Methods, devices, equipment and storage media for generating geological disaster monitoring views

Abstract

This application discloses a method, apparatus, equipment, and storage medium for generating geological disaster monitoring views, relating to the field of big data, and aims to solve the problem of inaccurate and inefficient monitoring of geological disasters. The method includes: extracting rasterized features by fusing multi-source data, quantifying various geological environmental features into feature values, converting them into information based on their historical correlation with geological disasters, and then obtaining the comprehensive state information of each unit through weighted fusion, finally outputting a monitoring view. This method replaces manual experience-based interpretation with data-driven objective analysis, which can significantly improve the accuracy and efficiency of geological disaster area monitoring.

Description

Technical Field

[0001] This application relates to the field of big data, and in particular to a method, apparatus, equipment and storage medium for generating geological disaster monitoring views. Background Technology

[0002] Geological disasters pose a continuous threat to residents' safety, infrastructure operation, and national land spatial planning. Therefore, carrying out scientific and effective regional geological disaster monitoring and control is the primary link in disaster prevention and mitigation work.

[0003] Existing technologies typically rely on technicians to manually interpret and analyze regional topography and geology, thereby making empirical judgments and classifications of regional stability.

[0004] However, this method, which relies on human experience for interpretation, is greatly influenced by personal subjectivity, resulting in low processing efficiency and accuracy, and is unable to accurately and effectively monitor geological disasters. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, equipment and storage medium for generating geological disaster monitoring views, which aims to solve the problem of the inability to accurately and efficiently monitor geological disasters.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application provides a method for generating geological disaster monitoring views, including: Acquire digital elevation data, basic geographic information data, remote sensing image data, and radar image data corresponding to the target area, which includes multiple raster units; Based on digital elevation data, basic geographic information data, remote sensing image data, and radar image data, raster cell features are extracted to determine the target values ​​of multiple feature quantities corresponding to each raster cell in the target area. These multiple feature quantities include topographic parameters, stratigraphic lithology parameters, surface cover type parameters, distance parameters from the target object, and surface deformation parameters. The target objects include roads and pipelines. Based on the pre-defined mapping relationship between the values ​​of multiple feature quantities and the amount of information, for each grid cell, multiple amounts of information are determined according to the target values ​​of the multiple feature quantities corresponding to the grid cell; the amount of information is used to characterize the degree of correlation between the corresponding feature quantity and the occurrence of geological disasters. Based on the weighting coefficients corresponding to multiple preset feature quantities, the multiple information quantities corresponding to each grid cell are weighted to obtain the comprehensive state information corresponding to each grid cell; the comprehensive state information is used to characterize the probability of geological disasters occurring in the grid cell; Based on the comprehensive status information of each grid cell, the geological disaster monitoring view corresponding to the target area is output.

[0007] The geological disaster monitoring view generation method provided in this application integrates multi-source data such as digital elevation data, basic geographic information data, remote sensing image data, and radar image data to achieve comprehensive coverage of geological disaster influencing factors in the target area. Through raster unit feature extraction, multi-dimensional features such as topography, geology, land cover, distance to critical infrastructure, and surface deformation are quantified into target values, providing a structured data foundation for subsequent geological disaster risk monitoring. Based on the preset mapping relationship between feature values ​​and information content, the target values ​​of the features are converted into information content representing the degree of correlation with geological disasters, realizing the transformation from raw data to disaster correlation. Then, through weighted processing and fusion of multiple information contents, comprehensive state information reflecting the probability of geological disaster occurrence in each raster unit is obtained, comprehensively considering the differences in the contribution of various factors to improve objectivity. Finally, a geological disaster monitoring view is generated based on the comprehensive state information, intuitively displaying the regional risk distribution, replacing the traditional subjective interpretation relying on human experience, significantly improving the accuracy and efficiency of geological disaster monitoring, and providing reliable data support for disaster prevention and mitigation decision-making.

[0008] In some embodiments, topographic parameters include slope, aspect, elevation, and topographic relief; surface deformation parameters include surface deformation rate. Before determining the corresponding multiple information values ​​for each grid cell based on the target values ​​of the multiple feature values ​​corresponding to the grid cell, according to the pre-defined mapping relationship between the values ​​of multiple feature values ​​and the information content, the method further includes: For each feature, perform the following steps to obtain the mapping relationship between the values ​​of multiple features and the amount of information: Obtain the grading criteria corresponding to the feature quantity, and determine multiple levels corresponding to the feature quantity based on the range of target values ​​of all grid cells in the target area and the grading criteria, and determine the total number of grid cells in each level; each level includes one or more values ​​of the feature quantity, and the values ​​of the feature quantity included in each level are different. Based on the target value of each grid cell under the feature quantity, each grid cell is mapped and divided into the corresponding level; Acquire historical geological disaster data corresponding to the target area, and based on the historical geological disaster data, determine the first number of surface deformation points included in the target area when the historical geological disaster occurred, and the second number of surface deformation points included in the grid unit within each level; the historical geological disaster data includes the location information of deformation points of each geological disaster. For each level corresponding to a feature, the information content corresponding to each level is determined according to the following expression:

[0009] Where i represents the level. The amount of information corresponding to level i; The total number of grid cells of level i within the target area. This represents the second number of surface deformation points included in the raster cells within level i. The first number of surface deformation points included within the target area. This represents the total number of grid cells within the target area.

[0010] In some embodiments, before weighting multiple information quantities corresponding to each grid cell according to preset weight coefficients corresponding to multiple feature quantities to obtain the comprehensive state value corresponding to each grid cell, the method further includes: Obtain the judgment matrix corresponding to multiple feature quantities, and determine the largest eigenvalue and the eigenvector corresponding to the largest eigenvalue of the judgment matrix; the judgment matrix is... Square array The number of characteristic quantities, A and b are positive integers greater than 1. The element value in the a-th row and b-th column of the matrix represents the importance scale value of the a-th feature relative to the b-th feature; a and b are both positive integers. The consistency ratio of the judgment matrix is ​​determined according to the following expression:

[0011] in, To determine the largest eigenvalue of a matrix, To determine the consistency ratio of the matrix, The pre-defined average random consistency index; If the consistency ratio is less than or equal to the preset threshold, the feature vector is normalized, and the values ​​of each element in the normalized vector are used as the weight coefficients corresponding to multiple features.

[0012] In some embodiments, the method further includes: If the consistency ratio is greater than the preset threshold, then each off-diagonal element in the judgment matrix is ​​subjected to quantitative perturbation processing to determine the change in the consistency ratio of the judgment matrix after perturbation processing, and the off-diagonal element whose change exceeds the preset change threshold is taken as the target element. Generate and send adjustment instructions for the target element to the user-side device, and update the judgment matrix in response to the adjustment operation performed by the user-side device based on the adjustment instructions for the target element, thereby obtaining a new judgment matrix; Repeat the step of determining the consistency ratio of the judgment matrix until the consistency ratio is less than or equal to the preset threshold.

[0013] In some embodiments, the comprehensive status information is a comprehensive status value; Based on the comprehensive status information of each grid cell, the geological hazard monitoring view corresponding to the target area is output, including: The comprehensive state values ​​of each grid cell are sorted according to their numerical values ​​to obtain a numerical sequence. Based on the preset number of levels K, the numerical sequence is divided into K groups; K is a positive integer greater than 1. With the goal of minimizing the sum of the within-group variances of K groups, the positions of K-1 hierarchical breakpoints in the numerical sequence are determined, and the comprehensive state value corresponding to the position is determined as the hierarchical threshold. Based on the classification threshold, the comprehensive state value of each grid cell is classified into the corresponding geological hazard susceptibility level; Based on the geological hazard susceptibility level corresponding to each grid cell, a geological hazard monitoring view is output.

[0014] In some embodiments, based on the preset mapping relationship between the values ​​of multiple feature quantities and the amount of information, for each grid cell, the corresponding multiple amounts of information are determined according to the target values ​​of the multiple feature quantities corresponding to the grid cell, including: For each grid cell within the target area, perform the following steps to determine multiple information quantities corresponding to each grid cell: For each of the multiple feature quantities, the corresponding level is determined based on the target value of the grid cell under the feature quantity; From the mapping relationship, obtain the amount of information corresponding to the feature quantity and level.

