Geological disaster emergency visualization integration method and system based on Cesium

Abstract

The present invention discloses a geological disaster emergency visualization integration method and system based on Cesium, which relates to the field of image processing technology, including: collecting real-time multi-source geological disaster data in a geological disaster area, matching geological disaster prototypes with a geological disaster prototype library, and obtaining a target geological disaster prototype; displaying an interfering geological disaster area and a geological disaster area; obtaining a target disaster deduction model; performing time-series monitoring and analysis on the geological disaster area and the interfering geological disaster area, determining the time-series monitoring results of the geological disaster area and the time-series monitoring results of the interfering geological disaster area, performing deduction analysis, obtaining the target deduction analysis results, and visualizing and integrating them through the Cesium platform. The present invention solves the technical problem of insufficient integration capabilities of real-time geological disaster monitoring and dynamic deduction visualization of disaster evolution in the existing technology, and achieves the technical effect of realizing the integrated linkage of real-time perception, dynamic deduction, and three-dimensional visualization of geological disasters.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a Cesium-based geological disaster emergency visualization integration method and system. Background Art

[0002] In geological disaster monitoring and emergency response, ground sensors and remote sensing observations are commonly used to obtain monitoring data such as rainfall, surface displacement, pore water pressure, and seismic motion. However, due to the heterogeneity of data sources, untimely updates, and limited coverage, it is difficult to achieve continuous, real-time dynamic monitoring of geological disaster areas and interference areas. Disaster evolution analysis is often based on empirical formulas or single-factor driven models, and fails to fully integrate multi-source time series data for comprehensive deduction, resulting in insufficient accuracy and timeliness in disaster development trend predictions. In terms of visualization, disaster information is often displayed in the form of static map overlays, lacking real-time presentation and interactive analysis of dynamic processes such as the spatial expansion of disasters and changes in risk levels. The data between monitoring, deduction, and visualization links is fragmented, and information flow is delayed. This makes it impossible to form a complete closed loop of disaster perception, evolution deduction, and decision support, making it difficult to meet the application requirements of rapid response and efficient early warning of geological disasters. Summary of the Invention

[0003] This application provides a geological disaster emergency visualization integration method and system based on Cesium, which is used to solve the technical problem that the existing technology has insufficient visualization integration capabilities in real-time monitoring of geological disasters and dynamic deduction of disaster evolution.

[0004] In view of the above problems, this application provides a geological disaster emergency visualization integration method and system based on Cesium.

[0005] The first aspect of this application provides a geological disaster emergency visualization integration method based on Cesium, the method comprising:

[0006] Collect real-time multi-source geological hazard data in the geological hazard area, match the geological hazard prototype with the geological hazard prototype library, and obtain the target geological hazard prototype, wherein the target geological hazard prototype includes an interference bandwidth identifier; transmit the target geological hazard prototype, real-time multi-source geological hazard data and geological hazard area to the Cesium platform, and display the interfering geological hazard area and the geological hazard area in combination with the interference bandwidth identifier; match the target geological hazard prototype in the disaster deduction model library to obtain the target disaster deduction model; according to the target geological hazard influencing factor set corresponding to the target geological hazard prototype, conduct time-series monitoring and analysis on the geological hazard area and the interfering geological hazard area, and determine the time-series monitoring results of the geological hazard area and the time-series monitoring results of the interfering geological hazard area; use the target disaster deduction model to deduce and analyze the time-series monitoring results of the geological hazard area and the time-series monitoring results of the interfering geological hazard area to obtain the target deduction analysis results; and visualize and integrate the target deduction and analysis results through the Cesium platform.

[0007] The second aspect of this application provides a geological disaster emergency visualization integrated system based on Cesium, the system comprising:

[0008] The first matching module is used to collect real-time multi-source geological hazard data in the geological hazard area, match the geological hazard prototype with the geological hazard prototype library, and obtain the target geological hazard prototype, wherein the target geological hazard prototype includes an interference bandwidth identifier; the area display module is used to transmit the target geological hazard prototype, real-time multi-source geological hazard data and geological hazard area to the Cesium platform, and display the interfering geological hazard area and the geological hazard area in combination with the interference bandwidth identifier; the second matching module is used to match the target geological hazard prototype in the disaster deduction model library to obtain the target disaster deduction model; the time series monitoring and analysis module is used to perform time series monitoring and analysis on the geological hazard area and the interfering geological hazard area according to the target geological hazard influencing factor set corresponding to the target geological hazard prototype, and determine the time series monitoring results of the geological hazard area and the time series monitoring results of the interfering geological hazard area; the deduction and analysis module is used to use the target disaster deduction model to deduce and analyze the time series monitoring results of the geological hazard area and the time series monitoring results of the interfering geological hazard area to obtain the target deduction analysis results; the visualization integration display module is used to visualize and integrate the target deduction and analysis results through the Cesium platform.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application collects real-time multi-source geological hazard data in geological hazard areas, matches geological hazard prototypes with geological hazard prototype libraries, and obtains target geological hazard prototypes, wherein the target geological hazard prototypes include interference bandwidth identifiers; transmits the target geological hazard prototypes, real-time multi-source geological hazard data, and geological hazard areas to the Cesium platform, and displays the interfering geological hazard areas and geological hazard areas in combination with the interference bandwidth identifier; matches the target geological hazard prototypes in the disaster deduction model library to obtain a target disaster deduction model; according to the target geological hazard influencing factor set corresponding to the target geological hazard prototype, performs time-series monitoring and analysis on the geological hazard area and the interfering geological hazard area, and determines the time-series monitoring results of the geological hazard area and the time-series monitoring results of the interfering geological hazard area; uses the target disaster deduction model to deduce and analyze the time-series monitoring results of the geological hazard area and the time-series monitoring results of the interfering geological hazard area to obtain target deduction and analysis results; and visualizes and integrates the target deduction and analysis results through the Cesium platform. The present invention solves the technical problem of insufficient integration capability of existing technologies in real-time monitoring of geological disasters and dynamic deduction and visualization of disaster evolution. By collecting real-time multi-source geological disaster data, prototype matching, disaster deduction model deduction and analysis, and dynamically visualizing the integrated process on the Cesium platform, the present invention achieves the technical effect of realizing the integrated linkage of real-time perception of geological disasters, dynamic deduction and three-dimensional visualization. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of the Cesium-based integrated geological disaster emergency visualization method provided in the embodiment of this application;

[0013] Figure 2 Schematic diagram of the structure of the geological disaster emergency visualization integrated system based on Cesium provided in the embodiment of this application.

