, so that resources can be concentrated in landslide-prone areas, and resource allocation for disaster prevention and control can be optimized;

[0048] (2) The present invention uses a dynamic threshold model, combined with historical rainfall data and geological parameters of landslide hazard sites, to more accurately set the warning threshold for each monitoring point, avoiding warning errors or lags that may be caused by fixed thresholds, thereby improving the sensitivity and accuracy of the system. In addition, the real-time landslide susceptibility index is used to divide each sub-region into landslide susceptibility categories and generate susceptibility labels, which can scientifically manage the risk level of each sub-region and formulate targeted preventive measures.

[0049] (3) The present invention can further improve the accuracy and reliability of prediction results by correcting the landslide susceptibility label through the geological parameters of the target area, especially in areas with complex geological characteristics, avoiding over-reliance on precipitation data and ignoring the impact of the geological environment; and the landslide susceptibility map and early warning information generated by the system can provide a scientific basis for relevant departments, helping decision makers make more effective disaster prevention, emergency response and resource scheduling decisions, thereby reducing the threat of landslide disasters to people's lives and property. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of the system architecture of the overall system in an embodiment of the present invention;

[0051] Figure 2 The figure is a flowchart of the steps of the overall method in one embodiment of the present invention. DETAILED DESCRIPTION

[0052] Example 1, as Figure 1 As shown, the present invention proposes a landslide geological disaster early warning system based on rainfall, comprising:

[0053] A rainfall monitoring unit is used to deploy a number of rainfall monitoring points in the target area based on historical landslide disaster data and historical precipitation data; a number of historical landslide disaster points are selected based on the historical landslide disaster data; each historical landslide disaster point corresponds to preset geographical coordinates and geological parameters;

[0054] A rainfall collection unit is used to collect real-time rainfall data based on rainfall monitoring points; based on a dynamic threshold model, the real-time rainfall warning threshold corresponding to each historical landslide disaster point is determined by using the real-time rainfall data and the geological parameters of each historical landslide disaster point;

[0055] The risk warning unit is used to determine the real-time rainfall risk distribution map of the target area based on the spatial interpolation method and the real-time rainfall warning threshold; and to determine the real-time high-risk landslide clusters in the target area based on the real-time rainfall risk distribution map and the geographical coordinates of historical landslide disaster points based on the clustering algorithm;

[0056] The landslide analysis unit is used for superimposed analysis of the real-time landslide high-risk cluster and the real-time rainfall risk distribution map to obtain a real-time landslide susceptibility index of each sub-region in the target region; and the landslide susceptibility of each sub-region in the target region is divided based on the real-time landslide susceptibility index to obtain a susceptibility label corresponding to each sub-region in the target region.

[0057] The region division unit is used for correcting the susceptibility label corresponding to each sub-region in the target region based on the geological parameters of the target region to obtain a landslide susceptibility map; and landslide geological disaster early warning information is determined based on the landslide susceptibility map.

[0058] In the present application, the rainfall monitoring point refers to a device point arranged in the target region for real-time monitoring of precipitation; these monitoring points can collect real-time precipitation data of the region, thereby providing data support for subsequent landslide warning; the historical landslide disaster data refers to related data of past landslide disaster events, including information such as the location, time, scale, and type of the disaster, and through these data, the rules and dangerous areas of landslide occurrence can be identified; the historical precipitation data refers to precipitation data of a certain region in the past; precipitation is one of the important factors affecting landslide occurrence, and therefore historical precipitation data can be used to analyze the relationship between precipitation and landslide.

[0059] In an optional embodiment, the rainfall warning threshold includes an hourly rainfall intensity threshold, a cumulative 24-hour rainfall threshold, and a cumulative 72-hour rainfall threshold; the susceptibility label includes an extremely low susceptibility area, a low susceptibility area, a medium susceptibility area, a high susceptibility area, and an extremely high susceptibility area; and the geological parameters include terrain slope, soil type, and land use type.