[0015] In some embodiments, raster cell feature extraction is performed based on digital elevation data, basic geographic information data, remote sensing image data, and radar image data to determine the target values ​​of multiple feature quantities corresponding to each raster cell in the target area, including: Based on digital elevation data, the slope, aspect, elevation, and topographic relief of each grid cell are determined through grid cell surface analysis. Based on basic geographic information data, spatial queries and distance calculations are used to determine the distance values ​​from roads, pipelines, and strata lithology of each grid cell. Based on remote sensing image data, the land cover type category value of each raster unit is determined through image classification processing. Based on radar image data, the deformation rate value of each grid cell is determined through interferometric phase analysis and time-series calculation.

[0016] Secondly, this application provides a geological disaster monitoring view generation device, the device comprising: The acquisition unit is used to acquire digital elevation data, basic geographic information data, remote sensing image data and radar image data corresponding to the target area. The target area includes multiple raster units. The first processing unit is used to extract raster unit features based on digital elevation data, basic geographic information data, remote sensing image data, and radar image data, and to determine the target values ​​of multiple feature quantities corresponding to each raster unit in the target area. The multiple feature quantities include topographic parameters, stratigraphic lithology parameters, surface cover type parameters, distance parameters from the target object, and surface deformation parameters. The target objects include roads and pipelines. The second processing unit is used to determine the corresponding multiple information quantities for each grid cell based on the target values ​​of the multiple feature quantities corresponding to the grid cell, according to the mapping relationship between the values ​​of multiple feature quantities and the information quantity. The information quantity is used to characterize the degree of correlation between the corresponding feature quantity and the occurrence of geological disasters. The determination unit is used to weight multiple information quantities corresponding to each grid unit according to the weight coefficients corresponding to multiple preset feature quantities, so as to obtain the comprehensive state information corresponding to each grid unit; the comprehensive state information is used to characterize the probability of geological disasters occurring in the grid unit; The output unit is used to output a geological disaster monitoring view corresponding to the target area based on the comprehensive status information of each grid cell.

[0017] Thirdly, an electronic device is provided, the method comprising: a memory and at least one processor. The memory is communicatively connected to the processor. The memory is used to store computer program code, the computer program code including computer instructions. When the processor executes the computer instructions, it causes the electronic device to perform the method of the first aspect and any possible implementation thereof.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions. When these computer instructions are executed by a processor, they are used to implement the method as described in the first aspect and any possible implementation thereof. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a method for generating geological disaster monitoring views provided in an embodiment of this application; Figure 2 This is a schematic diagram of grid division provided in an embodiment of this application; Figure 3 This is a schematic diagram of slope division provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the relationship between slope grading and the distribution of geological disaster points, provided in an embodiment of this application. Figure 5 This is a schematic diagram of slope aspect division provided in an embodiment of this application; Figure 6 This is a schematic diagram illustrating the relationship between slope aspect classification and the distribution of geological hazard points, provided in an embodiment of this application. Figure 7 This is a schematic diagram of elevation division provided in an embodiment of this application; Figure 8 This is a schematic diagram illustrating the relationship between elevation classification and the distribution of geological disaster points, provided in an embodiment of this application. Figure 9 This is a schematic diagram of terrain relief division provided in an embodiment of this application; Figure 10 This is a schematic diagram illustrating the relationship between terrain relief classification and the distribution of geological disaster points, provided in an embodiment of this application. Figure 11 This is a schematic diagram illustrating the division of distances from roads, provided in an embodiment of this application; Figure 12 This is a schematic diagram illustrating the relationship between road distance classification and the distribution of geological disaster points, provided in an embodiment of this application. Figure 13 This is a schematic diagram of stratigraphic lithology provided in an embodiment of this application; Figure 14 This is a schematic diagram illustrating the relationship between stratigraphic lithology classification and the distribution of geological hazard points, provided in an embodiment of this application. Figure 15 This is a schematic diagram illustrating the classification of land cover types provided in an embodiment of this application; Figure 16 This is a schematic diagram illustrating the relationship between land cover type classification and geological hazard point distribution, provided in an embodiment of this application. Figure 17 This is a schematic diagram illustrating the distance division from the pipeline provided in an embodiment of this application; Figure 18 This is a schematic diagram illustrating the relationship between pipeline distance classification and geological hazard point distribution, provided in an embodiment of this application. Figure 19 This is a schematic diagram of temporal InSAR deformation rate partitioning provided in an embodiment of this application; Figure 20 This is a geological disaster monitoring view provided in an embodiment of this application; Figure 21 This is a schematic diagram of the structure of a geological disaster monitoring view generation device provided in an embodiment of this application; Figure 22 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the description of this application, it should be understood that the terms "upper," "lower," "left," "right," "front," "rear," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or relative positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and for simplification, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Unless otherwise specified, the above-mentioned orientational descriptions can be flexibly set in practical applications, provided that the relative positional relationships shown in the accompanying drawings are satisfied.

[0023] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0024] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "communication" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. They can refer to a direct connection or an indirect connection through an intermediate medium, or a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0025] In embodiments of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, article, or apparatus that includes that element.

[0026] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0027] In the description of this specification, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0028] With the frequent occurrence of geological disasters, how to conduct susceptibility monitoring scientifically and accurately has become a core issue of great concern. Geological disaster susceptibility monitoring can provide important support for disaster risk management, land spatial planning, and emergency response, and is of great significance in reducing casualties and economic losses caused by geological disasters.

[0029] In related technologies, technicians typically make manual judgments and analyses based on the regional topography and geology to empirically assess and classify the stability of the region.

[0030] However, this method, which relies on human experience for interpretation, is greatly influenced by personal subjectivity, resulting in low processing efficiency and accuracy, and is unable to accurately and effectively monitor geological disasters.

[0031] To improve the efficiency and accuracy of geological disaster monitoring, this application's implementation method achieves rasterized feature extraction by fusing multi-source data. Various geological environmental characteristics are quantified into feature values, and based on their historical correlation with geological disasters, they are converted into information. Then, weighted fusion is used to obtain the comprehensive status information of each unit, ultimately generating a visualized monitoring view. This method replaces manual experience-based interpretation with data-driven objective analysis, significantly improving the accuracy and efficiency of geological disaster area monitoring.

[0032] The geological disaster monitoring view generation method provided in this application can be applied to electronic devices. These electronic devices can be computer equipment, a single server or a server cluster consisting of multiple servers, a cloud computing platform with data processing capabilities, an edge computing device, a chip, or a device with computing capabilities. This application does not limit the specific form of the electronic device.

[0033] Figure 1 This is a flowchart illustrating a method for generating geological disaster monitoring views provided in an embodiment of this application. Figure 1 As shown, the method in the embodiments of this application may include: S101. Acquire digital elevation data, basic geographic information data, remote sensing image data, and radar image data corresponding to the target area. The target area includes multiple raster units.

[0034] For example, this embodiment can obtain multi-source spatial data of the target area by calling a geographic information system interface, a remote sensing data service platform, or a local database. Among them, digital elevation data can be in digital elevation model (DEM) format to reflect terrain elevation information; basic geographic information data can include geological maps, road and pipeline vector data, etc.; remote sensing image data can be multispectral or hyperspectral imagery; radar image data can include synthetic aperture radar (SAR) imagery for surface deformation monitoring.

[0035] In this embodiment, the target region is divided into multiple raster units, serving as the basic spatial units for subsequent analysis. Using regular raster units as evaluation units provides a high-resolution analytical foundation with spatial continuity and uniform attributes for the target region, ensuring consistency between the analysis process and the results. Figure 2 As shown, Figure 2 This is a schematic diagram of grid division provided in an embodiment of this application.

[0036] This embodiment acquires multi-source spatial data to construct a data foundation that comprehensively covers key features such as topography, geology, land cover, and surface deformation. Furthermore, rasterization discretizes continuous space into standardized analytical units, providing a unified framework for subsequent quantitative and automated analysis.

