Landslide susceptible area identification method and device and storage medium

Abstract

The embodiment of the invention provides a landslide susceptible area identification method and device and a storage medium, and the method comprises the steps: obtaining geological data and satellite remote sensing data of a preset observation area; obtaining a landslide susceptibility zoning map according to the geological data; according to the satellite remote sensing data, generating a surface deformation rate map of the unstable region; and obtaining a potential landslide area map based on the landslide susceptibility zoning map and the unstable area surface deformation rate map. Therefore, the area where the landslide disaster may occur can be identified more accurately, and meanwhile, the accuracy and reliability of disaster early warning are improved.

Description

Technical Field

[0001] This document relates to the technical field of geological disaster risk assessment, and in particular to a method, device and storage medium for identifying landslide-prone areas. Background Art

[0002] Accurate prediction of landslides can effectively protect people’s lives and property, promote stable economic development, improve emergency response efficiency, promote scientific and technological development and progress, and enhance public awareness of disaster prevention and mitigation.

[0003] Existing technologies mainly use statistical analysis based on geological, topographical, climatic and other conditions to determine the spatial probability of landslides occurring in different regions.

[0004] However, the existing technology can only roughly determine the distribution of landslides, and it is difficult to accurately predict the occurrence of specific landslide events. In addition, it requires a lot of manpower and material resources to carry out prediction, forecasting, monitoring and management of landslide disasters in large areas of high and extremely high risk areas. Summary of the invention

[0005] In view of the above scheme, the present application aims to propose a method, device and storage medium for identifying landslide-prone areas to solve at least one of the above technical problems.

[0006] In a first aspect, one or more embodiments of this specification provide a method for identifying a landslide-prone area, comprising:

[0007] Obtain geological data and satellite remote sensing data of the preset observation area;

[0008] According to the geological data, a landslide susceptibility zoning map is obtained;

[0009] generating a surface deformation rate map of an unstable region based on the satellite remote sensing data; and

[0010] Based on the landslide susceptibility zoning map and the unstable area surface deformation rate map, a potential landslide area map is obtained.

[0011] Further, based on the random forest model, the landslide susceptibility zoning map is obtained according to the geological data,

[0012] The training process of the random forest model includes:

[0013] Obtain pre-trained geological data and landslide catalog library data;

[0014] Determine a plurality of influencing factors according to the pre-trained geological data, wherein the plurality of influencing factors include aspect, slope, elevation, plane curvature, profile curvature, terrain moisture index, average annual rainfall, distance to a river, road density, normalized difference vegetation index, stratum lithology, and distance to a fault;

[0015] Determining landslide negative samples according to the pre-trained geological data and the multiple influencing factors;

[0016] Determining a positive landslide sample according to the landslide catalog database data; and

[0017] The random forest model is trained according to the landslide negative samples and the landslide positive samples.

[0018] Further, based on the Pearson correlation coefficient, the plurality of influencing factors are determined according to the pre-trained geological data,

[0019] The calculation formula of the Pearson correlation coefficient is as follows:

[0020]

[0021] Among them, r represents the Pearson correlation coefficient between each influencing factor;

[0022] n represents the total number of observations; the observations are the values ​​contained in each influencing factor;

[0023] i represents the position of the observation value or the serial number of the data;

[0024] x i represents the i-th observed value of variable x; the variable is each influencing factor;

[0025] y i represents the i-th observation value of variable y;

[0026] represents the mean value of variable x; and

[0027] Represents the mean value of the variable y.

[0028] Furthermore, the satellite remote sensing data includes ascending orbit data and descending orbit data, and

[0029] Generating a surface deformation rate map of an unstable region according to the satellite remote sensing data includes:

[0030] Obtaining an orbit raising deformation rate diagram and an orbit lowering deformation rate diagram according to the orbit raising data and the orbit lowering data;

[0031] According to the orbit raising deformation rate diagram and the orbit lowering deformation rate diagram, an orbit raising deformation rate diagram in an unstable region and an orbit lowering deformation rate diagram in an unstable region are obtained; and

[0032] Based on the unstable region orbit raising deformation rate map and the unstable region orbit lowering deformation rate map, an unstable region surface deformation rate map is generated.

