Landslide disaster data processing method, device and equipment

Abstract

The invention provides a landslide disaster data processing method, device and equipment, belongs to the technical field of computer information processing, and solves the problems that an existing landslide disaster data processing method is inaccurate and the troubleshooting accuracy of a landslide hidden danger area is not high. The method comprises the following steps: acquiring remote sensing geological data of a target area within a preset target time range; obtaining grid region data according to the remote sensing geological data; obtaining evaluation factor data according to the remote sensing geological data and the grid region data; the evaluation factor data are input into a landslide prediction model for processing, grid area landslide susceptibility data are obtained, the landslide prediction model processes the evaluation factor data through a target function, and the grid area landslide susceptibility data are obtained; and obtaining landslide disaster susceptibility prediction data of the target area according to the landslide susceptibility data of the grid area. According to the scheme, the accuracy and reliability of landslide disaster prediction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer information processing, and in particular to a landslide disaster data processing method, device and equipment. Background Art

[0002] Landslides are geological events in which soil and rock on a slope slide downward. Factors such as strong earthquakes, surface water and groundwater movement, and natural erosion can affect the properties of soil and rock, the geological structure, and the internal structure of the slope layer. These factors destroy the soil-rock balance of the slope, leading to landslides. Landslides cause tens of thousands of casualties and tens of billions of dollars in economic losses every year. In addition, landslides are very likely to be accompanied by other geological disasters such as collapse and debris flow, and may also trigger secondary disasters such as reservoir surges and barrier lakes, further exacerbating the consequences and losses of the disasters.

[0003] Landslide susceptibility assessment is the primary content of geological disaster assessment. The landslide susceptibility zoning map produced based on the assessment results can directly reflect the possibility of landslide occurrence. At present, due to the difficulty in obtaining historical landslide points and the uncertainty and complexity of landslide causes, landslide susceptibility assessment is crucial for determining the spatiotemporal distribution and occurrence probability of landslides in natural disaster risk management and post-disaster reconstruction. Landslide susceptibility assessment methods mainly include empirical models, statistical models, and machine learning models. Through these methods, the occurrence of landslides can be predicted more accurately, thereby effectively preventing and managing them. However, landslide disasters are the result of the combined action of multiple hazard factors. The effects of various hazard factors on the development of landslide disasters are very complex, and it is difficult to accurately express the promotion relationship between different factors and the development of landslide disasters from a theoretical level. Summary of the invention

[0004] The present invention provides a landslide disaster data processing method, device and equipment, which solve the problems that the existing landslide disaster data processing method is inaccurate and the accuracy of landslide hazard area inspection is not high.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] An embodiment of the present invention provides a landslide disaster data processing method, comprising:

[0007] Acquire remote sensing geological data of the target area within a preset target time range;

[0008] Obtaining grid area data according to the remote sensing geological data;

[0009] Obtaining evaluation factor data according to the remote sensing geological data and the grid area data;

[0010] Inputting the evaluation factor data into a landslide prediction model for processing to obtain grid area landslide susceptibility data, wherein the landslide prediction model processes the evaluation factor data through an objective function to obtain grid area landslide susceptibility data;

[0011] The landslide susceptibility prediction data of the target area are obtained according to the landslide susceptibility data of the grid area.

[0012] Optionally, grid region data is obtained according to the remote sensing geological data, including:

[0013] The remote sensing geological data is rasterized according to a preset length to obtain raster area data.

[0014] Optionally, obtaining evaluation factor data according to the remote sensing geological data and the grid area data includes:

[0015] Obtaining a terrain evaluation factor, a geomorphic evaluation factor, a hydrological condition evaluation factor, and an engineering activity intensity evaluation factor based on the remote sensing geological data and the grid area data;

[0016] The terrain evaluation factor, landform evaluation factor, hydrological condition evaluation factor, and engineering activity intensity evaluation factor are graded to obtain evaluation factor data.