[0037] S102. Based on digital elevation data, basic geographic information data, remote sensing image data, and radar image data, raster cell feature extraction is performed to determine the target values ​​of multiple feature quantities corresponding to each raster cell in the target area. The multiple feature quantities include topographic parameters, stratigraphic lithology parameters, surface cover type parameters, distance parameters from the target object, and surface deformation parameters. The target objects include roads and pipelines.

[0038] For example, this embodiment extracts feature quantities reflecting geological hazard characteristics from multi-source data for each grid cell. For instance, slope, aspect, elevation, and topographic relief are calculated based on surface analysis using digital elevation data; the nearest distance to roads and pipelines is calculated using spatial query and buffer analysis based on basic geographic information data, and the lithological category of the strata is obtained through geological map analysis; land cover types (such as vegetation, bare soil, buildings, etc.) are identified using supervised classification or deep learning models based on remote sensing image data; and the surface deformation rate is extracted using interferometry techniques based on radar image data.

[0039] In one feasible implementation, feature extraction can be achieved using methods such as raster computation, spatial overlay analysis, and image classification algorithms. The extraction results are stored in the attribute table of each raster unit in the form of numerical values ​​or category codes, forming a structured feature dataset.

[0040] This embodiment realizes the transformation from raw spatial data to quantified disaster characteristics. It accurately quantifies complex information such as terrain, geology, and surface dynamics into feature values ​​for each grid cell, laying a standardized and computable data foundation for objective assessment and improving the efficiency and consistency of feature extraction.

[0041] S103. Based on the preset mapping relationship between the values ​​of multiple feature quantities and the information quantity, for each grid cell, determine the corresponding multiple information quantities according to the target values ​​of the multiple feature quantities corresponding to the grid cell; the information quantity is used to characterize the degree of correlation between the corresponding feature quantity and the occurrence of geological disasters.

[0042] For example, this embodiment pre-establishes a mapping relationship between the value and information content of each feature quantity. This mapping relationship can be obtained through statistical analysis of historical geological disaster data, reflecting the quantitative correlation between different feature value ranges and the frequency of disaster occurrence. For each grid cell, based on the target value of each feature quantity, the corresponding mapping relationship is queried to obtain the information content value corresponding to each feature quantity.

[0043] In one feasible implementation, the mapping relationship can be stored in the form of a lookup table, piecewise function, or rule base. For example, the slope value is divided into multiple intervals, each interval corresponding to an information value calculated based on the density of historical disaster points within that slope interval. This step converts the original feature values ​​into information with disaster indication significance, providing standardized input for subsequent comprehensive assessment.

[0044] This embodiment introduces the concept of "information content" based on historical statistics, objectively transforming feature values ​​into indicators that characterize their correlation with the occurrence of geological disasters. This mapping relationship originates from actual disaster data, reducing the bias caused by subjective experience-based assignments and making the contribution of each feature statistically reliable, thus providing a scientific and interpretable intermediate variable for subsequent comprehensive judgment.

[0045] S104. Based on the weighting coefficients corresponding to multiple preset feature quantities, the multiple information quantities corresponding to each grid cell are weighted to obtain the comprehensive state information corresponding to each grid cell; the comprehensive state information is used to characterize the probability of geological disasters occurring in the grid cell.

[0046] For example, this embodiment assigns weight coefficients to each feature quantity based on its relative importance to the impact of geological hazards. The weights can be determined through expert scoring, analytic hierarchy process (AHP), or statistical models based on historical data. For each grid cell, the information content corresponding to each feature quantity is multiplied by its corresponding weight and then summed to obtain the comprehensive state information (e.g., comprehensive state value) of that cell. The higher this value, the greater the likelihood of a geological hazard occurring in that grid cell.

[0047] In one feasible implementation, the weighting process can employ linear weighting, nonlinear fusion, or other methods. The weighting coefficients can be dynamically adjusted according to regional characteristics or monitoring targets to adapt to the assessment needs of different types of geological hazards (such as landslides and debris flows).

[0048] This embodiment overcomes the limitations of single-feature discrimination by comprehensively considering the combined effects of multiple features through weighted fusion. The introduction of weighting coefficients distinguishes the differences in contributions of different features, enabling the comprehensive state information to more reasonably reflect the spatial differentiation of the probability of geological disasters. This process achieves the aggregation from multiple indicators to a single risk index, making the results more intuitive.

[0049] S105. Based on the comprehensive status information of each grid cell, output the geological disaster monitoring view corresponding to the target area.

[0050] For example, this embodiment spatially visualizes the comprehensive status information of each grid cell to generate a geological disaster monitoring view. For instance, a gradient color scheme can be used to map the comprehensive status values ​​to colors, creating a grid thematic map; or grid cells can be divided into different risk levels based on hierarchical thresholds and displayed with different legends. The monitoring view can be output as an image file, a web map service, or integrated into a geographic information platform for users to view and analyze.

[0051] In one feasible implementation, this embodiment also supports interactive operations on the view, such as zooming, querying attributes, risk statistics, and time series comparison, to enhance the usability and decision support capabilities of the monitoring results.

[0052] This embodiment transforms numerical analysis results into intuitive views. The monitoring view can clearly show the spatial distribution pattern and risk level differences of geological disaster susceptibility throughout the target area, enabling decision-makers and managers to quickly identify high-risk areas. It provides intuitive and reliable graphical basis for the precise deployment of disaster prevention and mitigation, the scientific avoidance of land spatial planning, and the prioritization of emergency response, greatly improving the operational application efficiency of monitoring results.

[0053] In summary, this embodiment achieves comprehensive coverage of geological hazard influencing factors in the target area by integrating multi-source data such as digital elevation data, basic geographic information data, remote sensing image data, and radar image data. Through raster unit feature extraction, multi-dimensional features such as topography, geology, land cover, distance to critical infrastructure, and surface deformation are quantified into target values, providing a structured data foundation for subsequent geological hazard risk monitoring. Based on the preset mapping relationship between feature values ​​and information content, the target values ​​of the features are converted into information content representing the degree of correlation with geological hazards, realizing the transformation from raw data to hazard correlation. Then, through weighted processing and fusion of multiple information contents, comprehensive state information reflecting the probability of geological hazard occurrence in each raster unit is obtained, comprehensively considering the differences in the contribution of various factors to improve objectivity. Finally, a geological hazard monitoring view is generated based on the comprehensive state information, intuitively displaying the regional risk distribution, replacing the traditional subjective interpretation relying on human experience, significantly improving the accuracy and efficiency of geological hazard monitoring, and providing reliable data support for disaster prevention and mitigation decision-making.

[0054] In one feasible implementation, the topographic parameters include slope, aspect, elevation, and topographic relief; the surface deformation parameters include the surface deformation rate. S102 may specifically include the following steps: Based on digital elevation data, the slope, aspect, elevation, and topographic relief of each grid cell are determined through grid cell surface analysis.

[0055] Based on basic geographic information data, spatial queries and distance calculations are used to determine the distance values ​​from roads, pipelines, and strata lithology of each grid cell. Based on remote sensing image data, the land cover type category value of each raster unit is determined through image classification processing.

[0056] Based on radar image data, the deformation rate value of each grid cell is determined through interferometric phase analysis and time-series calculation.

[0057] In this embodiment, characteristics such as slope, aspect, elevation, and topographic relief affect surface runoff, material potential energy, and slope stability; stratigraphic lithology and surface cover type characteristics reflect the intrinsic properties of soil and rock masses, such as material composition and erosion resistance; distance from roads reveals the disturbance effect of human engineering activities (such as excavation and vibration) on the geological environment; distance from pipelines directly relates to the risk exposure degree of the core disaster-bearing body; and surface deformation rate characteristics are used to monitor surface displacement in real time using InSAR technology to capture the precursor dynamics of geological disaster development. The selection of the above characteristics comprehensively considers the static background and dynamic changes of the disaster-prone environment, takes into account both general disaster-causing mechanisms and the risk concerns of specific protection objects (in this embodiment, pipelines, but other objects are also possible), and verifies the correlation through historical disaster data to ensure the comprehensiveness, pertinence, and objectivity of the evaluation system.