[0033] Furthermore, the landslide susceptibility zoning map is divided into an extremely high susceptibility zoning map, a high susceptibility zoning map, a medium susceptibility zoning map, a low susceptibility zoning map, and an extremely low susceptibility zoning map, and

[0034] The potential landslide area map obtained based on the landslide susceptibility zoning map and the unstable area surface deformation rate map includes:

[0035] Selecting a very high susceptibility zoning map and a high susceptibility zoning map based on a preset susceptibility zoning threshold and a landslide susceptibility zoning map; and

[0036] Based on the extremely high susceptibility zoning map, the high susceptibility zoning map and the unstable area surface deformation rate map, a potential landslide area map is generated.

[0037] In a second aspect, an embodiment of the present application provides a device for identifying a landslide-prone area, comprising:

[0038] An acquisition module is used to acquire geological data and satellite remote sensing data of a preset observation area;

[0039] A first generating module is used to obtain a landslide susceptibility zoning map according to the geological data;

[0040] A second generating module is used to generate a surface deformation rate map of an unstable area according to the satellite remote sensing data; and

[0041] The third generating module is used to obtain a potential landslide area map based on the landslide susceptibility zoning map and the unstable area surface deformation rate map.

[0042] Furthermore, the first generating module is configured to:

[0043] Based on the random forest model, the landslide susceptibility zoning map is obtained according to the geological data,

[0044] The training process of the random forest model includes:

[0045] Obtain pre-trained geological data and landslide catalog library data;

[0046] Determine a plurality of influencing factors according to the pre-trained geological data, wherein the plurality of influencing factors include aspect, slope, elevation, plane curvature, profile curvature, terrain moisture index, average annual rainfall, distance to a river, road density, normalized difference vegetation index, stratum lithology, and distance to a fault;

[0047] Determining landslide negative samples according to the pre-trained geological data and the multiple influencing factors;

[0048] Determining a positive landslide sample according to the landslide catalog database data; and

[0049] The random forest model is trained according to the landslide negative samples and the landslide positive samples.

[0050] Furthermore, the first generating module is further configured to:

[0051] Based on the Pearson correlation coefficient, the plurality of influencing factors are determined according to the pre-trained geological data,

[0052] The calculation formula of the Pearson correlation coefficient is as follows:

[0053]

[0054] Among them, r represents the Pearson correlation coefficient between each influencing factor;

[0055] n represents the total number of observations; the observations are the values ​​contained in each influencing factor;

[0056] i represents the position of the observation value or the serial number of the data;

[0057] x i represents the i-th observed value of variable x; the variable is each influencing factor;

[0058] y i represents the i-th observation value of variable y;

[0059] represents the mean value of variable x; and

[0060] Represents the mean value of the variable y.

[0061] Furthermore, the second generating module is further configured to:

[0062] The satellite remote sensing data includes ascending orbit data and descending orbit data;

[0063] Obtaining an orbit raising deformation rate diagram and an orbit lowering deformation rate diagram according to the orbit raising data and the orbit lowering data;

[0064] According to the orbit raising deformation rate diagram and the orbit lowering deformation rate diagram, an orbit raising deformation rate diagram in an unstable region and an orbit lowering deformation rate diagram in an unstable region are obtained; and

[0065] Based on the unstable region orbit raising deformation rate map and the unstable region orbit lowering deformation rate map, an unstable region surface deformation rate map is generated.

[0066] In a third aspect, an embodiment of the present application provides a storage medium for storing computer-executable instructions, characterized in that when the computer-executable instructions are executed, the steps of the landslide-prone area identification method described in any one of the first aspects are implemented.

[0067] Compared with the prior art, this application can at least achieve the following technical effects:

[0068] The present application can obtain the landslide susceptibility zoning map of the observation area and the surface deformation rate map of the unstable area from different angles, so that the analysis of landslides can be more comprehensive; and then the maps obtained from different angles are combined to obtain the potential landslide area map, which can more accurately identify the areas where landslide disasters may occur, while improving the accuracy and reliability of disaster warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0070] Figure 1 A flow chart of a method for identifying landslide-prone areas provided for one or more embodiments of this specification;

[0071] Figure 2 A surface deformation rate map of an unstable area based on the fusion of ascending orbit data and descending orbit data provided in one or more embodiments of this specification;

[0072] Figure 3 An impact factor diagram provided for one or more embodiments of this specification;

[0073] Figure 4 A Pearson correlation analysis diagram provided for one or more embodiments of this specification;

[0074] Figure 5 A potential landslide area map for a landslide-prone area identification method provided in one or more embodiments of this specification;

[0075] Figure 6A schematic diagram of the structure of a device for identifying landslide-prone areas provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0076] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0077] Identifying landslide-prone areas can help nearby personnel discover potential dangers in a timely manner, take preventive measures in advance, and reduce disaster losses. However, existing technologies can only predict the probability of a certain affected body being affected by a landslide at a specific spatial location, making it difficult to predict, monitor, and control landslide disasters in large areas with high and extremely high risk.

