Gyon-type reservoir area landslide identification method, device and equipment and storage medium

Abstract

The invention relates to the technical field of water conservancy disaster monitoring, in particular to a canyon type reservoir area landslide identification method, device and equipment and a storage medium, and the method comprises the steps: obtaining radar data and landform of a canyon type reservoir area; determining a target landslide deformation point of the canyon type reservoir area according to the radar data and the landform, and calculating the deformation rate of the target landslide deformation point; and generating a spatial aggregation relationship of the target landslide deformation points based on the deformation rate, and identifying a landslide area in the canyon type reservoir area based on the deformation rate and the spatial aggregation relationship. Therefore, the problems of low identification accuracy of the landslide area and the like in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the technical field of water disaster monitoring, and in particular to a method, device, equipment and storage medium for identifying landslides in a canyon-type reservoir area. Background Art

[0002] Landslide refers to the phenomenon that a large amount of rock, debris or soil moves down a slope. There are many types of geological disasters in my country, and landslide is one of the most destructive disasters. The main causes of its occurrence include rainfall, earthquakes, human activities, landscape changes, and natural processes of eroding slopes. However, most reservoirs are located in mountainous canyon areas, with complex geological structures, undulating terrain, gullies, and many steep slopes. Landslide disasters frequently occur along the reservoir area, causing many social and economic losses and damaging the ecological environment. Therefore, it is of great significance to identify potential landslide hazards in water conservancy project areas and conduct landslide susceptibility assessments in project areas on this basis, which is of great significance to the planning and construction of regional water conservancy projects and the prevention of geological disasters in reservoir areas. It is also the basis and important component of reservoir dam safety evaluation.

[0003] To mitigate and avoid the impact of landslide disasters, the key is to accurately identify and discover potential landslides and deal with them in advance, thereby reducing the probability of landslides. Traditional landslide monitoring mainly monitors landslide movement through GPS, total stations and displacement meters, but it has the disadvantages of large investment and small monitoring range.

[0004] Synthetic aperture radar interferometry technology has attracted much attention due to its advantages such as all-weather, all-day, and large-scale surface deformation monitoring. It has become a new means of identifying geological disaster risks and monitoring deformation such as landslides. Among them, in D-InSAR technology, SAR images of different time periods have low correlation and decoherence phenomena; PS-InSAR technology uses a scene image as the common main image, and will produce decoherence for image pairs with too large interference time distance. Therefore, it is not suitable for deformation monitoring with a large time span, which leads to low accuracy in identifying landslide areas. Summary of the invention

[0005] The present application provides a method, device, equipment and storage medium for identifying landslides in a canyon-type reservoir area, so as to solve the problem that the existing technology has low accuracy in identifying landslide areas.

[0006] The first aspect of the present application provides a method for identifying landslides in a canyon-type reservoir area, comprising the following steps: acquiring radar data and topography of the canyon-type reservoir area; determining target landslide deformation points in the canyon-type reservoir area based on the radar data and topography, and calculating the deformation rate of the target landslide deformation points; generating a spatial clustering relationship of the target landslide deformation points based on the deformation rate, and identifying the landslide area in the canyon-type reservoir area based on the deformation rate and the spatial clustering relationship.

[0007] Optionally, after identifying the landslide area in the canyon-type reservoir area based on the deformation rate and spatial aggregation relationship, it also includes: evaluating the landslide susceptibility level of the landslide area; and issuing early warnings or reminders based on the landslide susceptibility level.

[0008] Optionally, calculating the deformation rate of the target landslide deformation point includes: obtaining the deformation rate in the line of sight corresponding to the target deformation point; and converting the deformation rate in the line of sight into a deformation rate perpendicular to the ground based on the geometric relationship of the radar and the topography.

[0009] Optionally, target landslide deformation points in the canyon-type reservoir area are determined based on radar data and topography, including: processing radar data to obtain multiple landslide deformation points and corresponding deformation rates in the canyon-type reservoir area; screening multiple landslide deformation points based on topography and deformation rate to obtain target landslide deformation points in the canyon-type reservoir area.

[0010] Optionally, generating the spatial clustering relationship of the target landslide deformation points based on the deformation rate includes: calculating the spatial distribution pattern of the target landslide deformation points based on the deformation rate; and generating the spatial clustering relationship of the target landslide deformation points based on the spatial distribution pattern.

[0011] Optionally, evaluating the landslide susceptibility level of the landslide area includes: obtaining at least one landslide influencing factor of the landslide area; calculating the normalized information value and weight of each landslide influencing factor, and evaluating the landslide susceptibility level of the landslide area based on the normalized information value and weight.