[0058] For example, when extracting raster cell features based on digital elevation data, this embodiment can utilize digital elevation model (DEM) data and perform calculations on each raster cell using GIS raster surface analysis tools. Specifically, it calculates the slope value (in degrees), aspect value (in degrees, which can be categorized and coded according to eight or nine directions), elevation value (in meters), and topographic relief (in meters) for each raster cell. The topographic relief can be calculated using a focus statistics tool by determining the difference between the maximum and minimum elevation values ​​within a specified neighborhood window (such as a 3x3 or 5x5 raster).

[0059] When extracting raster features based on basic geographic information data, this embodiment can import a geological database containing road and pipeline vector line data and geological maps. Then, through spatial analysis using "nearest neighbor analysis" or "Euclidean distance," the straight-line distance from the center point of each raster cell to the nearest road and the nearest pipeline is determined, yielding the distance values ​​to the road and pipeline, respectively. Simultaneously, through spatial overlay analysis, the stratigraphic lithology polygon layer from the geological map is overlaid with the raster cells, assigning each cell a corresponding stratigraphic lithology category code to represent different stratigraphic lithology categories (such as Triassic Qingyan Formation argillaceous limestone, Triassic Jialingjiang Formation limestone, Triassic Feixianguan Formation mudstone, Permian Qixia Formation limestone, Permian Maokou Formation limestone, etc.).

[0060] When extracting raster features based on remote sensing image data, this embodiment can acquire multispectral or high-resolution remote sensing images of the target area. Supervised classification (such as maximum likelihood or support vector machine) or unsupervised classification methods are used to classify land cover types in the images, identifying land cover types such as forest, grassland, cultivated land, built-up land, water bodies, and bare land. The classification result layer is then spatially registered with the raster cells and attribute assigned to obtain the land cover type category value for each cell.

[0061] When extracting grid features based on radar imagery data, this embodiment can acquire temporal synthetic aperture radar (SAR) imagery data covering the target area. Interferometric synthetic aperture radar (InSAR) techniques, such as permanent scatterer interferometry (PS-InSAR) or small baseline set (SBAS-InSAR), are used to perform interferometric phase analysis, phase unwrapping, and temporal calculation, ultimately extracting the average surface deformation rate (unit: mm / year) for each grid cell during the monitoring period. Positive values ​​typically indicate uplift, while negative values ​​indicate subsidence.

[0062] This embodiment achieves automated and precise quantification of feature quantities. By combining GIS spatial analysis with remote sensing and InSAR professional processing technologies, complex geological environmental information is transformed into feature quantities that can be directly used for statistical calculation in each raster unit, providing a reliable and consistent data foundation for subsequent geological disaster monitoring.

[0063] In one feasible implementation, prior to S103, this embodiment performs the following steps for each feature quantity to obtain the mapping relationship between the values ​​of multiple feature quantities and the amount of information: Obtain the grading criteria corresponding to the feature quantity, and determine multiple levels corresponding to the feature quantity based on the range of target values ​​of all grid cells in the target area and the grading criteria, and determine the total number of grid cells in each level; each level includes one or more values ​​of the feature quantity, and the values ​​of the feature quantity included in each level are different.

[0064] Based on the target value of each grid cell under the feature quantity, each grid cell is mapped and divided into the corresponding level.

[0065] Obtain historical geological disaster data corresponding to the target area, and based on the historical geological disaster data, determine the first number of surface deformation points included in the target area when the historical geological disaster occurred, and the second number of surface deformation points included in the grid unit within each level; the historical geological disaster data includes the location information of deformation points of various geological disasters.

[0066] For each level corresponding to a feature, the information content corresponding to each level is determined according to the following expression: (1) Where i represents the level. The amount of information corresponding to level i; The total number of grid cells of level i within the target area. This represents the second number of surface deformation points included in the raster cells within level i. The first number of surface deformation points included within the target area. This represents the total number of grid cells within the target area.

[0067] For example, in this embodiment, before determining the information content of each grid cell, a mapping relationship between the value of each feature and the information content is established in advance, specifically including: (1) Classification: For each feature quantity, first obtain its value range in all grid cells within the target area. Based on geological common sense, industry standards or natural discontinuity method and other classification criteria, divide the continuous value range into several discrete levels.

[0068] For example, regarding slope, Figure 3 This is a schematic diagram of slope division provided in an embodiment of this application, such as... Figure 3 As shown, this embodiment divides the slope of the target area into 8 levels: 0-8 degrees, 8-14 degrees, 14-19 degrees, 19-24 degrees, 24-29 degrees, 29-35 degrees, 35-41 degrees, and 41-58 degrees. The total number of grid cells falling into each level is counted. Figure 4 This is a schematic diagram illustrating the relationship between slope grading and the distribution of geological hazard points, provided in an embodiment of this application. (See attached diagram.) Figure 4 Geological hazard points within the target area are mainly concentrated in areas with slopes of 8° to 35°.

[0069] Regarding slope aspect, Figure 5 This is a schematic diagram of slope aspect division provided in an embodiment of this application, such as... Figure 5 As shown, this embodiment divides the slope direction within the target area into 9 directions: plane, north, northeast, east, southeast, south, southwest, west, and northwest. The total number of grid cells falling within each directional partition is then counted.

[0070] Figure 6 This is a schematic diagram illustrating the relationship between slope aspect classification and the distribution of geological hazard points, provided in an embodiment of this application. (See attached diagram.) Figure 6 Geological hazard points within the target area are mainly concentrated in the southeast, south, and southwest directions. This is because the southern slopes have better sunlight conditions, greater soil temperature variations, and faster water evaporation, which affect the soil's mobility and looseness, creating conditions conducive to the development of geological hazards.

[0071] Regarding elevation, Figure 7 This is a schematic diagram of elevation division provided in an embodiment of this application, such as... Figure 7 As shown, this embodiment divides the elevation into 6 levels based on the target area's altitude range (1238~1900m). The total number of grid cells falling within each elevation level is counted.

[0072] Figure 8 This is a schematic diagram illustrating the relationship between elevation classification and the distribution of geological hazard points, provided in an embodiment of this application. (See attached diagram.) Figure 8 ,Depend on Figure 8It can be seen that the geological disaster points in the target area are mainly distributed in the altitude range of 1475~1741m.

[0073] Regarding the terrain undulation, Figure 9 This is a schematic diagram of terrain relief division provided in an embodiment of this application, such as... Figure 9 As shown, this embodiment divides the range of terrain relief (0~126m) within the target area into 5 levels. The total number of grid cells falling into each level is counted.

[0074] Figure 10 This is a schematic diagram illustrating the relationship between terrain relief classification and the distribution of geological hazard points, provided in an embodiment of this application. (See attached diagram.) Figure 10 ,Depend on Figure 10 It can be seen that when the terrain undulation is between 0 and 66m, the density of geological disaster points shows an upward trend, which has obvious regularity.

[0075] Regarding the distance from the road, Figure 11 This is a schematic diagram illustrating the distance division from the road provided in an embodiment of this application, such as... Figure 11 As shown, this embodiment divides it into 5 levels: [0, 50) meters, [50, 200) meters, [200, 500) meters, [500, 1000) meters, and [1000, 1260] meters. The total number of grid cells falling within each distance buffer zone is counted. Figure 12 A schematic diagram illustrating the relationship between road distance classification and geological hazard point distribution, provided as an embodiment of this application, is shown below. Figure 12 ,Depend on Figure 12 It can be seen that the number of disaster points in the target area decreases as the distance from the road increases, with the highest number of disaster points within a 50m range, showing a clear pattern.

[0076] Regarding the lithology of the strata, Figure 13 This is a schematic diagram of stratigraphic lithology provided in an embodiment of this application, such as... Figure 13 As shown, this embodiment classifies lithology into five types based on the geological map of the target area: Triassic Qingyan Formation argillaceous limestone, Triassic Jialingjiang Formation limestone, Triassic Feixianguan Formation mudstone, Permian Qixia Formation limestone, and Permian Maokou Formation limestone. The total number of raster cells belonging to each lithology type is then counted.