[0060] In an optional embodiment, a plurality of rainfall monitoring points are arranged in the target region based on the historical landslide disaster data and the historical precipitation data, including:

[0061] A digital elevation model of the target region is obtained; terrain humidity index calculation is performed based on the digital elevation model and the historical precipitation data to obtain a historical regional humidity distribution map corresponding to the target region;

[0062] Kernel density estimation is performed on the historical landslide disaster data to obtain a historical landslide disaster density cloud map corresponding to the target region;

[0063] The historical regional humidity distribution map and the historical landslide disaster density cloud map are weighted and superimposed to obtain a historical landslide sensitivity comprehensive index map;

[0064] The landslide sensitivity of each sub-region in the target region is divided based on a historical landslide sensitivity comprehensive index map to obtain a sensitivity label of each sub-region; wherein the sensitivity label includes a high-sensitivity region, a medium-sensitivity region and a low-sensitivity region.

[0065] A rain monitoring point density gradient is planned based on the sensitivity label of each sub-region, rain monitoring points are arranged at a first interval in the high-sensitivity region, rain monitoring points are arranged at a second interval in the medium-sensitivity region, and rain monitoring points are arranged at a third interval in the low-sensitivity region to obtain a rain monitoring point distribution map; wherein the first interval < the second interval < the third interval.

[0066] It is worth noting that Digital Elevation Model (DEM) is obtained through remote sensing technology, LiDAR or other measurement means, reflecting the digital representation of the earth's surface (or the terrain of a certain area); it is usually stored in grid form, providing height information within the area; by obtaining DEM data of the target area, the terrain undulation of the area can be understood, and the impact on landslide and other disasters can be analyzed; Topographic Wetness Index (TWI) is calculated based on Digital Elevation Model and precipitation data, aiming to evaluate the accumulation of surface water, especially the accumulation of water in low-lying areas; TWI is usually used to analyze which areas are prone to soil erosion, landslides and other geological disasters; its calculation formula combines factors such as slope and watershed area, reflecting the impact of different terrain on water; the wetness index map calculated based on Digital Elevation Model and historical precipitation data is used to show the water accumulation in the area; areas with higher moisture are also prone to landslides, especially when there is heavy rainfall; Kernel Density Estimation is a method of estimating the probability density function by smoothing data points; in this scenario, it is used to estimate the density of historical landslide disasters; by kernel density estimation of historical landslide disaster data points, the distribution of landslide disasters in the target area can be obtained, i.e. high-density and low-density areas of landslide events; the landslide disaster density map obtained by kernel density estimation represents the landslide disaster density of different locations in the target area, and areas with high density indicate that landslides occur more frequently in these areas; in Geographic Information System (GIS), weighted overlay is a process of superimposing multiple layers together and assigning different weights to each layer; in this scenario, the historical regional wetness distribution map and the historical landslide disaster density cloud map are weighted and overlaid, considering the topographic wetness and the density of historical landslide disasters, so as to obtain a more comprehensive evaluation map; by weighted overlay of historical wetness distribution map and landslide disaster density cloud map, a comprehensive index map is generated, indicating the landslide sensitivity of each part of the area; this map can help identify which areas have high landslide risk and which areas have relatively low risk; based on the historical landslide sensitivity comprehensive index map, the target area is divided into different levels or labels according to its landslide sensitivity; monitoring point density gradient planning refers to adjusting the density of monitoring point layout according to the sensitivity labels of each sub-area, so as to strengthen monitoring in high-sensitivity areas and reduce the number of monitoring points in low-sensitivity areas; this can effectively and reasonably allocate resources and achieve precise monitoring: in high-sensitivity areas: due to high landslide risk, more intensive rainfall monitoring points should be deployed in this area to obtain rainfall data in time and warn potential landslide risks in advance; in medium-sensitivity areas: the precipitation and landslide risk are moderate, and the monitoring points can be deployed at the second interval, with a moderate interval; in low-sensitivity areas: the landslide risk is low, and the rainfall monitoring points are sparsely deployed with a larger interval, usually at the third interval;According to the monitoring point density gradient planning, the rainfall monitoring points in different regions are arranged to form a rainfall monitoring point distribution map; the map shows the layout of the rainfall monitoring points in each region, can help analyze the precipitation data, and further provide important support for landslide risk assessment and early warning.