[0078] In view of the above technical problems, this application proposes a method for identifying landslide-prone areas, such as Figure 1 As shown, the specific steps are as follows:

[0079] Step S1, obtaining geological data and satellite remote sensing data of a preset observation area.

[0080] Specifically, select the area to be observed, and then obtain the geological data of the area to be observed from platforms such as Copernicus Data Space Ecosystem, China Geological Survey Geological Cloud, 91 Satellite Map Platform, Geospatial Data Cloud, National Basic Geographic Information Center, and National Meteorological Information Center; then obtain satellite remote sensing data of the area to be observed from platforms such as ESA.

[0081] In this application, by acquiring different types of data, more comprehensive and accurate information support can be provided for the current observation area.

[0082] Step S2, obtaining a landslide susceptibility zoning map based on the geological data.

[0083] Specifically, multiple influencing factor data are screened out from the geological data, and the influencing factor data are preprocessed, such as standardization and normalization, to ensure the consistency and comparability of the data. Then, the preprocessed multiple influencing factor data are input into the trained model to predict the landslide susceptibility; using the natural breakpoint method, according to the prediction results, the area is divided into different landslide susceptibility levels, such as extremely high susceptibility area, high susceptibility area, medium susceptibility area, low susceptibility area, and extremely low susceptibility area. Then, using drawing software, the prediction results are presented in the form of a map to draw a landslide susceptibility zoning map.

[0084] In this application, multiple disaster-causing factors in landslides are combined, and the observation area is divided based on multiple factors such as geology, topography, climate, and vegetation coverage, which can more intuitively determine which areas are more prone to landslides.

[0085] Step S3, generating a surface deformation rate map of an unstable area based on the satellite remote sensing data.

[0086] Specifically, satellite remote sensing data is divided into orbit ascending data and orbit descending data. The orbit ascending data and orbit descending data are corrected respectively, including preprocessing such as radiation correction, geometric correction and phase correction, to improve data quality. Image registration is then performed to ensure that images at different time points can be accurately aligned. Interference processing is then performed on the preprocessed orbit ascending data and orbit descending data to obtain the deformation rate map of the orbit ascending and the deformation rate map of the orbit descending; the deformation rate map of the orbit ascending and the deformation rate map of the orbit descending are then processed to obtain the deformation rate map of the stable area of ​​the orbit ascending and the deformation rate map of the stable area of ​​the orbit descending respectively; based on the deformation rate map of the stable area of ​​the orbit ascending and the deformation rate map of the stable area of ​​the orbit descending, the deformation rate map of the unstable area of ​​the orbit ascending and the deformation rate map of the unstable area of ​​the orbit descending are determined; finally, the deformation rate map of the unstable area of ​​the orbit ascending and the deformation rate map of the unstable area of ​​the orbit descending are fused to obtain the surface deformation rate map of the unstable area, such as Figure 2 shown.

[0087] In this application, a surface deformation rate map of an unstable area is generated based on satellite remote sensing data, which can show the deformation of a certain area in different time periods on the surface, providing an important basis for monitoring and early warning of geological disasters such as landslides.

[0088] Step S4, obtaining a potential landslide area map based on the landslide susceptibility zoning map and the unstable area surface deformation rate map.

[0089] Specifically, according to the actual situation of landslide susceptibility, a susceptibility zoning threshold is set. According to the threshold, deformation areas with high landslide susceptibility are screened out, and then the screened landslide susceptibility zoning map and the surface deformation rate map of unstable areas are superimposed and fused to ensure the consistency of the two layers in geographic coordinates and resolution. For the superimposed layers, data matching and calibration are performed to ensure that the information on landslide susceptibility and surface deformation rate can accurately correspond. Combined with the landslide possibility provided by the landslide susceptibility zoning map and the surface deformation information provided by the surface deformation rate map of unstable areas, a comprehensive analysis of the superimposed layers is performed. Focus on those areas with both high landslide susceptibility and significant surface deformation, and then obtain a potential landslide area map.