[0077] Figure 14 This is a schematic diagram illustrating the relationship between stratigraphic lithology classification and the distribution of geological hazard points, provided in an embodiment of this application. (See attached diagram.) Figure 14 ,Depend on Figure 14 It can be seen that the geological hazards in the target area mainly occur in the mudstone of the Feixianguan Formation of the Triassic System and the argillaceous limestone of the Qingyan Formation of the Triassic System.

[0078] For land cover type, Figure 15This is a schematic diagram illustrating the classification of land cover types provided in an embodiment of this application, such as... Figure 15 As shown, this embodiment uses remote sensing image interpretation to classify land cover within the target area into five types: water bodies, woodlands, built-up areas, grasslands, and cultivated land. The total number of raster cells belonging to each cover type is then counted.

[0079] Figure 16 This is a schematic diagram illustrating the relationship between land cover type classification and geological hazard point distribution, provided in an embodiment of this application. (See attached diagram.) Figure 16 ,Depend on Figure 16 It can be seen that the bare land areas are the most prone to geological disasters.

[0080] This embodiment primarily focuses on the pipeline as the disaster-bearing object, and considers the distance from the pipeline. Figure 17 This is a schematic diagram of the distance division from the pipeline provided in an embodiment of this application, such as... Figure 17 As shown, this embodiment divides the distance into 5 levels: [0, 50) meters, [50, 200) meters, [200, 500) meters, [500, 1000) meters, and >1000 meters. The total number of grid cells falling within each distance range is counted.

[0081] Figure 18 This is a schematic diagram illustrating the relationship between pipeline distance classification and geological hazard point distribution, provided in an embodiment of this application. (See attached diagram.) Figure 18 ,Depend on Figure 18 It can be seen that the number of geological hazard points in each zone is similar across the different levels of distance from the pipeline.

[0082] Regarding the temporal InSAR deformation rate, Figure 19 This is a schematic diagram of temporal InSAR deformation rate partitioning provided in an embodiment of this application, as shown below. Figure 19 As shown, this embodiment, based on the natural breakpoint method, divides the deformation rate into 10 levels: [-66, -40) mm / year (mm / a), [-40, -30) mm / a, [-30, -20) mm / a, [-20, -10) mm / a, [-10, 0) mm / a, [0, 10) mm / a, [10, 20) mm / a, [20, 30) mm / a, [30, 40) mm / a, [40, 59) mm / a. The total number of grid cells falling into each deformation rate level interval is counted.

[0083] Among them, the schematic diagram of the distribution of the above-mentioned multiple characteristic quantities and their relationship with the distribution of geological disasters includes Figure 4 , Figure 6 , Figure 8 , Figure 10 , Figure 12 , Figure 14 , Figure 16 as well as Figure 18 The vertical axis, C-index, corresponds to the contribution of the characteristic quantity classification interval to the occurrence of geological disasters. If C-index > 1.00, it means that the density of disaster points in the slope interval is higher than the average level of the whole area, that is, the interval has a positive contribution to the occurrence of disasters and is a disaster-prone interval. If C-index ≈ 1.00, it means that the density of disaster points in the characteristic quantity classification interval is comparable to the average level of the whole area, that is, the influence of the interval on the occurrence of disasters is neutral. If C-index < 1.00, it means that the density of disaster points in the characteristic quantity classification interval is lower than the average level of the whole area, that is, the interval has an inhibitory effect on the occurrence of disasters and is a disaster-inactive interval. The point ratio represents the percentage of the number of disaster points distributed in the characteristic quantity classification interval to the total number of disaster points in the whole area, and the area ratio represents the percentage of the area of ​​the characteristic quantity classification interval to the total area of ​​the whole area.

[0084] (2) Cell mapping: Based on the specific target value (such as slope value) of each grid cell under each feature quantity, it is assigned to the corresponding level.

[0085] (3) Linking historical disaster data: Obtain historical geological disaster data for the target area, which includes the geographical location information of deformation points (or disaster points) where disasters have occurred. Count the total number of historical disaster deformation points in the entire area. Then, for each level of each characteristic quantity, count the number of disaster deformation points falling within the corresponding spatial range of that level.

[0086] (4) Calculate the amount of information: For each level of the characteristic quantity, calculate the amount of information it provides according to the expression (1), where the natural logarithm of the ratio of “the density of disaster points within the level” to “the average density of disaster points in the whole area” is calculated. A value greater than 0 indicates that the level is conducive to the occurrence of disasters; the larger the value, the stronger the correlation. <0 indicates that the level suppresses the occurrence of disasters.

[0087] This embodiment utilizes historical disaster data to objectively quantify the correlation between different value ranges (levels) of each characteristic quantity and the occurrence of geological disasters. By calculating the amount of information, qualitative understandings in the geological field (such as "steep slopes are prone to landslides") are transformed into calculable quantitative indicators, thereby improving scientific rigor and repeatability.

[0088] In one example, S103 above may include the following steps: For each grid cell within the target area, the following steps are performed to determine multiple information quantities corresponding to each grid cell: For each of the multiple feature quantities, the corresponding level is determined based on the target value of the grid cell under the feature quantity; from the mapping relationship, the information quantity corresponding to the feature quantity and level is obtained.

[0089] Among them, the information content is used to characterize the degree of correlation between the corresponding feature quantity and the occurrence of geological disasters; For example, in this embodiment, based on the established mapping relationship between the "value-information content" of each feature quantity, S103 is executed to determine the information content corresponding to each feature quantity of each grid cell. The specific process is as follows: For each grid cell within the target area, this embodiment iterates through all feature quantities (such as slope, aspect, elevation, distance from the pipeline, etc.) and performs the following operations: For the current feature quantity, firstly, based on the target value of the grid cell under that feature quantity (such as slope = 25°), its level (such as "25-35°" level) is determined by referring to the level classification standard of that feature quantity. Subsequently, the information quantity value matching the feature quantity and its corresponding level is queried and read from the pre-calculated and stored "feature quantity-level-information quantity" mapping table. After traversing all feature quantities, a set of information quantity values ​​corresponding to each feature quantity for that grid cell is obtained.

[0090] This embodiment achieves rapid, batch conversion from target values ​​of raster cell feature quantities to information content. By utilizing pre-calculated mapping relationships, it avoids repeatedly performing complex statistical calculations for each cell, greatly improving data processing efficiency and ensuring feasibility and efficiency in practical applications.

[0091] In one feasible implementation, before S104, this embodiment of the application obtains a judgment matrix corresponding to multiple feature quantities, and determines the largest eigenvalue of the judgment matrix and the eigenvector corresponding to the largest eigenvalue; the judgment matrix is... Square array The number of characteristic quantities, A and b are positive integers greater than 1. The element value in the a-th row and b-th column of the matrix represents the importance scale value of the a-th feature relative to the b-th feature; a and b are both positive integers. The consistency ratio of the judgment matrix is ​​determined according to the following expression: (2) in, To determine the largest eigenvalue of a matrix, To determine the consistency ratio of the matrix, The average random consistency index is a pre-defined metric.

[0092] If the consistency ratio is less than or equal to the preset threshold, the feature vector is normalized, and the values ​​of each element in the normalized vector are used as the weight coefficients corresponding to multiple features.

[0093] If the consistency ratio is greater than the preset threshold, then each off-diagonal element in the judgment matrix is ​​subjected to quantitative perturbation processing to determine the change in the consistency ratio of the judgment matrix after perturbation processing, and the off-diagonal element whose change exceeds the preset change threshold is taken as the target element. Generate and send adjustment instructions for the target element to the user-side device, and update the judgment matrix in response to the adjustment operation performed by the user-side device based on the adjustment instructions for the target element, thereby obtaining a new judgment matrix; Repeat the step of determining the consistency ratio of the judgment matrix until the consistency ratio is less than or equal to the preset threshold.