[0012] Optionally, the normalized information value and weight of each landslide impact factor are calculated, including: grading each landslide impact factor, and calculating the information value of each level of each landslide impact factor using an information value model; unifying the information values ​​of each level of each landslide impact factor to obtain a normalized information value; taking the landslide area and the graded characteristics of each landslide impact factor as samples; and classifying the samples into landslide and non-landslide to obtain the weight of each landslide impact factor.

[0013] The second aspect of the present application provides a device for identifying landslides in a canyon-type reservoir area, including: an acquisition module for acquiring radar data and topography of the canyon-type reservoir area; a determination module for determining target landslide deformation points in the canyon-type reservoir area based on the radar data and topography, and calculating the deformation rate of the target landslide deformation points; an identification module for generating spatial clustering relationships of target landslide deformation points based on the deformation rate, and identifying landslide areas in the canyon-type reservoir area based on the deformation rate and the spatial clustering relationship.

[0014] Optionally, it also includes: an evaluation module for evaluating the landslide susceptibility level of the landslide area after identifying the landslide area in the canyon-type reservoir area based on the deformation rate and spatial aggregation relationship; and issuing early warnings or reminders based on the landslide susceptibility level.

[0015] Optionally, the determination module is further used to: obtain the deformation rate in the line of sight corresponding to the target deformation point; and convert the deformation rate in the line of sight into a deformation rate perpendicular to the ground based on the geometric relationship of the radar and the terrain.

[0016] Optionally, the determination module is further used to: process radar data to obtain multiple landslide deformation points and corresponding deformation rates in the canyon-type reservoir area; screen multiple landslide deformation points based on topography and deformation rate to obtain target landslide deformation points in the canyon-type reservoir area.

[0017] Optionally, the identification module is further used to: calculate the spatial distribution pattern of the target landslide deformation points based on the deformation rate; and generate the spatial clustering relationship of the target landslide deformation points based on the spatial distribution pattern.

[0018] Optionally, the evaluation module is further used to: obtain at least one landslide impact factor of the landslide area; calculate the normalized information value and weight of each landslide impact factor, and evaluate the landslide susceptibility level of the landslide area based on the normalized information value and weight.

[0019] Optionally, the evaluation module is further used to: classify each landslide impact factor into grades, and calculate the information value of each grade of each landslide impact factor using an information value model; unify the information values ​​of each grade of each landslide impact factor to obtain a normalized information value; use the landslide area and the graded characteristics of each landslide impact factor as samples; and classify the samples into landslide and non-landslide to obtain the weight of each landslide impact factor.

[0020] The third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to execute the method for identifying landslides in a canyon-type reservoir area as described in the above embodiment.

[0021] The fourth aspect of the present application provides a computer-readable storage medium having a computer program or instructions stored thereon, and the computer program or instructions are executed by a processor to execute the method for identifying landslides in a canyon-type reservoir area as described in the above embodiment.

[0022] Therefore, this application has at least the following beneficial effects:

[0023] The embodiment of the present application can determine the target deformation point of the canyon-type reservoir area according to the radar data and topography of the canyon-type reservoir area, and calculate the deformation rate of the target landslide deformation point, and then generate the spatial clustering relationship of the target landslide deformation point based on the deformation rate, accurately identify the landslide area in the canyon-type reservoir area based on the deformation rate and the spatial clustering relationship, improve the accuracy of landslide area identification, and provide a basis for subsequent landslide disaster warning. Therefore, the technical problem of low accuracy in landslide area identification in the prior art is solved.

[0024] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0026] Figure 1 A flow chart of a method for identifying landslides in a canyon-type reservoir area according to an embodiment of the present application;

[0027] Figure 2 A flow chart of landslide identification and susceptibility assessment provided according to an embodiment of the present application;

[0028] Figure 3 This is an example diagram of a device for identifying landslides in a canyon-type reservoir area according to an embodiment of the present application;

[0029] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0031] Landslide susceptibility refers to a quantitative or qualitative assessment of the classification, volume (or area) and spatial distribution of landslides that exist or may occur in a certain area.

[0032] At present, the methods for mapping the susceptibility of landslide disasters at home and abroad are mainly divided into three categories: empirical models, statistical analysis models and machine learning models. The empirical model refers to the evaluation of the susceptibility of landslides in a region based on the empirical knowledge of experts and combined with specific factors, such as expert knowledge-based methods and hierarchical analysis methods. The statistical model analyzes the relationship between landslides and influencing factors from a quantitative perspective. Commonly used models include information value models, frequency ratio models, and evidence weight methods. The relationship between landslides and influencing factors is relatively complex. The use of machine learning models can well explain the nonlinear relationship and has been widely used in landslide susceptibility evaluation. In machine learning models, random forests and gradient boosting machines often obtain more effective landslide susceptibility evaluation results. However, due to the complex mechanism of landslide occurrence, a single model is often difficult to represent the landslide susceptibility status of a region. Previous studies on landslide susceptibility often use the collected historical landslide lists as a reference, which may affect the evaluation effect of susceptibility due to incomplete landslide data.