[0014] Explanation of the accompanying drawings: first matching module 11, area display module 12, second matching module 13, timing monitoring and analysis module 14, deduction and analysis module 15, visualization integrated display module 16. DETAILED DESCRIPTION

[0015] This application provides a geological disaster emergency visualization integration method and system based on Cesium, aiming to solve the technical problem of insufficient visualization integration capabilities of existing technologies in real-time geological disaster monitoring and dynamic deduction of disaster evolution. Through the integrated process of collecting real-time multi-source geological disaster data, prototype matching, disaster deduction model deduction and analysis, and dynamic visualization display on the Cesium platform, the application achieves the technical effect of realizing the integrated linkage of real-time geological disaster perception, dynamic deduction and three-dimensional visualization.

[0016] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0018] Example 1, as Figure 1 As shown, this application provides a geological disaster emergency visualization integration method based on Cesium, the method comprising:

[0019] Step S100: collecting real-time multi-source geological disaster data in the geological disaster area, matching the geological disaster prototype with the geological disaster prototype library, and obtaining the target geological disaster prototype, wherein the target geological disaster prototype includes an interference bandwidth identifier.

[0020] In this embodiment, real-time multi-source geohazard data is first collected from the geohazard area. This data is derived from multiple sources, including remote sensing, meteorological perception, hydrological observation, and earthquake detection, to form a comprehensive dataset reflecting the current state of the geohazard. This real-time data is then compared with a pre-built geohazard prototype library. This prototype library is formed by aggregating sample multi-source geohazard data sets and sample interference bandwidth sets through similar aggregation. Each prototype contains a set of baseline multi-source geohazard data and a corresponding interference bandwidth identifier.

[0021] During the matching phase, an approximate match is calculated between the real-time data and each benchmark data in the prototype library. The degree of closeness of each prototype to the real-time data is evaluated based on a predetermined similarity metric (e.g., Euclidean distance). Ultimately, the prototype with the highest degree of match is selected as the target geological hazard prototype for the current scenario, which includes an interference bandwidth identifier.

[0022] Furthermore, in the method provided in the embodiment of the application, real-time multi-source geological disaster data of the geological disaster area is collected, and geological disaster prototypes are matched with the geological disaster prototype library to obtain the target geological disaster prototype, which also includes:

[0023] A sample multi-source geological hazard data set and a corresponding sample interference bandwidth set are obtained, and geological hazard prototypes are constructed by performing similar aggregation on them to obtain a geological hazard prototype library, wherein each geological hazard prototype includes benchmark multi-source geological hazard data; the real-time multi-source geological hazard data are approximately matched with the benchmark multi-source geological hazard data of each geological hazard prototype in the geological hazard prototype library, and the geological hazard prototype corresponding to the benchmark multi-source geological hazard data with the highest matching degree is used as the target geological hazard prototype.

[0024] In this embodiment, we first collect a sample multi-source geological disaster data set and a corresponding sample interference bandwidth set from historical cases. This multi-source data includes topographic and geomorphological features, geotechnical structural parameters, historical landslide records, meteorological data (such as rainfall and rainfall intensity), seismic wave intensity, epicenter distance, and water level fluctuations. The interference bandwidth set reflects the width of the impact area of ​​each sample disaster event in spatial or temporal dimensions and is typically derived from post-disaster remote sensing mapping or 3D simulation data.

[0025] Next, M clustering points are randomly selected from the sample data set as representative centers. A K-means random initial center selection method is used here to ensure comprehensive and representative cluster centers, where M is a positive integer not less than 3. Based on the M selected points, a K-means homogeneous clustering analysis is then performed on the entire sample data set, clustering the data into M clusters. This yields M aggregated sample multi-source geological hazard data sets. The samples within each cluster represent a set of typical hazard characteristics. A mean shift analysis is then performed on each aggregated sample set to extract the distribution center of that class of samples as its representative representative, thereby obtaining M benchmark multi-source geological hazard data, the core data representation of each hazard prototype. After the benchmark data is determined, the interference bandwidth of the sample set within each aggregated cluster is mean-calculated to obtain M interference bandwidth values, representing the average disturbance range of that hazard in the spatial or temporal dimensions. Finally, each benchmark data set is combined with the corresponding interference bandwidth to form a geological hazard prototype containing the benchmark multi-source geological hazard data and the interference bandwidth identifier, thus constructing a complete geological hazard prototype library.

[0026] Next, real-time, multi-source geological hazard data for the target area is collected and matched against the baseline data for each geological hazard prototype in the prototype library using Euclidean distance similarity. The Euclidean distance between the real-time data and each prototype is calculated, with the closer the prototype, the smaller the distance. Ultimately, the prototype with the smallest Euclidean distance is selected as the target geological hazard prototype for the current scenario.

[0027] Furthermore, in the method provided in the embodiment of the application, a sample multi-source geological hazard data set and a corresponding sample interference bandwidth set are obtained, and similar data are aggregated to construct a geological hazard prototype to obtain a geological hazard prototype library, which also includes:

[0028] M aggregation punctuation points are randomly extracted from the sample multi-source geological hazard data set, where M is a positive integer greater than or equal to 3; the sample multi-source geological hazard data set is aggregated in the same category based on the M aggregation punctuation points to obtain M aggregated sample multi-source geological hazard data sets; mean shift analysis is performed on the M aggregated sample multi-source geological hazard data sets to determine M benchmark multi-source geological hazard data; interference bandwidth identification is performed on the M aggregated sample multi-source geological hazard data sets and the sample interference bandwidth set to determine M interference bandwidths; the M benchmark multi-source geological hazard data are identified using the M interference bandwidths to obtain the geological hazard prototype library.