[0094] For example, this embodiment uses the Analytic Hierarchy Process (AHP) to scientifically determine the weight coefficients of each feature quantity, and performs consistency checks and corrections, including: First, a judgment matrix is ​​constructed: Experts in the field of geological disaster monitoring assign corresponding weights to each feature quantity based on the relative importance of each feature quantity to the susceptibility of geological disasters along the pipeline, and construct a judgment matrix, as shown in Table 1. For example, if it is considered that "deformation rate" is significantly more important than "slope", then the corresponding element can be assigned a value of 5. The scale meanings are as follows: 1: both factors are equally important, 3: one factor is slightly more important than the other, 5: one factor is significantly more important than the other, 7: one factor is very important than the other, and 9: one factor is extremely important than the other.

[0095] Table 1 Judgment Matrix

[0096] After obtaining the judgment matrix, this embodiment calculates the largest eigenvalue of the judgment matrix and its corresponding eigenvector. The eigenvector is then normalized, and the resulting components are initially used as weight coefficients for each feature.

[0097] In one example, the weighting coefficients corresponding to Table 1 above are P=[0.06, 0.05, 0.03, 0.12, 0.18, 0.08, 0.12, 0.16, 0.20], and the corresponding features are, in order, slope, aspect, elevation, topographic relief, distance from road, lithology, surface cover type, distance from pipeline, and deformation rate.

[0098] The consistency ratio CR corresponding to the judgment matrix is ​​calculated according to expression 2, and the rationality of the judgment matrix is ​​judged and corrected based on the value of CR: if CR is less than or equal to a preset threshold, such as 0.1, the judgment matrix is ​​considered to have satisfactory consistency, and the weight coefficients calculated at the moment are accepted for subsequent weighting.

[0099] If the CR is greater than a preset threshold, it indicates that there is a logical inconsistency in the judgment matrix, which needs to be corrected. This embodiment can use a quantitative perturbation method: the values ​​of the off-diagonal elements in the judgment matrix are finely adjusted sequentially, and the change in the CR value ΔCR after each fine adjustment is observed. Elements that cause a significant decrease in ΔCR (exceeding the preset threshold) after a small adjustment are identified as "target elements," which are likely to be the main points of contention leading to inconsistency. The "target elements" and their corresponding feature quantity comparison relationships are sent to the user-side device, such as an expert, requesting the expert to review and adjust their importance judgment. After adjustment, the system updates the judgment matrix and re-executes the step of calculating the consistency ratio CR corresponding to the judgment matrix according to expression 2 until the CR meets the requirements.

[0100] In one example, based on the obtained weighting coefficients, the multiple information values ​​corresponding to each grid cell are weighted and processed, and the expression is as follows: (3) in, The weights of each evaluation factor.

[0101] This embodiment systematizes and quantifies expert experience using the Analytic Hierarchy Process (AHP) to determine the appropriate weights for each feature. It also introduces a consistency ratio check and correction mechanism to ensure the logical correctness of the judgment matrix and avoid weight distortion caused by contradictory judgments. This results in a final weighting system that both incorporates expert wisdom and conforms to mathematical logic, laying the foundation for the objectivity and reliability of subsequent weighted fusion results. This improves the accuracy and reliability of geological disaster monitoring.

[0102] In one example, the above-mentioned comprehensive state information is a comprehensive state value; S105 may include: The comprehensive state values ​​of each grid cell are sorted according to their numerical values ​​to obtain a numerical sequence. Based on the preset number of levels K, the numerical sequence is divided into K groups; K is a positive integer greater than 1.

[0103] With the goal of minimizing the sum of the within-group variances of K groups, the positions of K-1 hierarchical breakpoints in the numerical sequence are determined, and the comprehensive state value corresponding to the position is determined as the hierarchical threshold.

[0104] Based on the classification threshold, the comprehensive state value of each grid cell is classified into the corresponding geological hazard susceptibility level.

[0105] Based on the geological hazard susceptibility level corresponding to each grid cell, a geological hazard monitoring view is output.

[0106] In one example, Figure 20 This is a geological disaster monitoring view provided in an embodiment of this application, such as... Figure 20As shown, this embodiment divides the target area into five regions: extremely low susceptibility zone, low susceptibility zone, medium susceptibility zone, high susceptibility zone, and extremely high susceptibility zone.

[0107] For example, after obtaining the comprehensive state value of each grid cell, this embodiment sorts all the comprehensive state values ​​of the grid cells from largest to smallest (or from smallest to largest) to form a numerical sequence. The number of susceptibility levels to be divided is set to K (for example, K equals 5, including extremely low, low, medium, high, extremely high, etc.).

[0108] The natural breakpoint method is used to find the optimal classification. The goal is to find K. A single hierarchical breakpoint is used to minimize the sum of the within-group variances and maximize the between-group variances within the resulting K groups. This means making the overall state values ​​of units within the same level as similar as possible, while maximizing the differences between different levels. This K breakpoints are determined through iterative optimization. The position of a breakpoint in the sorted numerical sequence, and the corresponding comprehensive state value, is the grading threshold.

[0109] The natural breakpoint method for classification finds natural grouping boundaries based on the statistical distribution characteristics of the data itself, avoiding the subjectivity of artificially setting thresholds and making the classification results more objective and reasonable.

[0110] Then, using the determined grading thresholds, a susceptibility level is assigned to each grid cell. For example, if the threshold sequence is [T1,T2,T3,T4], then cells with a comprehensive state value > T1 are classified as "extremely high susceptibility zones", cells with T1 ≥ comprehensive state value > T2 are classified as "high susceptibility zones", and so on.

[0111] In one feasible implementation, this embodiment can also differentiate and render each raster cell according to its susceptibility level in a GIS platform (such as ArcGIS), for example, using colors ranging from green (very low susceptibility) to red (very high susceptibility). The final output is a geological hazard susceptibility monitoring view.

[0112] This embodiment transforms continuous comprehensive state values ​​into discrete geological hazard susceptibility levels with clear semantics, greatly improving the interpretability and practicality of the evaluation results. The final output geological hazard susceptibility monitoring view can transform complex numerical analysis results into a clear spatial view, greatly facilitating practical applications such as land and resources management, pipeline route planning, and disaster prevention and mitigation measures deployment.

[0113] In summary, this embodiment quantifies multi-dimensional information such as topography, geology, land cover, distance to key targets, and surface deformation into specific characteristic target values ​​by performing standardized grid cell analysis. Then, based on historical disaster data, it constructs an objective mapping relationship between the values ​​of each characteristic and the amount of information, transforming the raw data into quantitative indicators characterizing their correlation with disaster occurrence. Subsequently, the analytic hierarchy process (AHP) is used to determine the scientific weights of each characteristic, and the weights are coupled with the amount of information for weighted fusion to obtain the comprehensive state information of each grid cell, achieving a quantitative representation of the synergistic effect of multiple characteristics. Finally, based on the comprehensive state information, a visualized geological disaster monitoring view is generated, replacing traditional manual experience-based interpretation with objective and quantitative systematic analysis, significantly improving the accuracy, consistency, and efficiency of geological disaster susceptibility monitoring.

[0114] Figure 21 This is a schematic diagram of a geological disaster monitoring view generation device provided in an embodiment of this application. Figure 21 As shown, the geological disaster monitoring view generation device includes an acquisition unit 301, a first processing unit 302, a second processing unit 303, a determination unit 304, and an output unit 305.

[0115] The acquisition unit 301 is used to acquire digital elevation data, basic geographic information data, remote sensing image data and radar image data corresponding to the target area, which includes multiple raster units.

[0116] The first processing unit 302 is used to extract raster cell features based on digital elevation data, basic geographic information data, remote sensing image data and radar image data, and determine the target values ​​of multiple feature quantities corresponding to each raster cell in the target area; the multiple feature quantities include topographic parameters, stratigraphic lithology parameters, surface cover type parameters, distance parameters from the target object, and surface deformation parameters; the target objects include roads and pipelines.