[0033] To this end, the present application provides a method for identifying landslides in canyon-type reservoir areas. In the method, the target deformation points of the canyon-type reservoir area can be determined based on the radar data and topography of the canyon-type reservoir area, and the deformation rate of the target landslide deformation point can be calculated. Then, the spatial clustering relationship of the target landslide deformation point can be generated based on the deformation rate. The landslide area in the canyon-type reservoir area can be accurately identified based on the deformation rate and the spatial clustering relationship, thereby improving the accuracy of landslide area identification. In addition, the method can provide a basis for subsequent landslide disaster warning based on the assessment of the susceptibility level of the landslide area.

[0034] Specifically, Figure 1 A schematic flow chart of a method for identifying landslides in a canyon-type reservoir area provided in an embodiment of the present application.

[0035] like Figure 1 As shown, the landslide identification method in the canyon-type reservoir area includes the following steps:

[0036] In step S101, radar data and topography of a canyon-type reservoir area are obtained.

[0037] Among them, radar data can be obtained through satellite or ground radar systems, such as the long time series data of the C-band synthetic aperture radar SAR using Sentinel 1; topography and landforms can be obtained through the geographic information system GIS, such as hillsides, hills, woodlands, etc.

[0038] It is understandable that the embodiments of the present application can obtain radar data and topography of a canyon-type reservoir area to facilitate subsequent landslide identification.

[0039] In step S102, the target landslide deformation point in the canyon-type reservoir area is determined according to radar data and topography, and the deformation rate of the target landslide deformation point is calculated.

[0040] Among them, the target landslide deformation point is a deformation point with obvious deformation characteristics.

[0041] It is understandable that the embodiments of the present application can determine the target landslide deformation point in the canyon-type reservoir area based on radar data and topographic data, and calculate the deformation rate of the target landslide deformation point to facilitate subsequent identification of the landslide area.

[0042] In an embodiment of the present application, target landslide deformation points in a canyon-type reservoir area are determined based on radar data and topography, including: processing radar data to obtain multiple landslide deformation points and corresponding deformation rates in the canyon-type reservoir area; screening multiple landslide deformation points based on topography and deformation rate to obtain target landslide deformation points in the canyon-type reservoir area.

[0043] Among them, SBAS-InSAR can be used to process radar data.

[0044] It can be understood that the embodiments of the present application can obtain multiple landslide deformation points and corresponding deformation rates in the canyon-type reservoir area based on processing radar data, and then screen multiple landslide deformation points based on topography and deformation rate, remove unreliable deformation points, and obtain target landslide deformation points in the canyon-type reservoir area.

[0045] For example, when radar data is processed by SBAS-InSAR, a digital elevation model is used to eliminate the influence of terrain phase, and POD precise orbit data is used for orbit correction to improve the accuracy of deformation monitoring. The deformation results are converted into vector point format, and the deformation points distributed in woodlands and rivers are eliminated to eliminate the error influence caused by low accuracy, so as to obtain the target deformation points. In the process of processing radar data, the RI index can be used to perform visualization analysis on the radar data. For areas with geometric distortion caused by the visibility of SAR data, the RI index is used for quantitative evaluation to eliminate deformation points in radar image perspective contraction, overlap and shadow areas, and enhance the reliability of deformation point data.

[0046] In an embodiment of the present application, the deformation rate of the target landslide deformation point is calculated, including obtaining the deformation rate in the line of sight corresponding to the target deformation point; and converting the deformation rate in the line of sight into a deformation rate perpendicular to the ground based on the geometric relationship of the radar and the topography.

[0047] Among them, the deformation rate in the line of sight direction is the deformation rate in the radar direction.

[0048] It can be understood that the embodiments of the present application can obtain the deformation rate in the line of sight corresponding to the target deformation point through the processed radar data, and convert the deformation rate in the line of sight of the deformation vector point into a deformation rate perpendicular to the ground based on the geometric relationship of the radar and the topography, so as to more accurately describe the actual deformation situation of the landslide deformation point and improve the reliability of the landslide deformation point.

[0049] In step S103, a spatial clustering relationship of target landslide deformation points is generated based on the deformation rate, and a landslide area in a canyon-type reservoir area is identified based on the deformation rate and the spatial clustering relationship.