[0017] Optionally, a terrain evaluation factor, a landform evaluation factor, a hydrological condition evaluation factor and an engineering activity intensity evaluation factor are obtained based on the remote sensing geological data and the grid area data, including:

[0018] According to the influence of the terrain data in the grid area on the development and distribution of the landslide, a terrain evaluation factor is obtained, wherein the terrain evaluation factor includes one or more of elevation, slope, slope aspect, plane curvature, profile curvature and normalized vegetation index;

[0019] Obtaining a geomorphic evaluation factor according to the remote sensing geological data and the grid area data, including: obtaining a geomorphic evaluation factor according to the influence of the geomorphic data in the grid area on the stability of the landslide, wherein the geomorphic evaluation factor includes one or more of topography, rock formation, topographic moisture and fault;

[0020] Obtaining a hydrological condition evaluation factor according to the remote sensing geological data and the grid area data, including: obtaining a hydrological condition evaluation factor according to the influence of the hydrological data in the grid area on the generation of landslides, wherein the hydrological condition evaluation factor includes one or more of annual rainfall, water flow intensity and distance from the river;

[0021] According to the remote sensing geological data and the grid area data, an engineering activity intensity evaluation factor is obtained, including: according to the influence of the engineering activity intensity data in the grid area on the generation of landslides, an engineering activity intensity evaluation factor is obtained, wherein the engineering activity intensity evaluation factor includes the distance from residential areas, the distance from roads and the distance from earthquake sources.

[0022] Optionally, the terrain evaluation factor, landform evaluation factor, hydrological condition evaluation factor, and engineering activity intensity evaluation factor are graded to obtain evaluation factor data, including:

[0023] The slope and elevation in the terrain evaluation factor are graded according to the natural break point method to obtain evaluation factor data of the slope and elevation;

[0024] Classifying the slope aspects in the terrain evaluation factor according to direction to obtain evaluation factor data of the slope aspects;

[0025] The rock groups in the geomorphic evaluation factor are classified according to the point density of landslide hazard points in each rock group to obtain evaluation factor data of the rock group;

[0026] The rainfall in the hydrological condition evaluation factor is graded according to the natural break point method to obtain the evaluation factor data of the rainfall;

[0027] Classifying the distance to the river in the hydrological condition evaluation factor according to a first preset step length to obtain evaluation factor data of the distance to the river;

[0028] Classifying the distance to the road in the engineering activity intensity evaluation factor according to a first preset step length to obtain evaluation factor data of the distance to the road;

[0029] The distance from the residential area in the engineering activity intensity evaluation factor is graded according to a second preset step size to obtain evaluation factor data of the distance from the residential area.

[0030] Optionally, the evaluation factor data is input into a landslide prediction model for processing to obtain grid area landslide susceptibility data, including:

[0031] according to

[0032]

[0033] The information contribution value of the evaluation factor data to landslide disasters is obtained, where χ i is the level of the evaluation factor in the evaluation unit, I(χ i , H) is the evaluation factor χ i The amount of information contributed to landslide hazards, S is the total number of units in the study area, S i The study area contains the evaluation factor χi The number of units, N is the total number of units containing disaster points in the study area, N i The evaluation factor χ is distributed in the landslide disaster area i The number of k The comprehensive information corresponding to the kth evaluation factor, m is the number of evaluation factors;

[0034] according to

[0035]

[0036] Get the weight data of the kth evaluation factor among all evaluation factors, where m, n, and t are the total number of evaluation factors, the number of classification trees, and the number of nodes in a single tree, respectively; D Gkhj is the Gini index reduction value of the kth evaluation factor at the jth node of the hth tree; P k is the importance of the kth evaluation factor among all evaluation factors;

[0037] according to

[0038]

[0039] Get the comprehensive information value, where y is the comprehensive information value;

[0040] According to the comprehensive information value, landslide susceptibility data is obtained.

[0041] Optionally, obtaining landslide susceptibility prediction data according to the grid area landslide susceptibility data includes:

[0042] Statistical processing is performed on the landslide susceptibility data of the grid area to obtain landslide susceptibility prediction data.

[0043] The embodiment of the present invention further provides a landslide disaster data processing device, comprising:

[0044] An acquisition module is used to acquire remote sensing geological data of a target area within a preset target time range;

[0045] The processing module is used to obtain grid area data according to the remote sensing geological data; obtain evaluation factor data according to the remote sensing geological data and the grid area data; input the evaluation factor data into the landslide prediction model for processing to obtain grid area landslide susceptibility data, wherein the landslide prediction model processes the evaluation factor data through the objective function to obtain the grid area landslide susceptibility data;

[0046] The generation module is used to obtain the landslide susceptibility prediction data of the target area based on the landslide susceptibility data of the grid area.