[0090] In this application, the preset observation area is analyzed from different aspects, so that the occurrence area of ​​landslide can be predicted more accurately, thereby improving the accuracy and reliability of disaster warning.

[0091] Preferably, based on the random forest model, the landslide susceptibility zoning map is obtained according to the geological data, wherein the training process of the random forest model includes: obtaining pre-trained geological data and landslide catalog library data; determining multiple influencing factors according to the pre-trained geological data. The multiple influencing factors include slope aspect, slope, elevation, plane curvature, profile curvature, terrain moisture index, average annual rainfall, distance from river, road density, normalized difference vegetation index, stratum lithology and distance from fault; determining landslide negative samples according to the pre-trained geological data and the multiple influencing factors; determining landslide positive samples according to the landslide catalog library data; and training the random forest model according to the landslide negative samples and the landslide positive samples.

[0092] In the embodiment of the present application, the landslide distribution characteristics and disaster-causing factors in the observation area are analyzed in combination with engineering geological conditions, and the Pearson correlation coefficient is used to perform correlation analysis to determine reasonable influencing factors; all vector points in the landslide surface data are selected as training data and test data for positive landslide samples based on a landslide area ratio of about 7:3. Negative sample data of equal proportion to positive samples are selected based on the information quantity method; a random forest machine learning model is constructed to carry out landslide susceptibility evaluation and susceptibility zoning.

[0093] Specifically, the preset geological data include landslide catalog data, geological data, vegetation data, hydrological data, road data and meteorological data. Among them, the landslide catalog is mainly based on field surveys, previous studies and Google Earth images; geological data are obtained from the 1:200,000 engineering geological map of the China Geological Survey; vegetation data are obtained by using ENVI software to obtain normalized vegetation index data; hydrological data are obtained through the 91 satellite map platform; road data are obtained from the National Basic Geographic Information Center; meteorological data are obtained from the National Meteorological Information Center, as shown in Table 1.

[0094] Table 1 Geological data sources

[0095]

[0096] Firstly, based on the Pearson correlation coefficient and the pre-trained geological data, the correlation between the influencing factors is determined and the influencing factors with low correlation are selected. The influencing factors include slope, aspect, elevation, plan curvature (SoA), profile curvature (SoS), terrain wetness index (TWI), average annual rainfall, river distance, river density, normalized difference vegetation index (NDVI), lithology, and fault distance. Figure 3 As shown. If there is a strong correlation between the selected influencing factors, they may interact with each other, thus affecting the accuracy of the experimental results. For example, rainfall and groundwater level are two influencing factors that may be correlated with each other. If they are considered at the same time, it is difficult to accurately determine which factor plays a more critical role in the occurrence of landslides; when the correlation between the influencing factors is small, their impact on the landslide can be analyzed and evaluated more independently, thereby reducing experimental errors. This helps to more accurately understand the contribution of each factor to the landslide. In this application, the independence of the influencing factors determines whether the robustness and robustness performance of the trained model is superior. Variables with a strong degree of correlation are prone to overfitting, resulting in model distortion, which ultimately affects the evaluation accuracy. Estimating the covariance and standard deviation of the sample can obtain the Pearson correlation coefficient r of the sample, which ranges from -1 to 1, and the absolute value represents the strength of the correlation. |r|<0.2, very weak correlation or no correlation, 0.2<|r|<0.4, weak correlation, 0.4<|r|<0.6, moderate correlation, 0.6<|r|<0.8, strong correlation, 0.8<|r|<1.0, very strong correlation, such as Figure 4 The calculation formula is as follows:

[0097]

[0098] Among them, r represents the Pearson correlation coefficient between each influencing factor;

[0099] n represents the total number of observations; the observations are the values ​​contained in each influencing factor;

[0100] i represents the position of the observation value or the serial number of the data;

[0101] x i represents the i-th observed value of variable x; the variable is each influencing factor;

[0102] y i represents the i-th observation value of variable y;

[0103] represents the mean value of variable x;

[0104] Represents the mean value of the variable y.