[0050] It can be understood that the embodiments of the present application can generate the spatial clustering relationship of the target landslide deformation points based on the deformation rate, and identify the landslide area in the canyon-type reservoir area according to the deformation rate and the spatial clustering relationship. For example, the area with a large deformation rate and a high spatial clustering degree is regarded as the landslide area, wherein the spatial clustering relationship can reveal the spatial distribution law of landslide activities, and the landslide area identification is not limited by the landslide historical list data.

[0051] In an embodiment of the present application, generating a spatial clustering relationship of target landslide deformation points based on deformation rate includes: calculating a spatial distribution pattern of target landslide deformation points based on deformation rate; and generating a spatial clustering relationship of target landslide deformation points based on the spatial distribution pattern.

[0052] It is understandable that the embodiment of the present application can calculate the spatial distribution pattern of the target landslide deformation points based on the deformation rate, and then generate the spatial clustering relationship of the target landslide deformation points based on the spatial distribution pattern, as follows:

[0053] Generate a spatial distribution map of the deformation rate to visualize the distribution of deformation points; use a spatial clustering algorithm (such as DBSCAN, K-means, etc.) to perform cluster analysis on the deformation rate data to identify groups of deformation points with similar deformation rates and adjacent in space; calculate the density of deformation points around each deformation point to reflect the degree of spatial aggregation of the deformation points.

[0054] In an embodiment of the present application, after identifying the landslide area in the canyon-type reservoir area based on the deformation rate and spatial aggregation relationship, it also includes: evaluating the landslide susceptibility level of the landslide area; and issuing early warnings or reminders based on the landslide susceptibility level.

[0055] Among them, the landslide susceptibility level can be set in advance according to the specific situation. For example, it can be set to five categories, "very low", "low", "medium", "high" and "very high".

[0056] It can be understood that the embodiments of the present application can evaluate the landslide susceptibility level after identifying the landslide area, and issue early warnings or reminders based on the landslide susceptibility level, which can provide an important basis for disaster management and help decision makers take appropriate preventive measures.

[0057] In an embodiment of the present application, evaluating the landslide susceptibility level of a landslide area includes: obtaining at least one landslide influencing factor of the landslide area; calculating the normalized information value and weight of each landslide influencing factor, and evaluating the landslide susceptibility level of the landslide area based on the normalized information value and weight.

[0058] Among them, landslide influencing factors may include elevation, slope, aspect, surface undulation, NDVI, NDWI, distance to water bodies, and distance to faults.

[0059] It can be understood that the embodiments of the present application can calculate the normalized information value and weight of each landslide influencing factor in the landslide area, and evaluate the landslide susceptibility level of the landslide area based on the normalized information value and weight, comprehensively considering the influence of multiple landslide influencing factors on landslide susceptibility, so as to achieve a more comprehensive assessment of the landslide susceptibility level.

[0060] In an embodiment of the present application, the normalized information value and weight of each landslide impact factor are calculated, including: grading each landslide impact factor, and calculating the information value of each level of each landslide impact factor using an information value model; unifying the information values ​​of each level of each landslide impact factor to obtain a normalized information value; taking the landslide area and the graded characteristics of each landslide impact factor as samples; and classifying the samples into landslide and non-landslide to obtain the weight of each landslide impact factor.

[0061] Among them, normalization processing can be performed based on the inverse tangent function; binary classification can be achieved through methods such as random forest and extreme gradient boosting.

[0062] It can be understood that the embodiments of the present application can classify each landslide influencing factor, and use the information value model to calculate the information value of each level, unify the information value of each level to obtain the normalized information value, take the landslide area and the grading characteristics of each landslide influencing factor as samples, classify the samples into landslide and non-landslide, and obtain the weight of each landslide influencing factor, thereby improving the scientificity and accuracy of the evaluation.

[0063] Specifically, the landslide identification method in the canyon-type reservoir area of ​​the embodiment of the present application is mainly divided into two parts: one is the landslide area identification, and the other is the landslide susceptibility evaluation. Reliable landslide deformation points are screened out according to radar data and topographic characteristics, and their effective landslide deformation rates are calculated. The landslide area is identified by using the spatial clustering relationship of the deformation points and their deformation rates. The identified landslide areas are used as a list, and a new landslide susceptibility evaluation model is proposed, that is, the information value model is improved using the inverse tangent function, and is coupled with the random forest and extreme gradient boosting methods respectively to complete the landslide susceptibility mapping and evaluation of the target reservoir area, revealing the characteristics of landslide occurrence in the reservoir area and the contribution of different geographical factors, and providing a reference for landslide risk warning and management in the reservoir area. Figure 2 As shown, the following steps are included:

[0064] Step S1: Obtain reliable deformation points in the target area. In order to obtain reliable landslide deformation points, the C-band synthetic aperture radar (SAR) long time series data of Sentinel 1 is used for SBAS-InSAR processing, and deformation points are screened according to factors such as terrain and surface cover, and the effective landslide deformation rate is calculated to further obtain reliable landslide deformation rate points. This part includes three parts: SBAS-InSAR processing, visibility analysis based on RI index, and landslide point screening.