[0067] In an optional embodiment, the process of constructing the dynamic threshold model comprises:

[0068] Collecting rainfall data before historical landslide events, and extracting the corresponding hourly rainfall, cumulative 24-hour rainfall and cumulative 72-hour rainfall of each landslide event;

[0069] Based on the geological data of each landslide event, the rainfall data is divided into several geological condition groups; wherein the geological data includes the permeability coefficient of rock-soil mass, slope and vegetation coverage;

[0070] Statistical analysis is performed on the rainfall data in each geological condition group to determine the corresponding hourly rainfall threshold, cumulative 24-hour rainfall threshold and cumulative 72-hour rainfall threshold of each geological condition group;

[0071] Based on the support vector machine algorithm, a nonlinear mapping relationship between the geological data and the rainfall threshold is established to obtain the dynamic threshold model.

[0072] It should be noted that before the landslide disaster occurs, the rainfall data before the historical landslide events are collected and recorded. The permeability coefficient of rock-soil reflects the water permeability of rock-soil. The lower the permeability coefficient, the less the water permeation of the soil by rainfall, the higher the risk of water accumulation, and the greater the possibility of landslide. Slope is an important factor affecting the occurrence of landslide. The greater the slope, the higher the possibility of landslide. Vegetation can effectively prevent soil erosion and reduce the probability of landslide occurrence. Areas with high vegetation coverage are generally more stable. According to these geological data, all rainfall data before the occurrence of historical landslide events are divided into several geological condition groups. For example, areas with low permeability, high slope and low vegetation coverage may belong to one geological condition group, while areas with high permeability, low slope and high vegetation coverage may belong to another geological condition group. Within each geological condition group, statistical analysis of rainfall data is carried out, and the purpose is to determine the rainfall threshold under different geological conditions according to the data of historical landslide events. Support vector machine (SVM) algorithm is a powerful machine learning algorithm commonly used to solve classification and regression problems. In this problem, SVM will be used to establish a nonlinear mapping relationship between geological data (such as permeability coefficient, slope and vegetation coverage) and rainfall threshold. The change of rainfall threshold may not be a simple linear relationship, but is influenced by multiple geological factors. Support vector machine can model the relationship between geological data and rainfall threshold into a complex function through a nonlinear kernel function. Based on the training data (geological and rainfall data of historical landslide events), SVM can establish a dynamic threshold model that can automatically predict the rainfall threshold of each region according to the actual geological conditions (rock-soil permeability coefficient, slope, vegetation coverage, etc.). This dynamic threshold can change with the change of geological conditions, so as to predict the landslide risk in different geological environments. By establishing a dynamic threshold model, the possibility of landslide occurrence can be evaluated in real time according to real-time rainfall data and geological conditions during future rainfall processes. If the rainfall exceeds a certain threshold (such as hourly rainfall, 24-hour rainfall or 72-hour rainfall), the risk of landslide can be predicted, and early warning and emergency response can be carried out in advance. Through comprehensive analysis of geological conditions and rainfall data, the support vector machine model can more accurately predict the timing and location of landslide occurrence, and improve the prevention ability of landslide disaster.

[0073] In an optional embodiment, the real-time rainfall risk distribution map of the target area is determined based on the spatial interpolation method through the real-time rainfall warning threshold, comprising:

[0074] The real-time rainfall data collected by the rainfall monitoring point is preprocessed, wherein the preprocessing includes outlier elimination and data smoothing processing;

[0075] Based on the Kriging interpolation algorithm, the preprocessed rainfall data is spatially interpolated in combination with the terrain elevation data and the land use type data to obtain the real-time rainfall risk distribution map of the target area.