[0029] In an embodiment of the present application, a uniform random sampling method is first used to randomly extract M aggregated punctuation points from a sample multi-source geological hazard data set, where M is a positive integer not less than 3.

[0030] Next, based on the above M aggregation points, the K-means clustering algorithm is performed on the entire sample data set. By calculating the Euclidean distance between each sample and the current aggregation center, the samples are assigned to the cluster represented by the nearest center. Finally, M aggregation sample multi-source geological disaster data sets are generated, each set representing a sample subset with similar disaster morphology.

[0031] Subsequently, the mean shift analysis method is used on the M aggregated sample multi-source geological hazard data sets. By iteratively searching for the maximum density point in the feature space, the internal feature center of the cluster is identified, thereby extracting the benchmark multi-source geological hazard data of each cluster and determining M benchmark multi-source geological hazard data.

[0032] Next, interference bandwidth identification is performed by combining the M aggregated sample multi-source geological hazard data sets and the sample interference bandwidth sets. Based on the correspondence between multi-source geological hazard data and interference bandwidth, the sample interference bandwidth sets are classified and aggregated according to the M aggregated sample multi-source geological hazard data sets, forming M aggregated sample interference bandwidth sets. A mean calculation is then performed on each set to extract the average disturbance range of that type of hazard in the historical samples, thereby obtaining M interference bandwidths.

[0033] Finally, the M interference bandwidths are structuredly combined with the corresponding M benchmark multi-source geological hazard data, and M complete geological hazard prototypes are constructed using the identification mapping method, and then summarized into a geological hazard prototype library.

[0034] Furthermore, in the method provided in the embodiment of the application, the interference bandwidth is identified by combining M aggregated sample multi-source geological hazard data sets and sample interference bandwidth sets to determine M interference bandwidths, and further includes:

[0035] According to the one-to-one correspondence between multi-source geological hazard data and interference bandwidth, the sample interference bandwidth set is aggregated in combination with the determination of M aggregated sample multi-source geological hazard data sets to obtain M aggregated sample interference bandwidth sets; the mean of the M aggregated sample interference bandwidth sets is calculated to obtain M interference bandwidths.

[0036] Furthermore, the method provided in the application embodiment also includes:

[0037] The similarity between any two aggregated punctuation points in the M aggregated punctuation points is less than or equal to a preset similarity threshold.

[0038] In the embodiment of the present application, first, based on the M aggregated sample multi-source geological disaster data sets obtained by the previous K-means clustering, combined with the one-to-one correspondence between multi-source data and interference bandwidth, a label index mapping algorithm is used to classify and organize the interference bandwidth sets of the original samples. Specifically, the cluster label to which each multi-source geological disaster sample data belongs in the cluster is used as an index, and its corresponding interference bandwidth value is assigned to the same aggregation category, thereby forming M aggregated sample interference bandwidth sets, each set corresponding to a type of disaster morphology interference feature data group, such as landslide collapse range, debris flow lateral impact width, etc.

[0039] After aggregation, the arithmetic mean statistical method is applied to each interference bandwidth set to calculate the average of all bandwidth values ​​in the set, resulting in M ​​interference bandwidths. These average bandwidth values ​​represent the typical disturbance range exhibited by various disasters in historical samples and serve as interference bandwidth identifiers for subsequent descriptions of the prototype spatial impact range and boundary control of the visualization model.

[0040] At the same time, in order to ensure that the extracted M aggregated punctuation points have sufficient discriminability, the cosine similarity measurement strategy is adopted in the punctuation point selection stage, and a preset similarity threshold is set (for example, not higher than 0.8). Only point pairs with a similarity less than or equal to the threshold are retained to avoid prototype overlap caused by cluster centers being too close, thereby ensuring the independence and reliability of the disaster prototype library in subsequent deduction and analysis.

[0041] Step S200: The target geological disaster prototype, real-time multi-source geological disaster data and geological disaster area are transmitted to the Cesium platform, and the interference geological disaster area and geological disaster area are displayed in combination with the interference bandwidth identifier.

[0042] In an embodiment of the present application, the target geological hazard prototype, real-time multi-source geological hazard data, and geological hazard area are transmitted to the Cesium platform. First, a preset display template is called based on the prototype type, and then a format conversion algorithm is used to convert the original monitoring data into the Cesium object format to ensure that it can be rendered on the platform. During the visualization process, the interference bandwidth identifier in the target prototype is used, and a spatial buffer expansion method is used to display the core geological hazard area and the disturbed geological hazard area affected by the disturbance on the Cesium platform, respectively, to achieve a layered visualization of the main hazard area and the extended impact area.

[0043] Furthermore, in the method provided in the embodiment of the application, the target geological hazard prototype, real-time multi-source geological hazard data and geological hazard area are transmitted to the Cesium platform, and the interference geological hazard area and the geological hazard area are displayed in combination with the interference bandwidth identifier, which also includes:

[0044] The display template of the Cesium platform is called based on the target geological disaster prototype; the format of the real-time multi-source geological disaster data is converted to obtain the converted real-time multi-source geological disaster data in the object format of Cesium; based on the display template, the geological disaster area is displayed in the Cesium platform according to the converted real-time multi-source geological disaster data, and the interference geological disaster area determined based on the interference bandwidth identifier is displayed.

[0045] In this embodiment of the present application, the Cesium platform's display template is first called based on the target geological disaster prototype. This display template is a predefined disaster type mapping configuration file that contains the three-dimensional symbolic representation, layer styles, coloring rules, and label binding logic of different geological disaster categories such as landslides, debris flows, surges, and earthquakes in the Cesium platform. This is used to uniformly control the presentation of different disaster events in the visualization environment. Based on the disaster type field recorded in the target geological disaster prototype, the matching display template content is loaded through the template indexing mechanism to ensure that the disaster display conforms to its physical characteristics and spatial expression.

[0046] The real-time multi-source geological hazard data collected within the geological hazard area was then processed and restructured. Using the GeoJSON-to-Cesium Entity structure conversion method, the original multi-source data, including latitude and longitude coordinates, elevation information, rainfall, surface deformation, and magnitude parameters, was converted into a Cesium-compliant object format. This format, CZML or Entity JSON, supports the Cesium platform, meeting its technical requirements for 3D rendering, timeline control, and data interaction. The converted data retains all spatial features and attribute information and can be directly used for geospatial loading and layer binding.