[0065] Step S1.1: SBAS-InSAR processing and result optimization. According to the landslide monitoring requirements, the Sentinel-1 image data within the monitoring time range of the target area is used for SBAS-InSAR processing. During the processing, the digital elevation model is used to eliminate the influence of the terrain phase, and the POD precise orbit data is used for orbit correction to improve the accuracy of deformation monitoring. The obtained deformation results are converted into vector point format, and the deformation points distributed on the woodland and rivers are eliminated to eliminate the error caused by their low accuracy.

[0066] Step S1.2: Visibility analysis based on RI index: For areas with geometric distortion caused by the visibility of SAR data, the RI index is used for quantitative evaluation to eliminate deformation points in radar image perspective contraction, overlap and shadow areas, and enhance the reliability of deformation point data.

[0067] Step S1.3: Landslide point screening. Through the above steps, the deformation points and deformation rates of the target area are obtained. In order to obtain the landslide deformation points and more accurately describe the real deformation of the landslide, the effective landslide deformation rate is recalculated according to the deformation rate of the deformation vector point line of sight. On this basis, the negative value of the landslide deformation and the stability threshold are screened to obtain the reliable landslide deformation points in the target area.

[0068] Step S2: Identification of landslide areas by integrating landslide point attribute data and spatial aggregation relationship. The effective landslide deformation rate and spatial aggregation relationship of the obtained reliable landslide deformation points can reflect the stability of the regional landslide. The landslide area is identified by filtering and clustering the landslide deformation points based on spatial relationships. First, the spatial distribution pattern of the landslide points is calculated based on the attribute data of the effective landslide deformation rate to obtain its spatial aggregation and dependency relationship. For the occurrence of landslides, the places with larger deformation rates and tighter aggregation are more likely to have landslides. Therefore, according to the results, randomly distributed deformation points are eliminated. The distribution density of the eliminated landslide vector points in the entire reservoir study area is calculated to more intuitively show the degree of spatial aggregation. The aggregation results are divided into two categories using the natural break point method. The higher value proves that the overall landslide deformation is more serious and is regarded as the identified landslide area.

[0069] Step S3: Landslide susceptibility mapping. A new landslide susceptibility evaluation model is proposed, which uses the inverse tangent function to improve the information value model, and then uses the random forest and extreme gradient boosting method to weight the improved information value model to calculate the landslide susceptibility of the target reservoir area. It includes the following three steps.

[0070] Step S3.1: Calculate the normalized information volume of different subcategories of each landslide influencing factor. Collect data on multiple geographical factors in the study area and reclassify them in ArcGIS. The classification methods include natural breakpoint method and artificial threshold method. According to the identified landslide area, the information value model is used to calculate the information volume of each level of different geographical factors. This information volume can measure the degree of influence on the occurrence of landslides. When no landslide occurs in the influencing factors of a certain level, the calculated information volume is negative infinity. At this time, the subsequent landslide susceptibility calculation cannot be performed. In order to improve the stability of the data, the information volume model is improved, and the inverse tangent function is used to normalize the information volume, so as to calculate the normalized information volume of different subcategories of each geographical factor.

[0071] Step S3.2: Calculate the weight of each landslide influencing factor for landslide occurrence. Taking the landslide area identified in step S2 and the hierarchical characteristics of its corresponding multiple geographical factors as samples, the random forest and extreme gradient boosting methods are used to perform "landslide-non-landslide" binary classification and verify the accuracy of the classification, and the importance of different landslide influencing factors is obtained. The occurrence of landslides in the target reservoir area is analyzed according to the importance.

[0072] Step S3.3, calculate the landslide susceptibility according to the weighted normalized information. The weighted normalized information is calculated with the normalized information obtained in step S3.1 and the corresponding importance obtained in step 3.2 to characterize the landslide susceptibility. The obtained landslide susceptibility is divided into five categories using the natural breakpoint method, with "very low", "low", "medium", "high" and "very high" to represent the different degrees of landslide susceptibility, and the landslide susceptibility distribution of the target area is obtained, which is convenient for early warning and management.

[0073] The following is a specific example to describe the canyon reservoir landslide identification method of the present application. The target area is the Hekou Village Reservoir located at the junction of Shanxi Province and Henan Province and the Baihetan Reservoir in Sichuan Province. The image data is Sentinel-1, Sentinel-2, SRTM DEM and other data. The programming tool is Python. The method specifically includes the following steps:

[0074] Step S01: Obtain reliable landslide deformation points in Hekou Village and Baihetan Reservoir area. Download Sentinel-1 image data from January to December 2020 in the Hekou Village Reservoir area and from July 2021 to April 2023 in the Baihetan Reservoir area, and obtain reliable landslide deformation points within their ranges according to the following.