[0105] Secondly, in ArcGIS 10.8, the “Project” tool or “Define Projection” tool was used to unify the coordinate systems of all geological data into the WGS-84-UTM-zone-48N projection coordinate system, and the raster layers of the influencing factors used were extracted and produced. Then, based on the information volume method, the raster values ​​were extracted and the information values ​​were calculated. The calculated information volume values ​​were input into the corresponding influencing factor raster, and the 12 influencing factor raster layers were superimposed using the raster calculator. Then, the natural breakpoint method was used to reclassify the vector data obtained by superposition into five areas: extremely high susceptibility area, high susceptibility area, medium susceptibility area, low susceptibility area, and extremely low susceptibility area. As shown in Table 2, negative landslide samples were selected in the low susceptibility area and the extremely low susceptibility area to prepare for the subsequent input model data, and the positive landslide samples were extracted through the collected landslide catalog library data.

[0106] Table 2 Results of landslide susceptibility zoning

[0107]

[0108]

[0109] Finally, the landslide susceptibility was evaluated by selecting positive samples of landslides and negative samples of landslides using the information method. The training set and test set divided by positive and negative samples were read in the RF model. The code in the model would train the random forest classifier, and use the trained random forest classifier to predict the probability that each sample in the test set belongs to the positive class. Then the ROC curve was calculated and drawn. The accuracy of the model was verified by the ROC curve and AUC value. The grid search method was used to optimize the parameters of the random classifier to obtain the optimal random forest model for predicting all data sets in the study area. The spatial probability of landslides occurring at all grid points in the study area was obtained, and then the landslide susceptibility zoning map was drawn in ArcGIS10.8 software according to the spatial probability, which was divided into five categories: extremely high susceptibility area, high susceptibility area, medium susceptibility area, low susceptibility area, and extremely low susceptibility area.

[0110] Preferably, the satellite remote sensing data includes orbit ascending data and orbit descending data, and an orbit ascending deformation rate map and an orbit descending deformation rate map are obtained based on the orbit ascending data and the orbit descending data; an orbit ascending deformation rate map and an orbit descending deformation rate map of an unstable region are obtained based on the orbit ascending deformation rate map and the orbit descending deformation rate map; and a surface deformation rate map of an unstable region is generated based on the orbit ascending deformation rate map and the orbit descending deformation rate map of an unstable region.

[0111] In an embodiment of the present application, the satellite remote sensing data is preprocessed by parameter setting, image registration, etc. to ensure the consistency of phase information; the registered SAR image is then complex multiplied to generate an interference map containing the phase difference information between the two imagings; the phase winding phenomenon is unwrapped to restore the continuity of the phase, eliminate the jump phenomenon in the interference map, and restore the true phase relationship between pixels; the unwrapped phase map is orbitally refined and re-flattened to obtain an ascending orbit deformation rate map and a descending orbit deformation rate map; then, the flat ground effect is removed according to the terrain model (DEM) or orbit data, and the elevation is reconstructed and geocoded to obtain an ascending orbit deformation rate map in an unstable area and an descending orbit deformation rate map in an unstable area; the geometric distortion area caused by atmospheric disturbances, surface deformation or other factors is identified and removed, and the data blank area left after the distortion is removed can be filled by an interpolation method (such as neighboring point interpolation, bilinear interpolation, etc.). The displacement rate information of the ascending and descending orbits of the SAR images were extracted separately, and the displacement rate information of the ascending and descending orbits were merged using a joint algorithm to obtain a more accurate and complete surface deformation rate map of the unstable area.

[0112] Specifically, based on the SBAS-InSAR technology, interferometric image pairs with smaller temporal and spatial baselines are selected from satellite remote sensing data for interferometric multi-view processing to obtain M differential interferograms, where M satisfies the following conditions:

[0113]

[0114] Among them, N+1 represents SAR image;

[0115] M represents M differential interference patterns;

[0116] N represents the number of SAR images.

[0117] Then, based on the coherence threshold, high coherence points are selected and phase unwrapping is performed. a ,t b (t b >t a ) The i-th interference pattern generated by the image at different times, removing the flat ground and terrain phase, the differential interference phase at the azimuth coordinate x and the distance coordinate r pixel is:

[0118]

[0119] Among them, x represents the azimuth coordinate;

[0120] r represents the distance coordinate;

[0121] i represents the number of times the interference pattern is generated;

[0122] t a ,t b Indicates different moments of the image;

[0123] d represents the cumulative deformation in the radar line of sight direction;

[0124] λ is the operating wavelength of the radar;

[0125] d(t a / b ,x,r) is the cumulative deformation in the radar line of sight direction;

[0126] is the phase change value caused by the deformation d.