[0047] An embodiment of the present invention further provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program executes the above method when executed by the processor.

[0048] An embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above method.

[0049] The technical solution of the present invention includes at least the following effects:

[0050] The above-mentioned scheme of the present invention obtains remote sensing geological data of the target area within a preset target time range; obtains grid area data based on the remote sensing geological data; obtains evaluation factor data based on the remote sensing geological data and the grid area data; inputs the evaluation factor data into the landslide prediction model for processing to obtain grid area landslide susceptibility data, wherein the landslide prediction model processes the evaluation factor data through an objective function to obtain grid area landslide susceptibility data; obtains landslide disaster susceptibility prediction data of the target area based on the grid area landslide susceptibility data. This technical scheme reduces the influence of subjective factors on the evaluation factor weights by determining the weights of each evaluation factor, thereby improving the accuracy and reliability of the landslide disaster prediction method and providing a more scientific basis for the prevention, control and management of landslide disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flow chart of a landslide disaster data processing method provided by an embodiment of the present invention;

[0052] Figure 2 is a landslide susceptibility zoning map provided by an embodiment of the present invention;

[0053] Figure 3 is a structural diagram of a landslide disaster data processing device provided by an embodiment of the present invention;

[0054] Figure 4 is a schematic diagram of the structure of a computing device provided by an embodiment of the present invention;

[0055] Among them, 21. Landslide disaster occurrence points; 22. Extremely low landslide prone areas and low landslide prone areas; 23. Medium landslide prone areas; 24. High landslide prone areas; 25. Extremely high landslide prone areas. DETAILED DESCRIPTION

[0056] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0057] like Figure 1 As shown, an embodiment of the present invention provides a landslide disaster data processing method, comprising:

[0058] Step 11, obtaining remote sensing geological data of the target area within a preset target time range;

[0059] Step 12, obtaining grid area data according to the remote sensing geological data;

[0060] Step 13, obtaining evaluation factor data according to the remote sensing geological data and the grid area data;

[0061] Step 14, inputting the evaluation factor data into a landslide prediction model for processing to obtain grid area landslide susceptibility data, wherein the landslide prediction model processes the evaluation factor data through an objective function to obtain grid area landslide susceptibility data;

[0062] Step 15: obtaining the landslide susceptibility prediction data of the target area according to the landslide susceptibility data of the grid area.

[0063] In this example, in order to analyze the landslide susceptibility of the target area, relevant research is needed to collect basic data; specifically, by determining a specific target area, that is, a specific range around a mountain area or a river basin, and clarifying the preset target time range, such as the past five or ten years, obtain the geological related data of the area obtained during this time period through satellite remote sensing or aerial remote sensing; after obtaining the remote sensing geological data, it is converted into a raster area data format; among them, the raster data divides the specific target area into regular grid units; after forming the raster area data, various evaluation factors closely related to the landslide susceptibility are extracted, screened and calculated from the acquired remote sensing geological data and the converted raster area data; these evaluation factors are indicators that can reflect the possibility of landslide occurrence from different angles; through the comprehensive determination and assignment of these and other related evaluation factors, the evaluation factor data is finally obtained to provide input for the subsequent landslide prediction model. input data; after obtaining the evaluation factor data, predict the possibility of landslide in each grid area according to the input evaluation factor data, that is, obtain the landslide susceptibility data of the grid area; wherein, the objective function is the core part of the model, which defines how to calculate and process according to the input evaluation factor data; the target function will comprehensively consider the relationship between each evaluation factor and the degree of influence on the landslide susceptibility, and convert the evaluation factor data into the landslide susceptibility value of each grid area through mathematical operation; after obtaining the landslide susceptibility data of each grid area, it is necessary to conduct a comprehensive evaluation of the entire target area to obtain the landslide susceptibility prediction data of the target area; the prediction data can reflect the landslide susceptibility of the entire target area, and provide an important reference basis for the prevention, monitoring and response of landslide disasters; the above technical scheme of the present invention improves the accuracy and reliability of landslide disaster prediction, and provides a more scientific basis for the prevention, control and management of landslide disasters.