[0117] The second processing unit 303 is used to determine the corresponding multiple information quantities for each grid cell based on the target values ​​of the multiple feature quantities corresponding to the grid cell, according to the mapping relationship between the preset values ​​of multiple feature quantities and information quantities; the information quantities are used to characterize the degree of correlation between the corresponding feature quantities and the occurrence of geological disasters.

[0118] The determining unit 304 is used to perform weighted processing on multiple information quantities corresponding to each grid cell according to the weight coefficients corresponding to multiple preset feature quantities, so as to obtain the comprehensive state information corresponding to each grid cell; the comprehensive state information is used to characterize the probability of geological disasters occurring in the grid cell.

[0119] Output unit 305 is used to output a geological disaster monitoring view corresponding to the target area based on the comprehensive status information of each grid cell.

[0120] In other embodiments, the topographic parameters include slope, aspect, elevation, and topographic relief; the surface deformation parameters include the surface deformation rate; prior to the second processing unit 303, the apparatus further includes a first preprocessing unit for: For each feature, perform the following steps to obtain the mapping relationship between the values ​​of multiple features and the amount of information: Obtain the grading criteria corresponding to the feature quantity, and determine multiple levels corresponding to the feature quantity based on the range of target values ​​of all grid cells in the target area and the grading criteria, and determine the total number of grid cells in each level; each level includes one or more values ​​of the feature quantity, and the values ​​of the feature quantity included in each level are different.

[0121] Based on the target value of each grid cell under the feature quantity, each grid cell is mapped and divided into the corresponding level.

[0122] Obtain historical geological disaster data corresponding to the target area, and based on the historical geological disaster data, determine the first number of surface deformation points included in the target area when the historical geological disaster occurred, and the second number of surface deformation points included in the grid unit within each level; the historical geological disaster data includes the location information of deformation points of various geological disasters.

[0123] For each level corresponding to a feature, the information content corresponding to each level is determined according to the following expression:

[0124] Where i represents the level. The amount of information corresponding to level i; The total number of grid cells of level i within the target area. This represents the second number of surface deformation points included in the raster cells within level i. The first number of surface deformation points included within the target area. This represents the total number of grid cells within the target area.

[0125] In other embodiments, prior to the determining unit 304, the apparatus further includes a second preprocessing unit for: Obtain the judgment matrix corresponding to multiple feature quantities, and determine the largest eigenvalue and the eigenvector corresponding to the largest eigenvalue of the judgment matrix; the judgment matrix is... Square array The number of characteristic quantities, A and b are positive integers greater than 1. The element value in the a-th row and b-th column of the judgment matrix represents the importance scale value of the a-th feature relative to the b-th feature; a and b are both positive integers.

[0126] The consistency ratio of the judgment matrix is ​​determined according to the following expression:

[0127] in, To determine the largest eigenvalue of a matrix, To determine the consistency ratio of the matrix, The average random consistency index is a pre-defined metric.

[0128] If the consistency ratio is less than or equal to the preset threshold, the feature vector is normalized, and the values ​​of each element in the normalized vector are used as the weight coefficients corresponding to multiple features.

[0129] In other embodiments, the apparatus further includes a third preprocessing unit for: If the consistency ratio is greater than a preset threshold, then a quantitative perturbation is performed on each off-diagonal element in the judgment matrix, the change in the consistency ratio of the corresponding judgment matrix after the perturbation is determined, and the off-diagonal element whose change exceeds the preset change threshold is taken as the target element.

[0130] Generate and send adjustment instructions for the target element to the user-side device, and update the judgment matrix in response to the adjustment operation performed by the user-side device based on the adjustment instructions for the target element, thus obtaining a new judgment matrix.

[0131] Repeat the step of determining the consistency ratio of the judgment matrix until the consistency ratio is less than or equal to the preset threshold.

[0132] In other embodiments, the comprehensive state information is a comprehensive state value; the output unit 305 is specifically used for: The comprehensive state values ​​of each grid cell are sorted according to their numerical values ​​to obtain a numerical sequence. Based on the preset number of levels K, the numerical sequence is divided into K groups; K is a positive integer greater than 1.

[0133] With the goal of minimizing the sum of the within-group variances of K groups, the positions of K-1 hierarchical breakpoints in the numerical sequence are determined, and the comprehensive state value corresponding to the position is determined as the hierarchical threshold.

[0134] Based on the classification threshold, the comprehensive state value of each grid cell is classified into the corresponding geological hazard susceptibility level.

[0135] Based on the geological hazard susceptibility level corresponding to each grid cell, a geological hazard monitoring view is output.

[0136] In other embodiments, the second processing unit 303 is specifically used for: For each grid cell within the target area, perform the following steps to determine multiple information quantities corresponding to each grid cell: For each of the multiple feature quantities, the corresponding level is determined based on the target value of the grid cell under the feature quantity.

[0137] From the mapping relationship, obtain the amount of information corresponding to the feature quantity and level.

[0138] In other embodiments, the first processing unit 302 is specifically used for: Based on digital elevation data, the slope, aspect, elevation, and topographic relief of each grid cell are determined through grid cell surface analysis.

[0139] Based on basic geographic information data, spatial queries and distance calculations are used to determine the distance values ​​from roads, pipelines, and strata lithology of each grid cell.

[0140] Based on remote sensing image data, the land cover type category value of each raster unit is determined through image classification processing.

[0141] Based on radar image data, the deformation rate value of each grid cell is determined through interferometric phase analysis and time-series calculation.

[0142] The geological disaster monitoring view generation device provided in this application embodiment can execute the method shown in the above method embodiment. Its implementation principle and beneficial effects can be referred to the relevant description in the method embodiment, and will not be repeated here.

[0143] Figure 22 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 22 As shown, the electronic device includes a memory 401 and at least one processor 402.

[0144] The memory 401 is used to store computer program code, which includes computer instructions. These computer instructions run in the aforementioned electronic device to implement the method shown in the above-described method embodiments. For example, the memory may include high-speed random access memory (RAM), and may also include non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, portable hard drive, read-only memory, disk, or optical disc, etc.

[0145] Processor 402 can be a general-purpose processor, including a Central Processing Unit (CPU), a network processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. Processor 402 can also be other general-purpose processors. The general-purpose processor can be a microprocessor or any conventional processor.

[0146] The memory 401 and processor 402 are communicatively connected. For example, the memory 401 can be connected to the processor 402 via a system bus and communicate with it. The system bus can be a peripheral component interconnect (PCI) bus, an extended industry standard architecture (EISA) bus, an industry standard architecture (ISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the figure, but this does not mean that there is only one bus or one type of bus.

[0147] Optionally, the memory 401 can be either standalone or integrated with the processor 402. When the memory 401 is set up independently, it is connected to the processor 402 via a system bus.

[0148] This application also provides a chip for executing instructions, which is used to execute the technical solution of the geological disaster monitoring view generation method in the above embodiments.

[0149] This application also provides a computer-readable storage medium storing computer instructions. When these computer instructions are executed by a processor, they are used to implement the technical solution of the geological disaster monitoring view generation method described in the above embodiments. Specifically, when the computer instructions are executed by a processor, the electronic device can execute the technical solution of the geological disaster monitoring view generation method described in the above embodiments.

[0150] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, it can implement the technical solution of the geological disaster monitoring view generation method in the above embodiments.

[0151] The aforementioned computer-readable storage media can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The computer-readable storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0152] An exemplary computer-readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the computer-readable storage medium can also be a component of the processor. The processor and the computer-readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the computer-readable storage medium can exist as discrete components in an electronic control unit or main control device; this application does not limit this.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0154] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0155] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0156] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application.