[0047] After completing the data conversion, the geological disaster area is displayed in the Cesium platform based on the converted real-time multi-source geological disaster data based on the display template. Specifically, by calling the layer rendering interface of the Cesium platform, the geological disaster area is superimposed on the three-dimensional map in the form of a surface entity or dynamic boundary, and the label visualization is performed with the disaster intensity value, timestamp and other attributes to achieve real-time visual expression of the status of the geological disaster area.

[0048] At the same time, the interference bandwidth identifier in the target geological disaster prototype is parsed, and the buffer generation algorithm is used to automatically generate a spatial extension layer outside the boundary of the geological disaster area. The interference geological disaster area determined based on the interference bandwidth identifier is displayed. This area is rendered in a semi-transparent style or dotted boundary to indicate the extended impact area that the current disaster may affect, thereby assisting users in intuitively identifying the relationship between the disaster entity and the potential interference range in the Cesium platform.

[0049] Step S300: Matching the target geological disaster prototype in the disaster deduction model library to obtain a target disaster deduction model.

[0050] In this embodiment, a target hazard simulation model is first obtained by matching the target hazard prototype against a hazard simulation model library. Specifically, the benchmark multi-source hazard data contained in the target hazard prototype is first extracted as a standardized feature set for the current hazard scenario. The benchmark multi-source hazard data includes key parameters such as terrain slope, geological type, soil moisture content, accumulated rainfall, and earthquake intensity.

[0051] Next, we used a feature vector construction method to standardize the baseline multi-source geological hazard data into feature vectors of uniform scale. The uniform format facilitates direct matching with the model template. The dimensions of each feature vector correspond to key environmental or physical parameters required for hazard evolution, such as slope, rainfall rate, and earthquake magnitude.

[0052] The constructed baseline feature vectors were then compared with the input feature templates of each pre-set model in the disaster simulation model library using a feature vector similarity matching method, using cosine similarity as the similarity metric. Each model has a preset feature template when it is created, describing the disaster type, characteristic conditions, and triggering mechanism range for the model.

[0053] By calculating similarity scores, we screened out models that most closely matched the characteristics of the current benchmark multi-source geological hazard data. To ensure the optimal adaptability of the selected deduction models in practical applications, we used a similarity threshold screening method. Only models with a cosine similarity score above a preset threshold (e.g., 0.85) were considered candidates.

[0054] Finally, among all the candidate models that meet the similarity requirements, the best matching deduction model is directly determined according to the highest similarity score as the target disaster deduction model under the current disaster scenario.

[0055] Furthermore, the method provided in the application embodiment also includes:

[0056] The disaster simulation model library includes a landslide-surge intelligent simulation model, an earthquake-rainfall-landslide intelligent simulation model, an earthquake-rainfall-mudslide intelligent simulation model, and a dam breach intelligent simulation model.

[0057] In an embodiment of the present application, the disaster simulation model library includes a landslide-surge intelligent simulation model, an earthquake-rainfall-landslide intelligent simulation model, an earthquake-rainfall-mudslide intelligent simulation model, and a dam breach intelligent simulation model.

[0058] The intelligent landslide-surge model is trained using historical data on landslide-into-water events, including physical parameters such as landslide volume, landslide entry velocity, entry angle, and water depth. This data is derived from field geological surveys and post-disaster monitoring records. The training method utilizes numerical simulation of shallow water equations, solving for changes in water motion under the influence of landslide entry to establish a dynamic model of the surge-induced landslide entry. The input data are landslide volume, entry velocity, and water depth, and the output data are the maximum surge height, wave propagation velocity, and surge diffusion path.

[0059] The earthquake-rainfall-landslide intelligent prediction model is trained using data from historical earthquakes and heavy rainfall-induced landslides. This data includes environmental and geological information such as magnitude, epicenter distance, surface rainfall, rainfall duration, terrain slope, and rock and soil types. This data is sourced from seismic networks, meteorological stations, and geological surveys. The training method uses a support vector machine (SVM) classification method to establish classification boundaries between earthquakes, rainfall, and landslide occurrence. The input data includes magnitude, rainfall, slope, and rock and soil types, and the output data includes the probability of landslide occurrence, the boundaries of the potential landslide area, and the initial sliding direction.

[0060] The earthquake-rainfall-debris flow intelligent prediction model uses data from historical earthquake and rainfall debris flow events, including information on the distribution of geological fracture zones, rainfall accumulation, watershed slope, soil moisture content, and earthquake intensity. This data is derived from geological hazard surveys and meteorological and hydrological monitoring data. The training method uses a numerical simulation method for debris flow dynamics, simulating the evolution of debris flows by calculating the material initiation, flow, and accumulation processes. The input data includes the location of the geological fracture zone, rainfall, slope, and soil moisture content, and the output data includes the debris flow trajectory, velocity changes, and the accumulation area.

[0061] The establishment of the disaster simulation model library is completed through this training data standard, the use of a single method at each step, and the clear correspondence between input and output.

[0062] Furthermore, the method provided in the application embodiment also includes:

[0063] Water level, rainfall, earthquake data and dam monitoring data were collected multiple times in a synchronous manner to obtain a sample dam stability monitoring data set and a corresponding dam failure risk data set; a gridless numerical simulation method was used to construct a dam failure intelligent deduction model based on the sample dam stability monitoring data set and the dam failure risk data set.

[0064] In this embodiment, a time-synchronized data acquisition method is first employed. An automated monitoring system, including water level gauges, rain gauges, seismic accelerometers, displacement meters, piezometers, and strain gauges, is deployed on the dam body to collect water level, rainfall, seismic parameters, and structural response data from within and on the dam body at multiple times and simultaneously. High-frequency, periodic, synchronized sampling ensures that all data points have a uniform timestamp, forming a well-structured time series sample and constructing a sample dam stability monitoring data set.