[0075] Step S011: SBAS-InSAR processing. According to the landslide monitoring requirements, the Sentinel 1 image data downloaded from Hekou Village and Baihetan Reservoir area were processed by SBAS-InSAR. At the same time, the SRTM DEM data with a resolution of 30m in the corresponding area was used to eliminate the influence of terrain phase, and the POD precise orbit data was used for orbit correction. In order to facilitate subsequent spatial analysis, the deformation results were converted into vector point format. Since the accuracy of the obtained deformation points will be affected when the vegetation density and coverage are large, the land cover product of the European Space Agency is used to eliminate the deformation points distributed on the woodland and rivers.

[0076] Step S012: Visibility analysis based on RI index. In SAR system imaging, ups and downs, as well as the angular relationship between the antenna direction and the surface morphology will cause geometric distortion phenomena such as perspective contraction, overlap, and shadows in SAR images. The satellite azimuth, incident angle, and slope and aspect data obtained from DEM data are used to identify areas with good visibility, retain deformation points in areas with good visibility in Hekou Village and Baihetan Reservoir, and enhance the reliability of deformation point data.

[0077] Step S013: Landslide point screening. After the above steps, the deformation points with good visibility in the LOS direction and their deformation rates in Hekou Village and Baihetan Reservoir area are obtained. In order to more accurately describe the actual deformation of the landslide, the effective landslide deformation rate is recalculated according to the deformation rate in the line of sight. According to the characteristics of landslide occurrence, deformation points with negative effective landslide deformation rates are retained in both target areas, and their standard deviations are calculated as the stability threshold. Deformation points with deformation rates exceeding the stability threshold are regarded as reliable landslide deformation points identified in Hekou Village and Baihetan Reservoir area.

[0078] Step S02: Identification of landslide areas by integrating the attribute data of landslide points and spatial aggregation relationship. The effective landslide deformation rate characteristics and spatial aggregation relationship between the reliable landslide deformation points obtained after screening can reflect the stability of the landslide in the reservoir area. Therefore, the landslide area is identified by filtering and clustering the landslide deformation points based on spatial relationships. First, the spatial distribution pattern of the landslide points is calculated based on the attribute data of the effective landslide deformation rate, and its spatial aggregation and dependency are obtained. For the occurrence of landslides, the places with larger deformation rates and tighter aggregation are more likely to have landslides. Therefore, spatial filtering is performed according to the analysis results to eliminate randomly distributed deformation points. The distribution density of the eliminated landslide vector points in the entire study area is calculated to more intuitively display the degree of spatial aggregation. The aggregation results are divided into two categories using the natural break point method. The higher value proves that the overall landslide deformation is more serious and is regarded as the identified landslide area.

[0079] Step S03: Landslide susceptibility mapping. A new landslide susceptibility evaluation model is proposed, which uses the inverse tangent function to improve the information value model, and then couples it with the random forest and extreme gradient boosting methods to calculate the landslide susceptibility of the target reservoir area. According to the characteristics of the reservoir area, elevation, slope, slope aspect, surface undulation, NDVI, NDWI, water body distance and fault distance are selected as geographical factors affecting landslides and reclassified. The improved information volume model is used to calculate the normalized information volume of landslide occurrence, and the improved information value model is weighted using random forest and extreme gradient boosting methods to calculate the landslide susceptibility in Hekou Village and Baihetan Reservoir areas. It includes the following three steps:

[0080] Step S031: Calculate the normalized information of different subclasses of each landslide influencing factor. The landslide influencing factors of Hekou Village and Baihetan are graded respectively, and the grading methods include natural breakpoint method and artificial threshold division, so as to calculate the information value of each level of different landslide influencing factors to measure their influence on the occurrence of landslides. When calculating the information of the graded influencing factors in the Hekou Village reservoir area, there are cases where no landslides occur in the subclasses of elevation, NDVI and fault distance. At this time, the calculated information is negative infinity, and the subsequent landslide susceptibility judgment cannot be performed. In order to improve the stability of the data, the inverse tangent function is used to uniformly normalize the information.

[0081] Step S032: Calculate the importance of each landslide influencing factor to the occurrence of landslides. Taking the landslide areas of Hekou Village and Baihetan identified in step S02 and the grading characteristics of the corresponding landslide influencing factors as samples, the random forest and extreme gradient boosting methods are used to perform landslide-non-landslide binary classification to obtain the importance weights of different landslide influencing factors, and the ROC curve, AUC, Precision, Recall and F1 indicators are used to verify the accuracy of the classification. The occurrence of landslides in Hekou Village and Baihetan Reservoir areas is evaluated according to the importance of each influencing factor. In reservoir areas with canyon-type landforms such as Hekou Village and Baihetan, the slope direction has a great influence on the occurrence of landslides and is a factor that needs to be focused on.