[0076] It should be noted that outliers refer to values in the data that are significantly different from other data points, usually due to measurement errors, equipment failures, etc.; the purpose of outlier rejection is to ensure the accuracy of the data, to prevent abnormal data from affecting subsequent analysis; some common outlier detection methods include standard deviation-based detection, box plot analysis, etc., through which obvious outliers can be identified and removed; data smoothing refers to removing random fluctuations in the data through mathematical methods, making the data smoother and more continuous; common smoothing techniques include moving average, weighted average, low-pass filtering, etc.; in rainfall data, smoothing helps to eliminate noise caused by short-term rainfall fluctuations, making the trend of rainfall more clear, thereby facilitating subsequent analysis; Kriging interpolation is a geostatistical method based on spatial data, widely used in geographic information systems (GIS) and environmental monitoring, etc.; its core idea is to use the data of known points to predict the values of other locations; spatial interpolation refers to generating a weighted average value to estimate the rainfall at unknown locations based on the results of spatial autocorrelation analysis; the weighting coefficient of each point is determined according to its distance from known points and spatial autocorrelation relationship; Kriging method optimizes the weighting coefficient to minimize the prediction error, thereby obtaining a more accurate spatial distribution; terrain elevation has an important influence on rainfall distribution; for example, high-altitude areas may have more rainfall, while low-lying areas are prone to waterlogging; therefore, Kriging interpolation not only relies on rainfall monitoring data, but also considers terrain factors; in the interpolation process, terrain data as auxiliary information can adjust the interpolation results, making the interpolation results more consistent with the actual terrain rainfall distribution; land use type data (such as urban, agricultural land, forest, etc.) also affects rainfall distribution; for example, urban areas may have more rainfall due to the urban heat island effect, which may cause local rainfall to increase; combining land use data with rainfall data can further refine the spatial interpolation results, making the predicted rainfall risk distribution more realistic and accurate; the real-time rainfall risk distribution map of the target area will show the rainfall intensity and potential risks in each region, for example: high-risk areas: such as areas with high rainfall or long duration, which may experience floods or landslides and other natural disasters; low-risk areas: areas with less rainfall and relatively stable land use and terrain, which have lower rainfall risks; the generated rainfall risk distribution map can help relevant departments (such as meteorological bureaus, emergency management bureaus, etc.) monitor rainfall in real time, providing support for disaster prevention and emergency response.

[0077] In an optional embodiment, the real-time landslide high-risk cluster of the target area is determined based on the real-time rainfall risk distribution map and the geographical coordinates of the historical landslide disaster points by a clustering algorithm, comprising:

[0078] extracting geographic coordinates of historical landslide disaster points and rainfall risk values of corresponding positions in a real-time rainfall risk distribution map;

[0079] performing clustering analysis on the landslide disaster points based on a density peak clustering algorithm and taking the rainfall risk values as weights to obtain a plurality of initial clusters.

[0080] performing boundary optimization on each initial cluster to obtain a real-time landslide high-risk cluster of a target region; wherein the boundary optimization comprises cluster splitting and merging based on topographic fault data.

[0081] It is worth noting that the geographic coordinates of historical landslide disaster points represent the locations where landslide disasters have occurred in the past, and their geographic coordinates provide a reference for spatial location. Historical disaster points can be collected through satellite images, post-disaster assessment reports, or other means. In the previous steps, we have generated a real-time rainfall risk distribution map for the target area, which shows the rainfall risk in different regions. The rainfall risk value of each region is a comprehensive result of factors such as precipitation intensity, terrain, land use, etc. Through spatial overlap operations (such as spatial analysis of point and raster data), the rainfall risk value corresponding to the location of the historical landslide disaster point can be extracted from the real-time rainfall risk distribution map. In this way, we can assign a specific rainfall risk value to each historical disaster point for subsequent clustering analysis. Density peak clustering is a clustering algorithm that does not require pre-setting the number of clusters. It identifies clusters by calculating the density of each data point and the distance from the points with higher density. Areas with high density will form clusters, while areas with lower density will be identified as noise. The core of the density peak clustering algorithm is to use rainfall risk value as weight. This means that in the clustering process, landslide disaster points with higher rainfall risk values will be considered more important data points, and their influence on the final clustering will be greater. Based on the geographic coordinates of historical landslide disaster points and the corresponding rainfall risk values, the density peak clustering algorithm can cluster these disaster points into multiple preliminary clusters. Each cluster represents a region with high rainfall risk, which may be a high-risk area for landslide disasters. After clustering analysis, preliminary clusters are formed, but due to the complexity of the terrain and other factors, the boundaries of these clusters may not completely match the actual situation. Therefore, it is necessary to optimize the boundaries of each initial cluster to more accurately define the high-risk areas of landslides. Boundary optimization includes the following two key steps: Topographic fault data refers to the changes in the terrain within the region, such as mountains, faults, rivers, and other natural geographical features. Topographic changes are often closely related to the occurrence of landslide disasters. For example, steep slopes and faults are prone to landslides. According to the guidance of topographic data, the boundaries of the clusters are optimized. Topographic faults may cause the boundaries of the original clusters to be inaccurate, so some areas that are heavily affected by the terrain need to be split, or clusters with similar terrain features need to be merged. In this way, the boundaries of high-risk areas that are more consistent with the actual terrain and landslide occurrence patterns can be obtained. For example, if a cluster is located on a steep slope, the topographic fault data may indicate that the landslide risk in this area is high, so the boundaries of this cluster may need to be expanded. If a cluster crosses a fault line, it may need to be split into two more accurate clusters.