[0065] Then, through manual labeling and combined with existing records of dam failures or dangerous situations, we analyzed historical monitoring data for operating condition segments that were highly relevant to the actual failure process. We manually screened and labeled risk levels based on key indicators (such as sudden strain changes and sharp increases in pore water pressure), constructing a dam failure risk data set. This set serves as the output label for supervised learning, providing a reference for real-world conditions in model training.

[0066] During model construction, a meshless numerical simulation method, specifically smoothed particle hydrodynamics (SPH), was used to discretize the dam structure into multiple particle units. The stress-strain evolution relationship between the particles was calculated based on physical rules. In the simulation, a sample dam stability monitoring data set was used as the simulation input boundary condition. Water pressure, seismic acceleration, and seepage loads at different time points were applied to simulate the dynamic response behavior of the particle swarm and reconstruct the structural evolution of the dam under multi-source disturbances.

[0067] Subsequently, supervised learning training methods were used to compare the structural response results (such as local displacements, principal strains, and critical slip zone extents) generated by numerical simulations with the aforementioned dam failure risk data set to construct an input-output mapping. During the training process, a fixed loss function was used to evaluate errors, gradually updating the physical parameters and material response control values ​​in the simulation model, thereby enabling the model to identify and predict failure risks.

[0068] After the training was finally completed, an intelligent dam collapse simulation model was constructed, which can perform rapid response simulation and collapse risk assessment driven by new monitoring data.

[0069] Step S400: According to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, the geological disaster area and the interfering geological disaster area are subjected to time series monitoring and analysis to determine the geological disaster area time series monitoring results and the interfering geological disaster area time series monitoring results.

[0070] In this embodiment, according to the target geological hazard influencing factor set corresponding to the target geological hazard prototype, time series monitoring and analysis are performed on the geological hazard area and the interfering geological hazard area within a preset monitoring window, and the corresponding influencing factor set sequence is collected and generated. Subsequently, fluctuation variance analysis is performed on the influencing factor set sequence of these two types of areas, and the fluctuation coefficient of the geological hazard area and the fluctuation coefficient of the interfering geological hazard area are calculated respectively. The convolution scale of each is determined based on the fluctuation characteristics.

[0071] On this basis, convolution analysis is further performed on the two types of sequences to extract the change trends and disturbance patterns from the multi-scale time characteristics, and finally the time series monitoring results of geological disaster areas and the time series monitoring results of interfering geological disaster areas are obtained.

[0072] Furthermore, in the method provided in the embodiment of the application, according to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, the geological disaster area and the interfering geological disaster area are subjected to time series monitoring and analysis, and the geological disaster area time series monitoring results and the interfering geological disaster area time series monitoring results are determined, which also includes:

[0073] According to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, the geological disaster area and the interfering geological disaster area are subjected to time series monitoring and analysis within a preset monitoring window to obtain a set sequence of geological disaster area influencing factors and a set sequence of interfering geological disaster area influencing factors; a fluctuation variance analysis is performed on the set sequence of geological disaster area influencing factors and the set sequence of interfering geological disaster area influencing factors to determine the geological disaster area fluctuation coefficient and the interfering geological disaster area fluctuation coefficient; the convolution scale is determined according to the geological disaster area fluctuation coefficient and the interfering geological disaster area fluctuation coefficient, and a convolution analysis is performed on the set sequence of geological disaster area influencing factors and the set sequence of interfering geological disaster area influencing factors to obtain the geological disaster area time series monitoring results and the interfering geological disaster area time series monitoring results.

[0074] In the embodiment of the present application, a data collection method based on the characteristic mapping of the target geological hazard prototype is first adopted. According to the target geological hazard influencing factor set corresponding to the target geological hazard prototype, continuous high-frequency time series data collection is performed for the geological hazard area and the interfering geological hazard area respectively within the preset monitoring window. The influencing factor set is preset according to the hazard prototype. For example, the landslide prototype collects rainfall, pore water pressure and surface displacement data, and the debris flow prototype collects cumulative rainfall, runoff and slope change rate. By deploying automated monitoring sensors, remote sensing observations and ground station data fusion, a complete and continuous set sequence of geological hazard area influencing factors and a set sequence of interfering geological hazard area influencing factors are formed under a unified time axis.

[0075] After data collection is complete, a sliding time window fluctuation variance calculation method is used to extract short-term fluctuation characteristics for the set of factors affecting the geohazard region and the set of factors affecting the interfering geohazard region. The specific process involves setting a sliding window of fixed length (e.g., 24 hours). Within each sliding window, the mean of the sampled data is first calculated. Based on the mean, the sum of squared deviations of each sampling point from the mean is then calculated to obtain the variance within the window, completing the variance sequence extraction. This method obtains the local fluctuation amplitude of each influencing factor within each monitoring window, providing a quantitative description of the dynamic level within the region. After obtaining the local fluctuation variance of each influencing factor, a weighted synthesis method based on preset weights is used to determine the fluctuation coefficients for the geohazard region and the interfering geohazard region. During the initialization phase, a corresponding weight is preset for each influencing factor corresponding to each hazard prototype. For example, in the landslide prototype, the weight for pore water pressure is set to 0.5, the weight for rainfall is set to 0.3, and the weight for surface displacement is set to 0.2. These weights are fixed and match the hazard mechanism. Then, for the geological hazard area, a weighted summation method is used to multiply the variance values ​​of each influencing factor by the corresponding weight and then sum them up to finally determine the geological hazard area fluctuation coefficient. Simultaneously, the same method is used to perform weighted summation on the variance series of the influencing factors of the interference geological hazard area to determine the interference geological hazard area fluctuation coefficient.

[0076] After determining the fluctuation coefficients of the geological hazard area and the interference geological hazard area, a fluctuation amplitude-driven adaptive convolution scale setting method is used to set the convolution processing scale according to the fluctuation intensity of different areas. The setting standard is that when the fluctuation coefficient is greater than 15, the convolution scale is set to 3 hours to capture rapid and drastic changes; when the fluctuation coefficient is between 8 and 15, the convolution scale is set to 6 hours to adapt to the medium-speed evolution process; when the fluctuation coefficient is less than 8, the convolution scale is set to 12 hours to highlight the chronic change trend. For example, the fluctuation coefficient of the geological hazard area is 19.1, which is a high fluctuation level, so the convolution scale is set to 3 hours, while the fluctuation coefficient of the interference geological hazard area is 7.5, which is a low fluctuation level, so the convolution scale is set to 12 hours, realizing adaptive scale adjustment based on the frequency of change.