[0064] In an optional embodiment of the present invention, step 12 may include:

[0065] Step 121, rasterizing the remote sensing geological data according to a preset length to obtain raster area data.

[0066] In this example, the geographical coordinates of the remote sensing geological data are between 35°09′ and 35°59′ north latitude and 103°37′ and 104°30′ east longitude. The geological structure of this area is complex and the neotectonic movement is relatively strong. Therefore, earthquakes occur frequently, and thousands of landslide disasters caused by earthquakes are mostly caused by earthquakes and rainfall. According to the set grid size, 12.5m×12.5m is used as the evaluation grid unit size, and the study area is divided into 53131004 evaluation grid units to form grid area data.

[0067] In an optional embodiment of the present invention, step 13 may include:

[0068] Step 131, obtaining a terrain evaluation factor, a landform evaluation factor, a hydrological condition evaluation factor, and an engineering activity intensity evaluation factor according to the remote sensing geological data and the grid area data;

[0069] Step 132, the terrain evaluation factor, the landform evaluation factor, the hydrological condition evaluation factor, and the engineering activity intensity evaluation factor are graded to obtain evaluation factor data.

[0070] In this example, considering that the terrain factor is the air condition that controls the slope, it determines the development and distribution of the landslide to a large extent. For this reason, the elevation, slope, slope aspect, plane curvature, profile curvature and Normalized Difference Vegetation Index (NDVI) are extracted as the reflection factors of the terrain;

[0071] As the basic building block of the slope, the properties of the rock group have an absolute control over the slope stability, so topography, rock group, terrain moisture and faults are selected as evaluation factors;

[0072] The scouring effect of the river on the bank, rainwater erosion, and groundwater changes will cause the soil texture to soften and thus cause landslides. Therefore, the annual cumulative rainfall, water flow intensity, and distance from the river were selected as evaluation factors reflecting the hydrological conditions of the study area.

[0073] The areas with frequent human engineering activities in the study area are mostly landslide disaster-prone areas, and the distance to residential areas, distance to roads, and distance to earthquake sources are selected as evaluation factors reflecting the intensity of human engineering activities;

[0074] The evaluation factors are graded by combining the characteristics of each evaluation factor and using a variety of grading standards. Among them, the natural break point method is a statistical method for grading and classifying based on the statistical distribution law of numerical values, which can maximize the differences between classes. Therefore, rainfall, slope, and elevation are graded according to the natural break point method. Slope aspect is graded according to direction. Roads and rivers are graded with a step length of 500m. Considering the extensiveness and complexity of human activities, the distance from residential areas is graded with a step length of 5km. In view of the integrity and complexity of the rock and soil body, the rock group can be divided as a whole, and the rock group can be divided into 8 categories according to the point density of landslide hazard points in each rock group. Based on precipitation data, a multi-year average precipitation contour map is generated, and the distribution law and frequency of precipitation data at the disaster point are statistically analyzed. It is found that most disaster points are located in areas with high precipitation, and the precipitation contour map is rasterized and re-divided into 5 levels.

[0075] In an optional embodiment of the present invention, step 14 may include:

[0076] Step 141, according to

[0077]

[0078] The information contribution value of the evaluation factor data to landslide disasters is obtained, where χ i is the level of the evaluation factor in the evaluation unit, I(χ i , H) is the evaluation factor χ i The amount of information contributed to landslide hazards, S is the total number of units in the study area, S i The study area contains the evaluation factor χ i The number of units, N is the total number of units containing disaster points in the study area, N i The evaluation factor χ is distributed in the landslide disaster area i The number of k The comprehensive information corresponding to the kth evaluation factor, m is the number of evaluation factors;

[0079] Step 142, according to

[0080]

[0081] Get the weight data of the kth evaluation factor among all evaluation factors, where m, n, and t are the total number of evaluation factors, the number of classification trees, and the number of nodes in a single tree, respectively; D Gkhj is the Gini index reduction value of the kth evaluation factor at the jth node of the hth tree; P k is the importance of the kth evaluation factor among all evaluation factors;

[0082] Step 143, according to

[0083]

[0084] Get the comprehensive information value, where y is the comprehensive information value;

[0085] Step 144, obtaining landslide susceptibility data according to the comprehensive information value.