[0082] Step S033: Calculate the landslide susceptibility based on the normalized information volume and importance. The weighted normalized information volume of Hekou Village and Baihetan Reservoir is calculated using the normalized information volume obtained in step S031 and the importance of the corresponding influencing factors obtained in step S032 to characterize the landslide susceptibility. The higher the value, the greater the landslide susceptibility. The natural breakpoint method is used to divide the obtained landslide susceptibility into five categories, with "very low", "low", "medium", "high" and "very high" to represent the different degrees of landslide susceptibility. After visualization and analysis, it is concluded that areas with high landslide susceptibility are mainly concentrated near water bodies, and the susceptibility gradually decreases with the increase of the distance from the water body. This provides a reference for the occurrence of landslides in canyon-type reservoir areas such as Hekou Village and Baihetan, and facilitates timely early warning and management.

[0083] In summary, the landslide identification method in the canyon-type reservoir area of ​​the embodiment of the present application provides an integrated method of identification and evaluation, which can accurately carry out landslide warning and comprehensive evaluation, and introduces deformation points and their attribute data and spatial clustering relationships to identify landslide areas, and is not restricted by the historical landslide inventory data when conducting landslide susceptibility assessment; based on multiple geographical factors, the inverse tangent function is used to improve the information value model, and then coupled with the random forest and extreme gradient boosting method to evaluate and compare the landslide susceptibility of the reservoir area.

[0084] According to the landslide identification method in the canyon-type reservoir area proposed in the embodiment of the present application, the target deformation points of the canyon-type reservoir area can be determined according to the radar data and topography of the canyon-type reservoir area, and the deformation rate of the target landslide deformation point can be calculated, and then the spatial clustering relationship of the target landslide deformation point can be generated based on the deformation rate. The landslide area in the canyon-type reservoir area can be accurately identified based on the deformation rate and the spatial clustering relationship, thereby improving the accuracy of landslide area identification and providing a basis for subsequent landslide disaster warning.

[0085] Next, the device for identifying landslides in a canyon-type reservoir area proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0086] Figure 3 It is a block diagram of a device for identifying landslides in a canyon-type reservoir area according to an embodiment of the present application.

[0087] like Figure 3 As shown, the device 10 for identifying landslides in a canyon-type reservoir area includes: an acquisition module 100 , a determination module 200 and an identification module 300 .

[0088] Among them, the acquisition module 100 is used to obtain radar data and topography of the canyon-type reservoir area; the determination module 200 is used to determine the target landslide deformation point in the canyon-type reservoir area according to the radar data and topography, and calculate the deformation rate of the target landslide deformation point; the identification module 300 is used to generate the spatial clustering relationship of the target landslide deformation point based on the deformation rate, and identify the landslide area in the canyon-type reservoir area based on the deformation rate and the spatial clustering relationship.

[0089] In the embodiment of the present application, the device 10 of the embodiment of the present application further includes: an evaluation module.

[0090] Among them, the evaluation module is used to evaluate the landslide susceptibility level of the landslide area after identifying the landslide area in the canyon-type reservoir area based on the deformation rate and spatial aggregation relationship; and to issue early warnings or reminders based on the landslide susceptibility level.

[0091] In an embodiment of the present application, the determination module 200 is further used to: obtain the deformation rate in the line of sight corresponding to the target deformation point; and convert the deformation rate in the line of sight into a deformation rate perpendicular to the ground based on the geometric relationship of the radar and the terrain.

[0092] In an embodiment of the present application, the determination module 200 is further used to: process radar data to obtain multiple landslide deformation points and corresponding deformation rates in the canyon-type reservoir area; screen multiple landslide deformation points based on topography and deformation rate to obtain target landslide deformation points in the canyon-type reservoir area.

[0093] In the embodiment of the present application, the identification module 100 is further used to: calculate the spatial distribution pattern of the target landslide deformation points based on the deformation rate; and generate the spatial clustering relationship of the target landslide deformation points based on the spatial distribution pattern.

[0094] In an embodiment of the present application, the evaluation module is further used to: classify each landslide impact factor into a grade, and use the information value model to calculate the information value of each grade of each landslide impact factor; unify the information value of each grade of each landslide impact factor to obtain a normalized information value; use the landslide area and the grading characteristics of each landslide impact factor as samples; and classify the samples into landslide and non-landslide to obtain the weight of each landslide impact factor.