[0127] The interferometric phase is expressed as the product of the average phase rate between the two acquisition times and the time period, as shown in the following formula:

[0128]

[0129] Among them, v i represents the average phase rate.

[0130] The interference phase of the i-th differential interference pattern can be expressed as:

[0131]

[0132] Where t represents the observation time;

[0133] t a,i ,tb,i Indicates the start and end points of a time series;

[0134] t i -t i-1 is the time difference between observations i and i-1;

[0135] represents the total phase change over time;

[0136] Then convert the above formula into matrix form:

[0137]

[0138] Where A represents an M×N coefficient matrix;

[0139] Represents the matrix composed of the phases of M differential interferograms;

[0140] The singular value decomposition and least squares method are then used to calculate the cumulative deformation value at the time of image acquisition, and filtering processing in the space and time domains is used to remove the atmospheric influence. Finally, the deformation results of the orbit ascending deformation rate map and the orbit descending deformation rate map are obtained.

[0141] In InSAR data processing, accurate registration of primary and secondary images can ensure the consistency of the same ground objects in the image, which mainly includes: determining control points, establishing geometric deformation models, resampling and outputting registered images. After image registration, DEM is used to remove terrain phase, generate differential interferograms, eliminate or reduce noise, phase unwrapping, track refinement and re-flattening, deformation inversion and geocoding. Among them, phase unwrapping is the most critical step in InSAR data processing, which refers to the process of restoring the unwrapped phase from the entangled phase. Track refinement and re-flattening are to select an appropriate number of control points, remove the residual constant phase and the phase ramp that still exists after unwrapping, improve the quality and accuracy of the interferogram, and obtain accurate surface deformation information.

[0142] Then the deformation results of the ascending deformation rate map and the descending deformation rate map were geocoded, encoded from the SAR coordinate system to the geographic coordinate system, and the deformation information in the radar line of sight was generated. Based on this, the subsequent data analysis was completed in GIS. According to the previous study on the InSAR deformation rate of landslides in the same reservoir area, the terrain is in a stable state under the surface deformation rate of -10 to 10 mm / yr, and the number of coherent points in the stable state is 555781, accounting for 79.04% of the total number of coherent points in the study area. The surface deformation rate of -10 to 10 mm / yr was set as the InSAR threshold of the stable area; according to the InSAR threshold, the ascending deformation rate map and the descending deformation rate map, the ascending deformation rate map of the unstable area and the descending deformation rate map of the unstable area were determined, and they were fused to obtain the surface deformation rate map of the unstable area.

[0143] Furthermore, the landslide susceptibility zoning map is divided into an extremely high susceptibility zoning map, a high susceptibility zoning map, a medium susceptibility zoning map, a low susceptibility zoning map, and an extremely low susceptibility zoning map; and the extremely high susceptibility zoning map and the high susceptibility zoning map are selected based on the preset susceptibility zoning threshold and the landslide susceptibility zoning map; and a potential landslide area map is generated based on the extremely high susceptibility zoning map, the high susceptibility zoning map, and the unstable area surface deformation rate map.

[0144] Specifically, high and extremely high prone areas are selected as susceptibility zoning thresholds, and the extremely high prone zoning map and the high prone zoning map are obtained using the susceptibility zoning thresholds; the extremely high prone zoning map, the high prone zoning map and the unstable area surface deformation rate map are fused, and then eliminated, smoothed, and error values ​​are removed to obtain a detailed potential landslide area map, such as Figure 5 shown.

[0145] In this application, the experiment proves that the optimized potential landslide area is obtained by integrating the dual-track InSAR surface deformation rate threshold and the landslide susceptibility zoning threshold. The integrated potential landslide area accounts for 3.56% of the entire study area. Compared with the susceptibility evaluation based on the information volume method, the area of ​​medium to extremely high susceptibility areas is selected, accounting for 29.92% of the entire study area. The optimized fine potential landslide area is more conducive to displaying key sliding areas and effectively improving landslide investigation and monitoring and control.

[0146] The present application embodiment provides a device for identifying landslide-prone areas, such as Figure 6 As shown, including:

[0147] An acquisition module 101 is used to acquire geological data and satellite remote sensing data of a preset observation area;

[0148] A first generating module 102 is used to obtain a landslide susceptibility zoning map according to the geological data;

[0149] A second generating module 103 is used to generate a surface deformation rate map of an unstable region according to the satellite remote sensing data; and

[0150] The third generating module 104 is used to obtain a potential landslide area map based on the landslide susceptibility zoning map and the unstable area surface deformation rate map.