[0086] In this example, the information value of different subcategories in each evaluation factor is calculated to represent the degree of its promotion to the development of disasters. In the evaluation of landslide susceptibility, the information value model uses the information value and comprehensive level contributed by each evaluation factor as the standard to divide the regional landslide susceptibility. The comprehensive information corresponding to the kth evaluation factor can be obtained through formula (1);

[0087] The random forest model can evaluate the relative weights of landslide susceptibility factors, which are based on the Gini index. In the random forest classification tree, impurity is used to measure the best split, and impurity is calculated by the Gini index method. The reduction value D of the Gini index when the evaluation factor k is split at the node is calculated. Gk , D of all nodes in the forest Gk After summing up, take the average of all trees to get the importance of evaluation factor k; the relative importance of evaluation factors is measured by the percentage of their average Gini reduction value to the total average Gini reduction value of all evaluation factors. The importance of the kth evaluation factor among all evaluation factors can be obtained by formula (2);

[0088] The comprehensive information value can be obtained by formula (3), which is obtained by weighted superposition of the information value of each evaluation factor and its weight; the probability of landslide occurring in the grid area can be obtained by the comprehensive information value.

[0089] In an optional embodiment of the present invention, step 15 may include:

[0090] Step 151, statistically processing the landslide susceptibility data of the grid area to obtain landslide susceptibility prediction data.

[0091] In this example, each grid area represents a small geographical unit. The comprehensive information value of a specific grid area can be obtained through equations (1) to (3). The comprehensive information value is the landslide susceptibility data of the grid area. According to the position of each grid area, the landslide susceptibility data of each grid area is counted in turn, and the landslide susceptibility prediction data of the target area can be obtained.

[0092] A specific embodiment of the landslide disaster data processing method provided by the embodiment of the present invention is:

[0093] Step 1: Acquire remote sensing geological data of the target area within a preset target time range.

[0094] For the target area with geographic coordinates between 35°09′~35°59′N, 103°37′~104°30′E, remote sensing geological data of the past ten years were obtained. Among them, landslide hazard catalog data was used to extract landslide hazard types and location information; vector maps of administrative divisions, roads, rivers, etc. were provided and downloaded by Geospatial Data Cloud; digital elevation model data with a resolution of 12.5m was used to extract terrain and geomorphic attributes and terrain humidity index, water flow intensity index; Landsat satellite image data was used to extract vegetation information.

[0095] Step 2: Obtaining grid area data based on the remote sensing geological data.

[0096] The target area is divided into 53131004 evaluation grid units with a resolution of 12.5m×12.5m as the evaluation grid unit size.

[0097] Step 3, obtaining evaluation factor data based on the remote sensing geological data and the grid area data.

[0098] Obtaining a terrain evaluation factor, a geomorphic evaluation factor, a hydrological condition evaluation factor, and an engineering activity intensity evaluation factor based on the remote sensing geological data and the grid area data;

[0099] The terrain evaluation factor, landform evaluation factor, hydrological condition evaluation factor and engineering activity intensity evaluation factor are graded to obtain evaluation factor data.

[0100] Step 4: input the evaluation factor data into the landslide prediction model for processing to obtain grid area landslide susceptibility data.

[0101] according to

[0102]

[0103] Obtain the information contribution value of the evaluation factor data to landslide hazards;

[0104] according to

[0105]

[0106] Get the weight data of the kth evaluation factor among all evaluation factors;

[0107] according to

[0108]

[0109] Get the comprehensive information value;

[0110] According to the comprehensive information value, landslide susceptibility data is obtained.

[0111] Step 5: obtaining the landslide susceptibility prediction data of the target area according to the landslide susceptibility data of the grid area.

[0112] According to the location of each grid area, the landslide susceptibility data of each grid area is counted in turn, and the landslide susceptibility prediction data of the target area can be obtained, such as Figure 2 As shown in Table 1, Figure 2 The medium black dotted area 21 is the landslide disaster occurrence point, the light-colored area 22 is the extremely low-prone and low-prone areas for landslides, the medium-colored area 23 is the medium-prone area for landslides, the gray area 24 is the high-prone area for landslides, and the dark gray area 25 is the extremely high-prone area for landslides.