[0077] After the convolution scale is set, a multi-scale convolution feature extraction method is used to perform convolution analysis on the set of influencing factors in the geological hazard area and the set of influencing factors in the interfering geological hazard area. Based on the set convolution scale, a local sliding weighted calculation is applied to perform local smoothing and trend enhancement of the time series data. Through the convolution operation, important disaster evolution characteristics such as short-term sudden increases in pore water pressure, sharp increases in rainfall intensity, and displacement acceleration stages are extracted, and random noise interference is filtered out. In the geological hazard area with a convolution scale of 3 hours, the process of a sharp increase in pore pressure within 24 hours is captured, while in the interfering geological hazard area with a convolution scale of 12 hours, the trend of chronic displacement growth is highlighted. Finally, the time series monitoring results of the geological hazard area and the interfering geological hazard area are obtained.

[0078] Step S500: Utilizing the target disaster deduction model, the time series monitoring results of the geological disaster area and the time series monitoring results of the interfering geological disaster area are deduced and analyzed to obtain target deduction and analysis results.

[0079] In an embodiment of the present application, after obtaining the time-series monitoring results of the geological disaster area and the time-series monitoring results of the interfering geological disaster area, the target disaster deduction model is used to deduce and analyze the time-series monitoring results of the geological disaster area and the time-series monitoring results of the interfering geological disaster area to obtain a dynamic prediction of the development of the disaster.

[0080] Specifically, a target disaster simulation model matching the current hazard prototype is first invoked. This model internally defines the physical mechanisms or data-driven evolutionary paths of the hazard's evolution, ensuring that the simulation conforms to the hazard's causal logic. During the simulation analysis phase, a standardized input feature approach is employed to uniformly map the core influencing factors (such as rainfall intensity changes, pore water pressure evolution, and surface displacement trends) from the time-series monitoring results of the geological hazard region and the interfering geological hazard region into the standard input format required by the simulation model. After input standardization, a dynamic evolutionary process simulation method is used to recursively project the changing trends of these influencing factors over future time periods and simulate the dynamic response of the primary hazard region and the interfering geological hazard region over time. During the simulation, the geological hazard region serves as the primary impact zone, with its input features dominating the core hazard development trend. The interfering geological hazard region serves as the secondary response zone, reflecting the surrounding disaster transmission effects. Through coupled simulation, the overall hazard evolution trajectory is formed. Finally, through this simulation process, the target simulation analysis results are output, which comprehensively depict the future hazard evolution trend and expansion range.

[0081] Step S600: Visually integrate and display the target deduction and analysis results through the Cesium platform.

[0082] In an embodiment of the present application, after obtaining the target deduction and analysis results, the target deduction and analysis results are visualized and integrated and displayed through the Cesium platform. Specifically, the target deduction and analysis results are first converted into a format, and data such as disaster evolution trends, spatial expansion boundaries, and risk level changes are standardized into visualization formats supported by the Cesium platform, such as GeoJSON format, CZML format, or 3D Tiles format. Subsequently, the corresponding visualization interface is called on the Cesium platform, and a three-dimensional visualization entity of the geological disaster area is created based on the spatial position information and time change information in the deduction and analysis results. Different colors, transparencies, or dynamic animation effects are used to distinguish different stages of disaster evolution. At the same time, driven by the timeline control, the expansion process of the geological disaster area evolving over time is dynamically displayed. Finally, a spatial, dynamic, and interactive integrated display of the target deduction and analysis results is achieved on the Cesium platform.

[0083] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0084] This application collects real-time multi-source geological hazard data in geological hazard areas, matches geological hazard prototypes with geological hazard prototype libraries, and obtains target geological hazard prototypes, wherein the target geological hazard prototypes include interference bandwidth identifiers; transmits the target geological hazard prototypes, real-time multi-source geological hazard data, and geological hazard areas to the Cesium platform, and displays the interfering geological hazard areas and geological hazard areas in combination with the interference bandwidth identifier; matches the target geological hazard prototypes in the disaster deduction model library to obtain a target disaster deduction model; according to the target geological hazard influencing factor set corresponding to the target geological hazard prototype, performs time-series monitoring and analysis on the geological hazard area and the interfering geological hazard area, and determines the time-series monitoring results of the geological hazard area and the time-series monitoring results of the interfering geological hazard area; uses the target disaster deduction model to deduce and analyze the time-series monitoring results of the geological hazard area and the time-series monitoring results of the interfering geological hazard area to obtain target deduction and analysis results; and visualizes and integrates the target deduction and analysis results through the Cesium platform. The present invention solves the technical problem of insufficient integration capability of existing technologies in real-time monitoring of geological disasters and dynamic deduction and visualization of disaster evolution. By collecting real-time multi-source geological disaster data, prototype matching, disaster deduction model deduction and analysis, and dynamically visualizing the integrated process on the Cesium platform, the present invention achieves the technical effect of realizing the integrated linkage of real-time perception of geological disasters, dynamic deduction and three-dimensional visualization.

[0085] Example 2 is based on the same inventive concept as the geological disaster emergency visualization integration method based on Cesium in the previous embodiment. Figure 2As shown, this application provides a geological disaster emergency visualization integrated system based on Cesium. The system and method embodiments in the embodiments of this application are based on the same inventive concept. Among them, the system includes:

[0086] The first matching module 11 is used to collect real-time multi-source geological hazard data in the geological hazard area, match the geological hazard prototype with the geological hazard prototype library, and obtain the target geological hazard prototype, wherein the target geological hazard prototype includes an interference bandwidth identifier; the area display module 12 is used to transmit the target geological hazard prototype, real-time multi-source geological hazard data and geological hazard area to the Cesium platform, and display the interference geological hazard area and the geological hazard area in combination with the interference bandwidth identifier; the second matching module 13 is used to match the target geological hazard prototype in the disaster deduction model library to obtain the target disaster deduction model; The time series monitoring and analysis module 14 is used to perform time series monitoring and analysis on the geological disaster area and the interfering geological disaster area according to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, and determine the time series monitoring results of the geological disaster area and the time series monitoring results of the interfering geological disaster area; the deduction and analysis module 15 is used to use the target disaster deduction model to perform deduction and analysis on the time series monitoring results of the geological disaster area and the time series monitoring results of the interfering geological disaster area to obtain the target deduction and analysis results; the visualization integration display module 16 is used to perform visualization and integration display of the target deduction and analysis results through the Cesium platform.