[0095] It should be noted that the aforementioned explanation of the embodiment of the method for identifying landslides in a canyon-type reservoir area is also applicable to the device for identifying landslides in a canyon-type reservoir area of ​​this embodiment, and will not be repeated here.

[0096] According to the device for identifying landslides in canyon-type reservoir areas proposed in the embodiment of the present application, the target deformation points of the canyon-type reservoir area can be determined based on the radar data and topography of the canyon-type reservoir area, and the deformation rate of the target landslide deformation point can be calculated. Then, the spatial clustering relationship of the target landslide deformation point can be generated based on the deformation rate. The landslide area in the canyon-type reservoir area can be accurately identified based on the deformation rate and the spatial clustering relationship, thereby improving the accuracy of landslide area identification and providing a basis for subsequent landslide disaster warnings.

[0097] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0098] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0099] When the processor 402 executes the program, the canyon-type reservoir area landslide identification method provided in the above embodiment is implemented.

[0100] Furthermore, the identification also includes:

[0101] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0102] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0103] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0104] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0105] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0106] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0107] The embodiment of the present application also provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the above-mentioned method for identifying landslides in a canyon-type reservoir area is implemented.

[0108] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0109] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0110] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0111] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0112] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

Claims

1. A method for identifying landslides in a canyon reservoir area, characterized in that: The following steps are involved: Obtain radar data and topography of canyon-type reservoir areas; Determine the target landslide deformation point in the canyon-type reservoir area according to the radar data and the topography, and calculate the deformation rate of the target landslide deformation point; A spatial clustering relationship of the target landslide deformation points is generated based on the deformation rate, and a landslide area in the canyon-type reservoir area is identified based on the deformation rate and the spatial clustering relationship.

2. The method for identifying landslides in canyon-type reservoir areas according to claim 1, characterized in that: After identifying the landslide area in the canyon-type reservoir area based on the deformation rate and the spatial aggregation relationship, the method further includes: Assess the landslide susceptibility level of the landslide area; An early warning or reminder is issued based on the landslide susceptibility level.

3. The method for identifying landslides in canyon-type reservoir areas according to claim 1, characterized in that: The step of calculating the deformation rate of the target landslide deformation point includes: Obtaining the deformation rate in the sight direction corresponding to the target deformation point; The deformation rate in the line of sight is converted into a deformation rate perpendicular to the ground based on the geometric relationship of the radar and the topography.

4. The method for identifying landslides in a canyon reservoir area according to claim 2, characterized in that: The step of determining the target landslide deformation point in the canyon-type reservoir area according to the radar data and the topography includes: Processing the radar data to determine a plurality of landslide deformation points and corresponding deformation rates in the canyon-type reservoir area; The plurality of landslide deformation points are screened based on the topography and the deformation rate to obtain target landslide deformation points in the canyon-type reservoir area.

5. The method for identifying landslides in a canyon reservoir area according to claim 1, characterized in that: The generating the spatial clustering relationship of the target landslide deformation points based on the deformation rate includes: Calculating a spatial distribution pattern of deformation points of the target landslide based on the deformation rate; The spatial clustering relationship of the target landslide deformation points is generated based on the spatial distribution pattern.

6. The method for identifying landslides in a canyon reservoir area according to claim 2, characterized in that: The landslide susceptibility level of the landslide area is assessed, including: Acquire at least one landslide influencing factor of the landslide area; The normalized information value and weight of each landslide influencing factor are calculated, and the landslide susceptibility level of the landslide area is evaluated based on the normalized information value and the weight.

7. The method for identifying landslides in canyon-type reservoir areas according to claim 6, characterized in that: The calculation of the normalized information value and weight of each landslide impact factor includes: Classifying each of the landslide impact factors, and calculating the information value of each level of each of the landslide impact factors using an information value model; Unifying the information values ​​of each level of each landslide impact factor to obtain a normalized information value; taking the landslide area and the graded characteristics of each landslide influencing factor as samples; The samples are classified into landslide and non-landslide categories to obtain the weight of each landslide influencing factor.

8. A device for identifying landslides in canyon-type reservoirs, characterized in that: include: Acquisition module, used to obtain radar data and topography of canyon-type reservoir areas; A determination module, used to determine the target landslide deformation point in the canyon-type reservoir area according to the radar data and the topography, and calculate the deformation rate of the target landslide deformation point; An identification module is used to generate a spatial clustering relationship of the target landslide deformation points based on the deformation rate, and to identify the landslide area in the canyon-type reservoir area based on the deformation rate and the spatial clustering relationship.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for identifying landslides in a canyon-type reservoir area as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: The computer program or instruction is executed by a processor to implement the method for identifying landslides in a canyon-type reservoir area as described in any one of claims 1-7.

Images