[0157] It should be understood that the steps of the method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0158] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0159] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for generating geological disaster monitoring views, characterized in that, The method includes: Acquire digital elevation data, basic geographic information data, remote sensing image data, and radar image data corresponding to the target area, wherein the target area includes multiple grid units; Based on the digital elevation data, basic geographic information data, remote sensing image data, and radar image data, raster unit features are extracted to determine the target values ​​of multiple feature quantities corresponding to each raster unit in the target area; the multiple feature quantities include topographic parameters, stratigraphic lithology parameters, surface cover type parameters, distance parameters from the target object, and surface deformation parameters; the target objects include roads and pipelines. Based on the preset mapping relationship between the values ​​of the multiple feature quantities and the information quantity, for each grid cell, based on the target values ​​of the multiple feature quantities corresponding to the grid cell, the corresponding multiple information quantities are determined; the information quantity is used to characterize the degree of correlation between the corresponding feature quantity and the occurrence of geological disasters; Based on the preset weight coefficients corresponding to the multiple feature quantities, the multiple information quantities corresponding to each grid cell are weighted to obtain the comprehensive state information corresponding to each grid cell; the comprehensive state information is used to characterize the probability of geological disasters occurring in the grid cell; Based on the comprehensive status information of each grid cell, a geological disaster monitoring view corresponding to the target area is output.

2. The method for generating geological disaster monitoring views according to claim 1, characterized in that, The topographic parameters include slope, aspect, elevation, and topographic relief; the surface deformation parameters include surface deformation rate. Before determining the corresponding multiple information quantities for each grid cell based on the target values ​​of the multiple feature quantities corresponding to the grid cell according to the preset mapping relationship between the values ​​of the multiple feature quantities and the information quantity, the method further includes: For each of the aforementioned features, the following steps are performed to obtain the mapping relationship between the values ​​of the multiple features and the amount of information: Obtain the grading criteria corresponding to the feature quantity, and determine multiple levels corresponding to the feature quantity based on the value range of the target value of the feature quantity and the grading criteria for all grid cells in the target area, and determine the total number of grid cells in each level; each level includes one or more values ​​of the feature quantity, and the values ​​of the feature quantity included in each level are different. Based on the target value of each grid cell under the aforementioned feature quantity, each grid cell is mapped and divided into corresponding levels; The system acquires historical geological disaster data corresponding to the target area, and based on the historical geological disaster data, determines the first number of surface deformation points included in the target area when the historical geological disaster occurred, and the second number of surface deformation points included in each grid cell within each level; the historical geological disaster data includes the location information of deformation points of various geological disasters. For each level corresponding to the aforementioned feature quantity, the information content corresponding to each level is determined according to the following expression: Where i represents the level. The amount of information corresponding to level i; The total number of grid cells of level i within the target area. This represents the second number of surface deformation points included in the raster cells within level i. The first number of surface deformation points included in the target area. This represents the total number of grid cells within the target area.

3. The method for generating geological disaster monitoring views according to claim 1, characterized in that, Before performing weighted processing on the multiple information quantities corresponding to each grid cell according to the preset weight coefficients corresponding to the multiple feature quantities to obtain the comprehensive state value corresponding to each grid cell, the method further includes: Obtain the judgment matrix corresponding to the plurality of feature quantities, and determine the largest eigenvalue of the judgment matrix and the eigenvector corresponding to the largest eigenvalue; the judgment matrix is... Square array The number of characteristic quantities, The value of the element in the a-th row and b-th column of the judgment matrix is ​​a positive integer greater than 1, representing the importance scale value of the a-th feature relative to the b-th feature; a and b are both positive integers. The consistency ratio of the judgment matrix is ​​determined according to the following expression: in, The largest eigenvalue of the judgment matrix is... The consistency ratio of the judgment matrix. The pre-defined average random consistency index; If the consistency ratio is less than or equal to a preset threshold, the feature vector is normalized, and each element value in the normalized vector is used as the weight coefficient corresponding to the multiple feature quantities.

4. The method for generating geological disaster monitoring views according to claim 3, characterized in that, The method further includes: If the consistency ratio is greater than the preset threshold, then a quantitative perturbation process is performed on each off-diagonal element in the judgment matrix that is in an off-diagonal position, the change in the consistency ratio of the judgment matrix after the perturbation process is determined, and the off-diagonal element whose change exceeds the preset change threshold is taken as the target element. An adjustment instruction for the target element is generated and sent to the user-side device, and in response to the adjustment operation for the target element performed by the user-side device according to the adjustment instruction, the judgment matrix is ​​updated to obtain a new judgment matrix; The step of determining the consistency ratio of the judgment matrix is ​​repeated until the consistency ratio is less than or equal to the preset threshold.

5. The method for generating geological disaster monitoring views according to claim 1, characterized in that, The comprehensive status information is a comprehensive status value; The geological hazard monitoring view corresponding to the target area is output based on the comprehensive status information of each grid cell, including: The comprehensive state values ​​of each grid cell are sorted according to their numerical values ​​to obtain a numerical sequence. Based on a preset number of levels K, the numerical sequence is divided into K groups; K is a positive integer greater than 1. With the goal of minimizing the sum of the within-group variances of the K groups, the positions of K-1 hierarchical breakpoints in the numerical sequence are determined, and the comprehensive state value corresponding to the position is determined as the hierarchical threshold. Based on the aforementioned grading threshold, the comprehensive state value of each grid cell is classified into the corresponding geological hazard susceptibility level. Based on the geological hazard susceptibility level corresponding to each grid cell, the geological hazard monitoring view is output.

6. The method for generating geological disaster monitoring views according to claim 2, characterized in that, The step of determining multiple information quantities for each grid cell based on the preset mapping relationship between the values ​​of the multiple feature quantities and the information quantity includes: For each grid cell within the target area, the following steps are performed to determine multiple information quantities corresponding to each grid cell: For each of the plurality of feature quantities, the corresponding level is determined based on the target value of the grid unit under the feature quantity; From the mapping relationship, obtain the amount of information corresponding to the feature quantity and the level.

7. The method for generating geological disaster monitoring views according to claim 2, characterized in that, The step of extracting raster unit features based on the digital elevation data, basic geographic information data, remote sensing image data, and radar image data to determine the target values ​​of multiple feature quantities corresponding to each raster unit in the target area includes: Based on the digital elevation data, the slope value, aspect value, elevation value and topographic relief value of each grid cell are determined through grid cell surface analysis. Based on the aforementioned basic geographic information data, the distance values ​​from the road, the distance values ​​from the pipeline, and the stratigraphic lithology values ​​of each grid cell are determined through spatial query and distance calculation. Based on the remote sensing image data, the land cover type category value of each grid cell is determined through image classification processing. Based on the radar image data, the deformation rate value of each grid cell is determined through interferometric phase analysis and time-series calculation.

8. A geological disaster monitoring view generation device, characterized in that, The device includes: The acquisition unit is used to acquire digital elevation data, basic geographic information data, remote sensing image data and radar image data corresponding to the target area, wherein the target area includes multiple grid units; The first processing unit is used to extract raster unit features based on the digital elevation data, basic geographic information data, remote sensing image data, and radar image data, and to determine the target values ​​of multiple feature quantities corresponding to each raster unit in the target area; the multiple feature quantities include topographic parameters, stratigraphic lithology parameters, surface cover type parameters, distance parameters from the target object, and surface deformation parameters; the target object includes roads and pipelines. The second processing unit is used to determine, for each grid cell, multiple information quantities corresponding to each grid cell based on the target values ​​of the multiple feature quantities corresponding to the grid cell, according to the preset mapping relationship between the values ​​of the multiple feature quantities and the information quantities; the information quantities are used to characterize the degree of correlation between the corresponding feature quantities and the occurrence of geological disasters. The determining unit is used to perform weighted processing on multiple information quantities corresponding to each grid cell according to the preset weight coefficients corresponding to the multiple feature quantities, so as to obtain the comprehensive state information corresponding to each grid cell; the comprehensive state information is used to characterize the probability of geological disasters occurring in the grid cell; The output unit is used to output a geological disaster monitoring view corresponding to the target area based on the comprehensive status information of each grid cell.

9. An electronic device, characterized in that, include: The device includes a memory and at least one processor; the memory is communicatively connected to the processor; the memory is used to store computer program code, the computer program code including computer instructions; when the processor executes the computer instructions, the electronic device performs the geological disaster monitoring view generation method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when executed by a processor, are used to implement the geological disaster monitoring view generation method as described in any one of claims 1-7.

Images