[0151] Furthermore, the first generation module is configured to:

[0152] Based on the random forest model, the landslide susceptibility zoning map is obtained according to the geological data,

[0153] The training process of the random forest model includes:

[0154] Obtain pre-trained geological data and landslide catalog library data;

[0155] Determine a plurality of influencing factors according to the pre-trained geological data, wherein the plurality of influencing factors include aspect, slope, elevation, plane curvature, profile curvature, terrain moisture index, average annual rainfall, distance to a river, road density, normalized difference vegetation index, stratum lithology, and distance to a fault;

[0156] Determining landslide negative samples according to the pre-trained geological data and the multiple influencing factors;

[0157] Determining a positive landslide sample according to the landslide catalog database data; and

[0158] The random forest model is trained according to the landslide negative samples and the landslide positive samples.

[0159] Furthermore, the first generation module is further configured to:

[0160] Based on the Pearson correlation coefficient, the plurality of influencing factors are determined according to the pre-trained geological data,

[0161] The calculation formula of the Pearson correlation coefficient is as follows:

[0162]

[0163] Among them, r represents the Pearson correlation coefficient between each influencing factor;

[0164] n represents the total number of observations; the observations are the values ​​contained in each influencing factor;

[0165] i represents the position of the observation value or the serial number of the data;

[0166] x i represents the i-th observed value of variable x; the variable is each influencing factor;

[0167] y i represents the i-th observation value of variable y;

[0168] represents the mean value of variable x; and

[0169] Represents the mean value of the variable y.

[0170] Furthermore, the second generation module is further configured to:

[0171] The satellite remote sensing data includes ascending orbit data and descending orbit data;

[0172] Obtaining an orbit raising deformation rate diagram and an orbit lowering deformation rate diagram according to the orbit raising data and the orbit lowering data;

[0173] According to the orbit raising deformation rate diagram and the orbit lowering deformation rate diagram, an orbit raising deformation rate diagram in an unstable region and an orbit lowering deformation rate diagram in an unstable region are obtained; and

[0174] Based on the unstable region orbit raising deformation rate map and the unstable region orbit lowering deformation rate map, an unstable region surface deformation rate map is generated.

[0175] An embodiment of the present application provides a storage medium for storing computer-executable instructions, characterized in that the computer-executable instructions, when executed, implement the steps of the landslide-prone area identification method described in any one of the above embodiments.

[0176] It should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention. The embodiments of the storage medium in this specification and the embodiments of the service provision method based on blockchain in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding service provision method based on blockchain, and the repetitions will not be repeated.

[0177] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0178] In the 1930s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0179] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0180] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0181] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0182] It should be understood by those skilled in the art that one or more embodiments of this specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0183] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0184] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0185] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0186] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0187] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0188] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0189] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0190] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0191] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0192] The above description is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document should be included in the scope of the claims of this document.

Claims

1. A method for identifying landslide-prone areas, characterized in that include: Obtain geological data and satellite remote sensing data of the preset observation area; According to the geological data, a landslide susceptibility zoning map is obtained; generating a surface deformation rate map of an unstable region based on the satellite remote sensing data; as well as Based on the landslide susceptibility zoning map and the unstable area surface deformation rate map, a potential landslide area map is obtained.

2. The method according to claim 1, characterized in that Based on the random forest model, the landslide susceptibility zoning map is obtained according to the geological data, The training process of the random forest model includes: Obtain pre-trained geological data and landslide catalog library data; Determine a plurality of influencing factors according to the pre-trained geological data, wherein the plurality of influencing factors include aspect, slope, elevation, plane curvature, profile curvature, terrain moisture index, average annual rainfall, distance to a river, road density, normalized difference vegetation index, stratum lithology, and distance to a fault; Determining landslide negative samples according to the pre-trained geological data and the multiple influencing factors; Determining a positive landslide sample according to the landslide catalog database data; and The random forest model is trained according to the landslide negative samples and the landslide positive samples.