[0082] In an optional embodiment, the formula for calculating the landslide susceptibility index is as follows:

[0083] ;

[0084] wherein, represents a landslide susceptibility index, represents a weight coefficient corresponding to the rainfall warning threshold, represents an overrun multiple of the rainfall warning threshold, represents a terrain slope correction coefficient, represents a stability coefficient corresponding to the soil type.

[0085] In an optional embodiment, the landslide susceptibility labels corresponding to each sub-region in the target region are corrected based on the geological parameters of the target region to obtain a landslide susceptibility map, including:

[0086] obtaining geographical information of the target region and performing standardization processing on the geographical information; wherein the geographical information includes terrain slope, soil type and land use type;

[0087] determining the landslide susceptibility labels corresponding to the geographical information based on the analytic hierarchy process;

[0088] fusing the standardized geographical information and the landslide susceptibility index based on the weighted superposition method to obtain the landslide susceptibility map.

[0089] It should be noted that the terrain slope refers to the degree of inclination of the ground surface, usually expressed in angle; areas with high slope are more prone to landslides, especially during heavy rain; slope can be calculated through DEM; different types of soil have large differences in water permeability, retention capacity, and bearing capacity, etc., and some soils (such as loose sandy soil) may be more prone to landslides; soil type can be obtained through soil classification map or related database; land use type reflects the development and use status of land; for example, urban construction, agricultural activities, forest coverage, etc. will affect the stability of soil; land use type is generally obtained through remote sensing image or land use database; standardization refers to the numerical conversion of the above geographical information to make them have uniform measurement standards and comparability; since different types of geographical information (such as slope, soil, land use) may differ greatly in numerical range, standardization will convert these data into the same scale or standardized values (such as between 0 and 1); common standardization methods include: min-max standardization: subtract the minimum value from each data value and divide by the range (maximum value - minimum value) of the data; Z-score standardization: convert data to standard normal distribution by subtracting the mean and dividing by the standard deviation; AHP is a multi-level decision analysis method used to evaluate and rank by breaking down complex problems into different levels and factors; therefore, we can assign a relative importance weight to each geographical information element (such as terrain slope, soil type and land use type); AHP converts these geographical information into "susceptibility labels", i.e. the degree of influence of each geographical element on landslide occurrence; the evaluation process is to first determine the hierarchical relationship between the target (landslide susceptibility) and the influencing factors; according to expert knowledge or data analysis results, give the relative importance judgment between influencing factors; for example, slope may have more influence on landslide than soil type; calculate the weight of each factor through the mathematical model of AHP; according to the calculated weight and the value of each factor (such as slope value, soil type code), assign a susceptibility label to each region; weighted overlay is a commonly used spatial analysis technique that combines multiple levels of data (here, standardized geographical information and landslide susceptibility index) to generate a comprehensive evaluation result; in this process, each factor is weighted according to its weight and then overlaid; in weighted overlay, each standardized geographical information is weighted according to its importance in susceptibility assessment; for example, if the weight of slope is high, the value of slope will have a greater impact on the final result; overlay operation is to combine weighted geographical information and landslide susceptibility index to generate a comprehensive score; this usually means combining multiple factors of each region into a final landslide susceptibility score; landslide susceptibility index is a comprehensive value calculated from different factors, indicating the risk of landslide in the region;In this process, the standardized geographic information and landslide susceptibility index are weighted and superimposed to generate the final landslide susceptibility map; the higher the susceptibility score of each region, the more likely it is to occur in that region; through the above steps, the final landslide susceptibility map shows the landslide susceptibility of each point or grid in the target area; each region of the map will have a susceptibility value indicating the landslide risk of that area; this map can help governments and disaster management agencies identify high-risk areas, plan for disaster prevention, and take measures to reduce the likelihood of landslides, such as improving land management, strengthening soil protection, and optimizing infrastructure design.