[0113] Figure 2 The data of disaster points in Table 1 are the real data of landslide disasters in the target area in recent years. It can be seen from Table 1 that the area of ​​the high-prone area predicted by this embodiment is 70.37%, the medium-prone area is 14.61%, the disaster points in the extremely high-prone area are 22.69%, and the density is 18.24, which has a high match with the real data of landslide disasters and has a high prediction accuracy.

[0114] Landslide susceptibility zoning <![CDATA[Area / km 2 > Area ratio Disaster Point Disaster Point Proportion Disaster point density Very low risk area 136.79 1.67％ 0 0.00％ 0.00％ Low risk area 415.76 5.09％ 1 0.18％ 0.24％ Medium-prone area 1193.64 14.61％ 39 7.20％ 3.27％ High risk area 5748.65 70.37％ 379 69.93％ 6.59％ Highly susceptible areas 674.16 8.25％ 123 22.69％ 18.24％

[0115] The landslide disaster data processing method proposed in the present invention reduces the influence of subjective factors on the weights of evaluation factors by determining the weights of various evaluation factors, thereby improving the accuracy and reliability of the landslide disaster prediction method and providing a more scientific basis for the prevention, control and management of landslide disasters.

[0116] like Figure 3 As shown, the embodiment of the present invention further provides a landslide disaster data processing device 30, comprising:

[0117] An acquisition module 31 is used to acquire remote sensing geological data of a target area within a preset target time range;

[0118] The processing module 32 is used to obtain grid area data according to the remote sensing geological data; obtain evaluation factor data according to the remote sensing geological data and the grid area data; input the evaluation factor data into the landslide prediction model for processing to obtain grid area landslide susceptibility data, wherein the landslide prediction model processes the evaluation factor data through the objective function to obtain the grid area landslide susceptibility data;

[0119] The generating module 33 is used to obtain the landslide susceptibility prediction data of the target area according to the landslide susceptibility data of the grid area.

[0120] Optionally, the processing module 32 is specifically used for:

[0121] The remote sensing geological data is rasterized according to a preset length to obtain raster area data.

[0122] Optionally, the processing module 32 is further specifically configured to:

[0123] Obtaining a terrain evaluation factor, a geomorphic evaluation factor, a hydrological condition evaluation factor, and an engineering activity intensity evaluation factor based on the remote sensing geological data and the grid area data;

[0124] The terrain evaluation factor, landform evaluation factor, hydrological condition evaluation factor, and engineering activity intensity evaluation factor are graded to obtain evaluation factor data.

[0125] Optionally, a terrain evaluation factor, a landform evaluation factor, a hydrological condition evaluation factor and an engineering activity intensity evaluation factor are obtained based on the remote sensing geological data and the grid area data, including:

[0126] According to the influence of the terrain data in the grid area on the development and distribution of the landslide, a terrain evaluation factor is obtained, wherein the terrain evaluation factor includes one or more of elevation, slope, slope aspect, plane curvature, profile curvature and normalized vegetation index;

[0127] Obtaining a geomorphic evaluation factor according to the remote sensing geological data and the grid area data, including: obtaining a geomorphic evaluation factor according to the influence of the geomorphic data in the grid area on the stability of the landslide, wherein the geomorphic evaluation factor includes one or more of topography, rock formation, topographic moisture and fault;

[0128] Obtaining a hydrological condition evaluation factor according to the remote sensing geological data and the grid area data, including: obtaining a hydrological condition evaluation factor according to the influence of the hydrological data in the grid area on the generation of landslides, wherein the hydrological condition evaluation factor includes one or more of annual rainfall, water flow intensity and distance from the river;

[0129] According to the remote sensing geological data and the grid area data, an engineering activity intensity evaluation factor is obtained, including: according to the influence of the engineering activity intensity data in the grid area on the generation of landslides, an engineering activity intensity evaluation factor is obtained, wherein the engineering activity intensity evaluation factor includes the distance from residential areas, the distance from roads and the distance from earthquake sources.