3. The method according to claim 2, characterized in that Based on the Pearson correlation coefficient, the plurality of influencing factors are determined according to the pre-trained geological data, The calculation formula of the Pearson correlation coefficient is as follows: Among them, r represents the Pearson correlation coefficient between each influencing factor; n represents the total number of observations; the observations are the values ​​contained in each influencing factor; i represents the position of the observation value or the serial number of the data; x i represents the i-th observed value of variable x; the variable is each influencing factor; y i represents the i-th observation value of variable y; represents the mean value of variable x; and Represents the mean value of the variable y.

4. The method according to claim 1, characterized in that: The satellite remote sensing data includes ascending orbit data and descending orbit data, and Generating a surface deformation rate map of an unstable region according to the satellite remote sensing data includes: Obtaining an orbit raising deformation rate diagram and an orbit lowering deformation rate diagram according to the orbit raising data and the orbit lowering data; According to the orbit raising deformation rate diagram and the orbit lowering deformation rate diagram, an orbit raising deformation rate diagram in an unstable region and an orbit lowering deformation rate diagram in an unstable region are obtained; and Based on the unstable region orbit raising deformation rate map and the unstable region orbit lowering deformation rate map, an unstable region surface deformation rate map is generated.

5. The method according to claim 1, characterized in that The landslide susceptibility zoning map is divided into an extremely high susceptibility zoning map, a high susceptibility zoning map, a medium susceptibility zoning map, a low susceptibility zoning map, and an extremely low susceptibility zoning map, and The potential landslide area map obtained based on the landslide susceptibility zoning map and the unstable area surface deformation rate map includes: Selecting a very high susceptibility zoning map and a high susceptibility zoning map based on a preset susceptibility zoning threshold and a landslide susceptibility zoning map; and Based on the extremely high susceptibility zoning map, the high susceptibility zoning map and the unstable area surface deformation rate map, a potential landslide area map is generated.

6. A device for identifying landslide-prone areas, characterized in that include: An acquisition module is used to acquire geological data and satellite remote sensing data of a preset observation area; A first generating module is used to obtain a landslide susceptibility zoning map according to the geological data; A second generating module is used to generate a surface deformation rate map of an unstable area according to the satellite remote sensing data; as well as The third generating module is used to obtain a potential landslide area map based on the landslide susceptibility zoning map and the unstable area surface deformation rate map.

7. The device according to claim 6, characterized in that The first generation module is configured to: Based on the random forest model, the landslide susceptibility zoning map is obtained according to the geological data, The training process of the random forest model includes: Obtain pre-trained geological data and landslide catalog library data; Determine a plurality of influencing factors according to the pre-trained geological data, wherein the plurality of influencing factors include aspect, slope, elevation, plane curvature, profile curvature, terrain moisture index, average annual rainfall, distance to a river, road density, normalized difference vegetation index, stratum lithology, and distance to a fault; Determining landslide negative samples according to the pre-trained geological data and the multiple influencing factors; Determining a positive landslide sample according to the landslide catalog database data; and The random forest model is trained according to the landslide negative samples and the landslide positive samples.

8. The device according to claim 6, characterized in that The first generation module is further configured to: Based on the Pearson correlation coefficient, the plurality of influencing factors are determined according to the pre-trained geological data, The calculation formula of the Pearson correlation coefficient is as follows: Among them, r represents the Pearson correlation coefficient between each influencing factor; n represents the total number of observations; the observations are the values ​​contained in each influencing factor; i represents the position of the observation value or the serial number of the data; x i represents the i-th observed value of variable x; the variable is each influencing factor; y i represents the i-th observation value of variable y; represents the mean value of variable x; and Represents the mean value of the variable y.

9. The device according to claim 6, characterized in that The second generation module is further configured to: The satellite remote sensing data includes ascending orbit data and descending orbit data; Obtaining an orbit raising deformation rate diagram and an orbit lowering deformation rate diagram according to the orbit raising data and the orbit lowering data; According to the orbit raising deformation rate diagram and the orbit lowering deformation rate diagram, the orbit raising deformation rate diagram in the unstable region and the orbit lowering deformation rate diagram in the unstable region are obtained; as well as Based on the unstable region orbit raising deformation rate map and the unstable region orbit lowering deformation rate map, an unstable region surface deformation rate map is generated.

10. A storage medium for storing computer executable instructions, characterized in that: When the computer executable instructions are executed, the steps of the method for identifying landslide-prone areas according to any one of claims 1 to 5 are implemented.

Images