[0090] In an optional embodiment, the landslide geological disaster warning information is determined based on the landslide susceptibility map, including:

[0091] Based on the real-time rainfall data, the real-time rainfall risk distribution map is updated, and the rainfall risk values of each sub-region in the updated rainfall risk distribution map are extracted;

[0092] Coupling analysis is performed on the rainfall risk value and the landslide susceptibility index of the corresponding sub-region in the landslide susceptibility map to obtain a landslide risk comprehensive index;

[0093] Based on the landslide risk comprehensive index, the target area is divided into five warning levels by the natural break method to obtain the landslide geological disaster warning information.

[0094] It should be noted that real-time rainfall data reflects the amount of rainfall in the current or recent period; rainfall is an important trigger factor for landslides, as heavy rainfall can increase soil moisture and reduce soil resistance, leading to landslides; using real-time rainfall data, a rainfall risk distribution map can be generated or updated, which shows the rainfall risk in different areas; the rainfall risk value of each sub-area reflects the current rainfall level in that area, the greater the rainfall, the higher the rainfall risk value, and the greater the likelihood of landslides; it can be calculated based on rainfall (such as cumulative rainfall, rainfall intensity, etc.); if the rainfall exceeds a certain threshold, some areas may be marked as high-risk areas; the rainfall risk value of each sub-area can be obtained by comparing the rainfall data of that area with the pre-set standard; these values will be dynamically calculated according to the intensity, duration, etc. of the rainfall, and updated to the rainfall risk distribution map; if a sub-area has more than 100 mm of rainfall in the past 24 hours, its rainfall risk value will be updated to a higher value; at this time, the risk value of the area is extracted and ready to be combined with the corresponding data in the landslide susceptibility map for analysis; the rainfall risk value of each sub-area is coupled with the landslide susceptibility index, i.e. combining the risk of rainfall with the landslide susceptibility of the area itself; through this coupling, it can be identified which areas are most likely to have landslides under rainfall conditions; for example, some areas may have a low landslide susceptibility, but due to extreme rainfall, their overall risk value may still be high; the natural break method is a commonly used classification method that divides a dataset into multiple categories, making the data within each category relatively uniform, while the data between different categories is as different as possible; in this application, it is used to divide the target area into different warning levels according to the landslide risk comprehensive index; the warning levels divided will be used as landslide geological disaster warning information provided to relevant departments or the public for disaster prevention and emergency response; these information can help relevant departments to reasonably arrange emergency response and take preventive measures in advance to avoid or reduce the loss of landslide disasters.

[0095] In some embodiments, as shown in FIG. 2, the present application provides a landslide geological disaster warning method based on rainfall, which is applicable to the landslide geological disaster warning system based on rainfall described above, and includes the following steps: Figure 2

[0096] S1, based on historical landslide disaster data and historical precipitation data, a plurality of rainfall monitoring points are arranged in the target area; a plurality of historical landslide disaster points are selected based on historical landslide disaster data; each historical landslide disaster point corresponds to a pre-set geographic coordinate and geological parameter;

[0097] ​S2, collecting real-time rainfall data based on the rainfall monitoring points; determining the real-time rainfall warning threshold corresponding to each historical landslide disaster point based on the dynamic threshold model through the real-time rainfall data and the geological parameters of each historical landslide disaster point;

[0098] S3, determining the real-time rainfall risk distribution map of the target region based on the spatial interpolation method through the real-time rainfall warning threshold; determining the real-time landslide high-risk cluster of the target region based on the clustering algorithm through the real-time rainfall risk distribution map and the geographic coordinates of the historical landslide disaster points;

[0099] S4, superimposing and analyzing the real-time landslide high-risk cluster and the real-time rainfall risk distribution map to obtain the real-time landslide proneness index of each sub-region in the target region; dividing the landslide proneness of each sub-region in the target region based on the real-time landslide proneness index to obtain the proneness label corresponding to each sub-region in the target region;

[0100] S5, correcting the proneness label corresponding to each sub-region in the target region based on the geological parameters of the target region to obtain the landslide proneness map; determining the landslide geological disaster warning information based on the landslide proneness map.

[0101] The embodiments of the present application are described in detail above in combination with the drawings, but the present application is not limited thereto, and various changes can be made within the knowledge of those skilled in the art without departing from the purpose of the present application.