[0130] Optionally, the terrain evaluation factor, landform evaluation factor, hydrological condition evaluation factor, and engineering activity intensity evaluation factor are graded to obtain evaluation factor data, including:

[0131] The slope and elevation in the terrain evaluation factor are graded according to the natural break point method to obtain evaluation factor data of the slope and elevation;

[0132] Classifying the slope aspects in the terrain evaluation factor according to direction to obtain evaluation factor data of the slope aspects;

[0133] Classifying the rock groups in the geomorphic evaluation factors according to the point density of landslide hazard points in each rock group, and obtaining evaluation factor data of the rock groups;

[0134] The rainfall in the hydrological condition evaluation factor is graded according to the natural break point method to obtain the evaluation factor data of the rainfall;

[0135] Classifying the distance to the river in the hydrological condition evaluation factor according to a first preset step length to obtain evaluation factor data of the distance to the river;

[0136] Classifying the distance to the road in the engineering activity intensity evaluation factor according to a first preset step length to obtain evaluation factor data of the distance to the road;

[0137] The distance from the residential area in the engineering activity intensity evaluation factor is graded according to a second preset step size to obtain evaluation factor data of the distance from the residential area.

[0138] Optionally, the processing module 32 is further specifically configured to:

[0139] according to

[0140]

[0141] The information contribution value of the evaluation factor data to landslide disasters is obtained, where χ i is the level of the evaluation factor in the evaluation unit, I(χ i , H) is the evaluation factor χ i The amount of information contributed to landslide hazards, S is the total number of units in the study area, S i The study area contains the evaluation factor χ i The number of units, N is the total number of units containing disaster points in the study area, N i The evaluation factor χ is distributed in the landslide disaster area i The number of k The comprehensive information corresponding to the kth evaluation factor, m is the number of evaluation factors;

[0142] according to

[0143]

[0144] Get the weight data of the kth evaluation factor among all evaluation factors, where m, n, and t are the total number of evaluation factors, the number of classification trees, and the number of nodes in a single tree, respectively; D Gkhj is the Gini index reduction value of the kth evaluation factor at the jth node of the hth tree; P k is the importance of the kth evaluation factor among all evaluation factors;

[0145] according to

[0146]

[0147] Get the comprehensive information value, where y is the comprehensive information value;

[0148] According to the comprehensive information value, landslide susceptibility data is obtained.

[0149] Optionally, the generating module 33 is further specifically used for:

[0150] Statistical processing is performed on the landslide susceptibility data of the grid area to obtain landslide susceptibility prediction data.

[0151] It should be noted that the device is a device corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0152] like Figure 4 As shown, the embodiment of the present invention further provides a computing device 40, including a processor 41, a memory 42, a program or instruction stored in the memory 42 and executable on the processor 41, and when the program or instruction is executed by the processor 41, each process of the above landslide disaster data processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not described here. It should be noted that the computing device in the embodiment of the present invention includes the above-mentioned mobile electronic device and non-mobile electronic device.

[0153] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0154] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0155] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0156] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0157] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0158] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0159] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0160] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code for implementing a method or device. That is to say, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0161] The above are preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A landslide disaster data processing method, characterized in that: include: Acquire remote sensing geological data of the target area within a preset target time range; Obtaining grid area data according to the remote sensing geological data; Obtaining evaluation factor data according to the remote sensing geological data and the grid area data; Inputting the evaluation factor data into a landslide prediction model for processing to obtain grid area landslide susceptibility data, wherein the landslide prediction model processes the evaluation factor data through an objective function to obtain grid area landslide susceptibility data; The landslide susceptibility prediction data of the target area are obtained according to the landslide susceptibility data of the grid area.

2. The landslide hazard data processing method according to claim 1, characterized in that: According to the remote sensing geological data, grid area data is obtained, including: The remote sensing geological data is rasterized according to a preset length to obtain raster area data.

3. The landslide hazard data processing method according to claim 1, characterized in that: According to the remote sensing geological data and the grid area data, evaluation factor data is obtained, including: Obtaining a terrain evaluation factor, a geomorphic evaluation factor, a hydrological condition evaluation factor, and an engineering activity intensity evaluation factor based on the remote sensing geological data and the grid area data; The terrain evaluation factor, landform evaluation factor, hydrological condition evaluation factor, and engineering activity intensity evaluation factor are graded to obtain evaluation factor data.