[0087] Furthermore, the system is also used to implement the following functions:

[0088] A sample multi-source geological hazard data set and a corresponding sample interference bandwidth set are obtained, and geological hazard prototypes are constructed by performing similar aggregation on them to obtain a geological hazard prototype library, wherein each geological hazard prototype includes benchmark multi-source geological hazard data; the real-time multi-source geological hazard data are approximately matched with the benchmark multi-source geological hazard data of each geological hazard prototype in the geological hazard prototype library, and the geological hazard prototype corresponding to the benchmark multi-source geological hazard data with the highest matching degree is used as the target geological hazard prototype.

[0089] Furthermore, the system is also used to implement the following functions:

[0090] M aggregation punctuation points are randomly extracted from the sample multi-source geological hazard data set, where M is a positive integer greater than or equal to 3; the sample multi-source geological hazard data set is aggregated in the same category based on the M aggregation punctuation points to obtain M aggregated sample multi-source geological hazard data sets; mean shift analysis is performed on the M aggregated sample multi-source geological hazard data sets to determine M benchmark multi-source geological hazard data; interference bandwidth identification is performed on the M aggregated sample multi-source geological hazard data sets and the sample interference bandwidth set to determine M interference bandwidths; the M benchmark multi-source geological hazard data are identified using the M interference bandwidths to obtain the geological hazard prototype library.

[0091] Furthermore, the system is also used to implement the following functions:

[0092] According to the one-to-one correspondence between multi-source geological hazard data and interference bandwidth, the sample interference bandwidth set is aggregated in combination with the determination of M aggregated sample multi-source geological hazard data sets to obtain M aggregated sample interference bandwidth sets; the mean of the M aggregated sample interference bandwidth sets is calculated to obtain M interference bandwidths.

[0093] Furthermore, the system is also used to implement the following functions:

[0094] The similarity between any two aggregated punctuation points in the M aggregated punctuation points is less than or equal to a preset similarity threshold.

[0095] Furthermore, the system is also used to implement the following functions:

[0096] According to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, the geological disaster area and the interfering geological disaster area are subjected to time series monitoring and analysis within a preset monitoring window to obtain a set sequence of geological disaster area influencing factors and a set sequence of interfering geological disaster area influencing factors; a fluctuation variance analysis is performed on the set sequence of geological disaster area influencing factors and the set sequence of interfering geological disaster area influencing factors to determine the geological disaster area fluctuation coefficient and the interfering geological disaster area fluctuation coefficient; the convolution scale is determined according to the geological disaster area fluctuation coefficient and the interfering geological disaster area fluctuation coefficient, and a convolution analysis is performed on the set sequence of geological disaster area influencing factors and the set sequence of interfering geological disaster area influencing factors to obtain the geological disaster area time series monitoring results and the interfering geological disaster area time series monitoring results.

[0097] Furthermore, the system is also used to implement the following functions:

[0098] The disaster simulation model library includes a landslide-surge intelligent simulation model, an earthquake-rainfall-landslide intelligent simulation model, an earthquake-rainfall-mudslide intelligent simulation model, and a dam breach intelligent simulation model.

[0099] Furthermore, the system is also used to implement the following functions:

[0100] Water level, rainfall, earthquake data and dam monitoring data were collected multiple times in a synchronous manner to obtain a sample dam stability monitoring data set and a corresponding dam failure risk data set; a gridless numerical simulation method was used to construct a dam failure intelligent deduction model based on the sample dam stability monitoring data set and the dam failure risk data set.

[0101] Furthermore, the system is also used to implement the following functions:

[0102] The display template of the Cesium platform is called based on the target geological disaster prototype; the format of the real-time multi-source geological disaster data is converted to obtain the converted real-time multi-source geological disaster data in the object format of Cesium; based on the display template, the geological disaster area is displayed in the Cesium platform according to the converted real-time multi-source geological disaster data, and the interference geological disaster area determined based on the interference bandwidth identifier is displayed.

[0103] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0104] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0105] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. The geological disaster emergency visualization integration method based on Cesium is characterized by: The method comprises: Collecting real-time multi-source geological disaster data in the geological disaster area, matching the geological disaster prototype with the geological disaster prototype library, and obtaining the target geological disaster prototype, wherein the target geological disaster prototype includes an interference bandwidth identifier; The target geological hazard prototype, real-time multi-source geological hazard data and geological hazard area are transmitted to the Cesium platform, and the interference geological hazard area and geological hazard area are displayed in combination with the interference bandwidth identifier; Matching the target geological disaster prototype in the disaster deduction model library to obtain a target disaster deduction model; According to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, the geological disaster area and the interfering geological disaster area are subjected to time series monitoring and analysis to determine the geological disaster area time series monitoring results and the interfering geological disaster area time series monitoring results; Using the target disaster deduction model, the time series monitoring results of the geological disaster area and the time series monitoring results of the interfering geological disaster area are deduced and analyzed to obtain target deduction analysis results; Visually integrate and display the target deduction and analysis results through the Cesium platform; Collect real-time multi-source geological hazard data in geological hazard areas, match geological hazard prototypes with the geological hazard prototype database, and obtain target geological hazard prototypes, including: Obtain a sample multi-source geological hazard data set and a corresponding sample interference bandwidth set, aggregate the data into similar types to construct a geological hazard prototype, and obtain a geological hazard prototype library, wherein each geological hazard prototype includes benchmark multi-source geological hazard data; The real-time multi-source geological hazard data are approximately matched with the benchmark multi-source geological hazard data of each geological hazard prototype in the geological hazard prototype library, and the geological hazard prototype corresponding to the benchmark multi-source geological hazard data with the highest matching degree is used as the target geological hazard prototype.