Claims

1. A landslide geological disaster early warning system based on rainfall, characterized in that: include: A rainfall monitoring unit (1), the rainfall monitoring unit (1) is used to deploy a plurality of rainfall monitoring points in a target area based on historical landslide disaster data and historical precipitation data; select a plurality of historical landslide disaster points based on the historical landslide disaster data; each of the historical landslide disaster points corresponds to preset geographical coordinates and geological parameters; A rainfall collection unit (2), the rainfall collection unit (2) is used to collect real-time rainfall data based on the rainfall monitoring point; Determine the real-time rainfall warning threshold corresponding to each of the historical landslide disaster points based on the dynamic threshold model using the real-time rainfall data and the geological parameters of each of the historical landslide disaster points; The process of constructing the dynamic threshold model includes: Collect rainfall data before historical landslide events and extract the hourly rainfall, cumulative 24-hour rainfall, and cumulative 72-hour rainfall corresponding to each landslide event; Based on the geological data of each landslide event, the rainfall data is divided into a plurality of geological condition groups; wherein the geological data includes rock and soil permeability coefficient, slope and vegetation coverage; Performing statistical analysis on the rainfall data within each geological condition group to determine the hourly rainfall threshold, the cumulative 24-hour rainfall threshold, and the cumulative 72-hour rainfall threshold corresponding to each geological condition group; Establishing a nonlinear mapping relationship between the geological data and the rainfall threshold based on a support vector machine algorithm to obtain the dynamic threshold model; A risk warning unit (3) is used to determine a real-time rainfall risk distribution map of the target area through the real-time rainfall warning threshold based on a spatial interpolation method; and to determine a real-time landslide high-risk cluster of the target area through the real-time rainfall risk distribution map and the geographical coordinates of the historical landslide disaster points based on a clustering algorithm; A landslide analysis unit (4) is used to perform superposition analysis on the real-time landslide high-risk cluster and the real-time rainfall risk distribution map to obtain a real-time landslide susceptibility index for each sub-region in the target area; and to divide each sub-region in the target area into landslide susceptibility groups based on the real-time landslide susceptibility index to obtain a susceptibility label corresponding to each sub-region in the target area; A region division unit (5) is used to modify the susceptibility labels corresponding to each sub-region in the target region based on the geological parameters of the target region to obtain a landslide susceptibility map; and to determine landslide geological disaster warning information based on the landslide susceptibility map.

2. The landslide geological disaster early warning system based on rainfall according to claim 1 is characterized in that: The rainfall warning thresholds include hourly rainfall intensity thresholds, cumulative 24-hour rainfall thresholds, and cumulative 72-hour rainfall thresholds; the susceptibility labels include extremely low susceptibility areas, low susceptibility areas, moderate susceptibility areas, high susceptibility areas, and extremely high susceptibility areas; the geological parameters include terrain slope, soil type, and land use type.

3. The landslide geological disaster early warning system based on rainfall according to claim 2 is characterized in that: Based on historical landslide hazard data and historical precipitation data, several rainfall monitoring points are set up in the target area, including: Acquire a digital elevation model of the target area; calculate a terrain humidity index based on the digital elevation model and the historical precipitation data to obtain a historical regional humidity distribution map corresponding to the target area; Performing kernel density estimation on the historical landslide disaster data to obtain a historical landslide disaster density cloud map corresponding to the target area; Performing weighted superposition on the historical regional moisture distribution map and the historical landslide disaster density cloud map to obtain a historical landslide sensitivity comprehensive index map; Based on the historical landslide sensitivity comprehensive index map, each sub-region in the target area is divided into landslide sensitivity categories to obtain sensitivity labels for each sub-region; wherein the sensitivity labels include high-sensitivity areas, medium-sensitivity areas, and low-sensitivity areas; Based on the sensitivity labels of each sub-area, a monitoring point density gradient planning is performed, wherein rainfall monitoring points are arranged at a first spacing in the highly sensitive area, at a second spacing in the medium-sensitive area, and at a third spacing in the low-sensitivity area, so as to obtain a rainfall monitoring point distribution map; wherein the first spacing < the second spacing < the third spacing.