4. The landslide hazard data processing method according to claim 3, characterized in that: According to the remote sensing geological data and the grid area data, terrain evaluation factors, landform evaluation factors, hydrological condition evaluation factors and engineering activity intensity evaluation factors are obtained, including: According to the influence of the terrain data in the grid area on the development and distribution of the landslide, a terrain evaluation factor is obtained, wherein the terrain evaluation factor includes one or more of elevation, slope, slope aspect, plane curvature, profile curvature and normalized vegetation index; Obtaining a geomorphic evaluation factor according to the remote sensing geological data and the grid area data, including: obtaining a geomorphic evaluation factor according to the influence of the geomorphic data in the grid area on the stability of the landslide, wherein the geomorphic evaluation factor includes one or more of topography, rock formation, topographic moisture and fault; Obtaining a hydrological condition evaluation factor according to the remote sensing geological data and the grid area data, including: obtaining a hydrological condition evaluation factor according to the influence of the hydrological data in the grid area on the generation of landslides, wherein the hydrological condition evaluation factor includes one or more of annual rainfall, water flow intensity and distance from the river; According to the remote sensing geological data and the grid area data, an engineering activity intensity evaluation factor is obtained, including: according to the influence of the engineering activity intensity data in the grid area on the generation of landslides, an engineering activity intensity evaluation factor is obtained, wherein the engineering activity intensity evaluation factor includes the distance from residential areas, the distance from roads and the distance from earthquake sources.

5. The landslide hazard data processing method according to claim 3, characterized in that: The terrain evaluation factor, landform evaluation factor, hydrological condition evaluation factor, and engineering activity intensity evaluation factor are graded to obtain evaluation factor data, including: The slope and elevation in the terrain evaluation factor are graded according to the natural break point method to obtain evaluation factor data of the slope and elevation; Classifying the slope aspects in the terrain evaluation factor according to direction to obtain evaluation factor data of the slope aspects; The rock groups in the geomorphic evaluation factor are classified according to the point density of landslide hazard points in each rock group to obtain evaluation factor data of the rock group; The rainfall in the hydrological condition evaluation factor is graded according to the natural break point method to obtain the evaluation factor data of the rainfall; Classifying the distance to the river in the hydrological condition evaluation factor according to a first preset step length to obtain evaluation factor data of the distance to the river; Classifying the distance to the road in the engineering activity intensity evaluation factor according to a first preset step length to obtain evaluation factor data of the distance to the road; The distance from the residential area in the engineering activity intensity evaluation factor is graded according to a second preset step size to obtain evaluation factor data of the distance from the residential area.

6. The landslide hazard data processing method according to claim 1, characterized in that: The evaluation factor data is input into the landslide prediction model for processing to obtain grid area landslide susceptibility data, including: according to The information contribution value of the evaluation factor data to landslide disasters is obtained, where χ i is the level of the evaluation factor in the evaluation unit, I(χ i , H) is the evaluation factor χ i The amount of information contributed to landslide hazards, S is the total number of units in the study area, S i The study area contains the evaluation factor χ i The number of units, N is the total number of units containing disaster points in the study area, N i The evaluation factor χ is distributed in the landslide disaster area i The number of k The comprehensive information corresponding to the kth evaluation factor, m is the number of evaluation factors; according to Get the weight data of the kth evaluation factor among all evaluation factors, where m, n, and t are the total number of evaluation factors, the number of classification trees, and the number of nodes in a single tree, respectively; D Gkhj is the Gini index reduction value of the kth evaluation factor at the jth node of the hth tree; P k is the importance of the kth evaluation factor among all evaluation factors; according to Get the comprehensive information value, where y is the comprehensive information value; According to the comprehensive information value, landslide susceptibility data is obtained.

7. The landslide hazard data processing method according to claim 1, characterized in that: According to the landslide susceptibility data of the grid area, landslide susceptibility prediction data is obtained, including: Statistical processing is performed on the landslide susceptibility data of the grid area to obtain landslide susceptibility prediction data.

8. A landslide disaster data processing device, characterized in that: include: An acquisition module is used to acquire remote sensing geological data of a target area within a preset target time range; The processing module is used to obtain grid area data according to the remote sensing geological data; obtain evaluation factor data according to the remote sensing geological data and the grid area data; input the evaluation factor data into the landslide prediction model for processing to obtain grid area landslide susceptibility data, wherein the landslide prediction model processes the evaluation factor data through the objective function to obtain the grid area landslide susceptibility data; The generation module is used to obtain the landslide susceptibility prediction data of the target area based on the landslide susceptibility data of the grid area.

9. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is performed.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images