2. The geological disaster emergency visualization integration method based on Cesium according to claim 1 is characterized in that: Obtain a sample multi-source geological hazard data set and a corresponding sample interference bandwidth set, aggregate the same type of data to construct a geological hazard prototype, and obtain a geological hazard prototype library, including: Randomly extract M aggregated punctuation points from the sample multi-source geological hazard data set, where M is a positive integer greater than or equal to 3; Performing similar aggregation on the sample multi-source geological hazard data set based on the M aggregation punctuation points to obtain M aggregated sample multi-source geological hazard data sets; Performing mean shift analysis on the M aggregated sample multi-source geological hazard data sets to determine M benchmark multi-source geological hazard data; Interference bandwidth identification is performed by combining M aggregated sample multi-source geological hazard data sets and sample interference bandwidth sets to determine M interference bandwidths; The M reference multi-source geological disaster data are identified using the M interference bandwidths to obtain the geological disaster prototype library.

3. The geological disaster emergency visualization integration method based on Cesium according to claim 2 is characterized in that: Interference bandwidth identification is performed by combining M aggregated sample multi-source geological hazard data sets and sample interference bandwidth sets to determine M interference bandwidths, including: According to the one-to-one correspondence between multi-source geological hazard data and interference bandwidth, the sample interference bandwidth set is aggregated in combination with the determined M aggregated sample multi-source geological hazard data set to obtain M aggregated sample interference bandwidth sets; Mean calculation is performed on the M aggregated sample interference bandwidth sets to obtain M interference bandwidths.

4. The geological disaster emergency visualization integration method based on Cesium according to claim 2, characterized in that: The similarity between any two aggregated punctuation points in the M aggregated punctuation points is less than or equal to a preset similarity threshold.

5. The geological disaster emergency visualization integration method based on Cesium according to claim 1 is characterized in that: According to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, the geological disaster area and the interfering geological disaster area are subjected to time series monitoring and analysis to determine the geological disaster area time series monitoring results and the interfering geological disaster area time series monitoring results, including: According to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, the geological disaster area and the interfering geological disaster area are subjected to time series monitoring and analysis within a preset monitoring window to obtain a set sequence of geological disaster area influencing factors and a set sequence of interfering geological disaster area influencing factors; Performing fluctuation variance analysis on the set sequence of influencing factors of the geological hazard region and the set sequence of influencing factors of the interfering geological hazard region to determine the fluctuation coefficient of the geological hazard region and the fluctuation coefficient of the interfering geological hazard region; The convolution scale is determined according to the fluctuation coefficient of the geological disaster area and the fluctuation coefficient of the interfering geological disaster area, and the convolution analysis is performed on the set sequence of influencing factors of the geological disaster area and the set sequence of influencing factors of the interfering geological disaster area to obtain the time series monitoring results of the geological disaster area and the time series monitoring results of the interfering geological disaster area.

6. The geological disaster emergency visualization integration method based on Cesium according to claim 1, characterized in that: The disaster simulation model library includes a landslide-surge intelligent simulation model, an earthquake-rainfall-landslide intelligent simulation model, an earthquake-rainfall-mudslide intelligent simulation model, and a dam breach intelligent simulation model.

7. The Cesium-based geological disaster emergency visualization integration method according to claim 6, characterized in that: include: Collect water level, rainfall, earthquake data and dam monitoring data in parallel multiple times to obtain a sample dam stability monitoring data set and a corresponding dam failure risk data set; Using the meshless numerical simulation method, an intelligent dam failure simulation model is constructed based on the sample dam stability monitoring data set and the dam failure risk data set.

8. The geological disaster emergency visualization integration method based on Cesium according to claim 1 is characterized in that: The target geological hazard prototype, real-time multi-source geological hazard data and geological hazard area are transmitted to the Cesium platform, and the interference geological hazard area and geological hazard area are displayed in combination with the interference bandwidth identifier, including: Calling a display template of the Cesium platform based on a target geological hazard prototype; Performing format conversion on the real-time multi-source geological hazard data to obtain the converted real-time multi-source geological hazard data in an object format that conforms to Cesium; Based on the display template, the geological disaster area is displayed in the Cesium platform according to the converted real-time multi-source geological disaster data, and the interference geological disaster area determined based on the interference bandwidth identifier is displayed.

9. The geological disaster emergency visualization integrated system based on Cesium is characterized by: The system comprises: The first matching module is used to collect real-time multi-source geological disaster data in the geological disaster area, match the geological disaster prototype with the geological disaster prototype library, and obtain the target geological disaster prototype, wherein the target geological disaster prototype includes an interference bandwidth identifier; The regional display module is used to transmit the target geological hazard prototype, real-time multi-source geological hazard data and geological hazard area to the Cesium platform, and display the interference geological hazard area and geological hazard area in combination with the interference bandwidth identifier; A second matching module is used to match the target geological disaster prototype in the disaster deduction model library to obtain a target disaster deduction model; A time series monitoring and analysis module is used to perform time series monitoring and analysis on the geological disaster area and the interfering geological disaster area according to the target geological disaster influencing factor set corresponding to the target geological disaster prototype, and determine the time series monitoring results of the geological disaster area and the time series monitoring results of the interfering geological disaster area; A deduction and analysis module is used to use the target disaster deduction model to deduce and analyze the time series monitoring results of the geological disaster area and the time series monitoring results of the interfering geological disaster area to obtain target deduction and analysis results; A visualization integrated display module is used to visualize and integrate the target deduction and analysis results through the Cesium platform; The system is also used to implement the following functions: A sample multi-source geological hazard data set and a corresponding sample interference bandwidth set are obtained, and geological hazard prototypes are constructed by performing similar aggregation on them to obtain a geological hazard prototype library, wherein each geological hazard prototype includes benchmark multi-source geological hazard data; the real-time multi-source geological hazard data are approximately matched with the benchmark multi-source geological hazard data of each geological hazard prototype in the geological hazard prototype library, and the geological hazard prototype corresponding to the benchmark multi-source geological hazard data with the highest matching degree is used as the target geological hazard prototype.

Images