4. The landslide geological disaster early warning system based on rainfall according to claim 3 is characterized in that: Determining a real-time rainfall risk distribution map of the target area by using the real-time rainfall warning threshold based on a spatial interpolation method includes: Preprocessing the real-time rainfall data collected by the rainfall monitoring point, wherein the preprocessing includes outlier removal and data smoothing; Based on the Kriging interpolation algorithm, combined with terrain elevation data and land use type data, the preprocessed rainfall data is spatially interpolated to obtain a real-time rainfall risk distribution map of the target area.

5. The landslide geological disaster early warning system based on rainfall according to claim 4 is characterized in that: Determining a real-time high-risk landslide cluster in the target area based on the real-time rainfall risk distribution map and the geographical coordinates of the historical landslide disaster points based on a clustering algorithm includes: Extracting the geographical coordinates of the historical landslide disaster point and the rainfall risk value of the corresponding position in the real-time rainfall risk distribution map; Based on the density peak clustering algorithm, the landslide hazard points are clustered and analyzed with the rainfall risk value as a weight to obtain a number of initial clusters; Boundary optimization is performed on each of the initial clusters to obtain real-time high-risk landslide clusters in the target area; wherein the boundary optimization includes cluster segmentation and merging based on terrain fault data.

6. The landslide geological disaster early warning system based on rainfall according to claim 5, characterized in that: The calculation formula of the landslide susceptibility index is as follows: ； in, Landslide susceptibility index Indicates the The weight coefficient corresponding to the rainfall warning threshold is: Indicates the The number of times the rainfall warning threshold exceeds the limit, represents the terrain slope correction coefficient, Indicates the stability coefficient corresponding to the soil type.

7. The landslide geological disaster early warning system based on rainfall according to claim 6 is characterized in that: Modifying the susceptibility labels corresponding to the sub-regions in the target region based on the geological parameters of the target region to obtain a landslide susceptibility map includes: Acquiring geographic information of the target area and performing standardization processing on the geographic information; wherein the geographic information includes terrain slope, soil type, and land use type; Determine the susceptibility label corresponding to the geographic information based on the hierarchical analysis method; Based on the weighted superposition method, the standardized geographic information and the landslide susceptibility index are fused to obtain a landslide susceptibility map.

8. The landslide geological disaster early warning system based on rainfall according to claim 7 is characterized in that: Determining landslide geological disaster warning information based on the landslide susceptibility map includes: updating the real-time rainfall risk distribution map based on the real-time rainfall data, and extracting the rainfall risk value of each sub-region in the updated rainfall risk distribution map; performing coupling analysis on the rainfall risk value and the landslide susceptibility index of the corresponding sub-region in the landslide susceptibility map to obtain a comprehensive landslide risk index; Based on the comprehensive landslide risk index, the target area is divided into five warning levels through the natural break method to obtain landslide geological disaster warning information.

9. A landslide geological disaster early warning method based on rainfall, which is applicable to a landslide geological disaster early warning system based on rainfall according to any one of claims 1 to 8, characterized in that: include: Several rainfall monitoring points are deployed in the target area based on historical landslide hazard data and historical precipitation data; Selecting a number of historical landslide disaster points based on historical landslide disaster data; each of the historical landslide disaster points corresponds to preset geographical coordinates and geological parameters; Collecting real-time rainfall data based on the rainfall monitoring points; Determine the real-time rainfall warning threshold corresponding to each of the historical landslide disaster points based on the dynamic threshold model using the real-time rainfall data and the geological parameters of each of the historical landslide disaster points; Determine the real-time rainfall risk distribution map of the target area through the real-time rainfall warning threshold based on the spatial interpolation method; Determining the real-time landslide high-risk clusters in the target area based on the real-time rainfall risk distribution map and the geographical coordinates of the historical landslide disaster points based on a clustering algorithm; Overlaying and analyzing the real-time landslide high-risk clusters and the real-time rainfall risk distribution map to obtain a real-time landslide susceptibility index for each sub-area in the target area; Based on the real-time landslide susceptibility index, each sub-region in the target region is divided into landslide susceptibility categories to obtain a susceptibility label corresponding to each sub-region in the target region; Modifying the susceptibility labels corresponding to the sub-regions in the target region based on the geological parameters of the target region to obtain a landslide susceptibility map; Landslide geological disaster warning information is determined based on the landslide susceptibility map.

Images