Geological disaster monitoring and early warning platform using dynamic superposition

Abstract

The invention relates to the technical field of geological disaster monitoring, and discloses a geological disaster monitoring and early warning platform using dynamic superposition, and the early warning platform comprises an initial module, a dynamic superposition module, an iteration module, and a monitoring and early warning data output module. According to the application, the initial module is used for collecting original data and generating a first superposition strategy, the dynamic superposition module is used for processing data and scoring according to the strategy and generating a second superposition strategy and data, the iteration module is used for judging a scoring difference value and optimizing the strategy, and the monitoring and early warning data output module is used for outputting final data. Dynamic optimization processing of geological disaster monitoring data is realized, a superposition strategy is continuously adjusted according to data characteristics and processing effects based on cooperative work, and it is ensured that the output monitoring and early warning data is higher in precision, so that the value of multi-source data is fully mined, and the real condition of geological disasters is more accurately presented. The accuracy and reliability of geological disaster monitoring and early warning are effectively improved, and powerful support is provided for disaster prevention and control decisions.

Description

Technical Field

[0001] The present application relates to the technical field of geological disaster monitoring, and specifically, it is a geological disaster monitoring and early warning platform using dynamic superposition. Background Art

[0002] The frequent occurrence of geological disasters seriously threatens the safety of human life and property and the sustainable development of society. Facing such a severe disaster situation, accurate and efficient monitoring and early warning technologies are crucial.

[0003] Currently, in the field of geological disaster monitoring and early warning, a variety of technical means are widely used to obtain data, such as satellite remote sensing, aerial photography, unmanned aerial vehicle monitoring, and ground sensors, etc., in an attempt to comprehensively master geological disaster information. However, in the data processing link, most traditional methods simply splice data from different sources when fusing data, and fail to fully explore the internal connections and complementary values of various types of data, resulting in insufficient information utilization and an inability to accurately present the true situation of geological disasters.

[0004] Chinese Publication No. CN114333245B discloses a multi-parameter model dynamic early warning method based on landslide three-dimensional monitoring. It mainly processes specific parameters for landslide monitoring, and the data types are relatively limited, making it difficult to integrate multi-source data to achieve deep fusion. When updating data, there is a lack of a dynamic real-time processing mechanism and it is unable to timely reflect the changes in geological bodies. Moreover, its data analysis method is relatively fixed, and it is difficult to flexibly adjust the processing strategy according to the characteristics and changes of the data, greatly reducing the accuracy and timeliness of monitoring and early warning, and unable to meet the requirements of complex and changeable geological disaster monitoring and early warning.

[0005] In summary, there is an urgent need for a new technical solution for geological disaster monitoring and early warning using dynamic superposition to solve the above technical problems. Summary of the Invention

[0006] The purpose of the present application is to provide a geological disaster monitoring and early warning platform using dynamic superposition to solve the technical problems raised in the above background art.

[0007] To achieve the above purpose, the present application discloses the following technical solutions: A geological disaster monitoring and early warning platform using dynamic superposition, the early warning platform includes:

[0008] The initial module is configured to: collect original data and generate a first superposition strategy based on the type of the original data;

[0009] The dynamic overlay module is configured to: process the original data based on the first overlay strategy to generate first overlay data, score the first overlay data to generate a first overlay score; when the first overlay score does not meet a preset first overlay score threshold, generate a second overlay strategy based on the type of the original data, the first overlay score, and a threshold difference, where the threshold difference is the difference between the first overlay score and the first overlay score threshold; process the original data based on the second overlay strategy to generate second overlay data, score the second overlay data to generate a second overlay score, and calculate the overlay score difference between the first overlay score and the second overlay score;

[0010] The iteration module is configured to: determine whether the superposition score difference meets a preset superposition score difference threshold; if not, generate a new first superposition strategy based on the type of original data and the superposition score difference, feed it back to the dynamic superposition module, and repeat the process until the superposition score difference threshold is met;

[0011] The monitoring and early warning data output module is configured to output the second superimposed data as data for geological disaster monitoring and early warning when the superimposed score difference meets the superimposed score difference threshold.

[0012] Preferably, the raw data collected by the initial module includes at least InSAR data, optical remote sensing data, UAV LiDAR data, oblique photogrammetry data and data collected by ground monitoring instruments.

[0013] Preferably, when processing the original data based on the first overlay strategy, the dynamic overlay module includes the following steps:

[0014] A1: performing denoising, filtering, splicing and fusion processing on the original data;

[0015] A2: Calculating a priority score for the raw data processed in step A1, the priority score being used to represent the priority of the raw data when processed based on the first overlay strategy; wherein the priority score is calculated using a preset data level, data timeliness, and an estimated correlation between the first overlay data and geological hazards;

[0016] A3: Based on the ranking of the priority scores, the original data processed in step A1 is processed using the first overlay strategy to obtain first overlay original data.

[0017] Preferably, when the dynamic superposition module scores the first superposition data and the second superposition data, the score is calculated based on a preset superposition data scoring formula using the data's completeness, accuracy, degree of reflection of geological hazard characteristics, and matching degree with historical data; wherein the matching degree is calculated using spatial feature matching degree, time series matching degree, and feature matching degree, and the superposition data scoring formula is:

[0018] Sc = C * A * R * M

[0019] Among them, C is a data integrity quantization index and C ∈ (0, 1), A is an accuracy quantization index and A ∈ (0, 1), R is a quantization index for the degree of reflection of geological disaster characteristics and R ∈ (0, 1), and M is the comprehensive matching degree between the data and historical data;

[0020] The comprehensive matching degree M between the data and historical data is calculated based on the comprehensive matching degree calculation formula. The comprehensive matching degree calculation formula is:

[0021]

[0022] Among them, M s is the spatial feature matching degree, M t is the time series matching degree, M f is the feature matching degree;

[0023] The spatial feature matching degree M s is calculated by using where S new is the area of the new data spatial range, S old is the area of the historical data spatial range, S over is the overlapping area of the new data spatial range area and the historical data spatial range area;

[0024] The time series matching degree M t is calculated by using where d rate is the absolute value of the difference in the relative change rate of the new data and the historical data time series, and d max_rate is the maximum difference in the corresponding absolute value of the difference in the relative change rate;

[0025] The feature matching degree M f is calculated by using where d e is the Euclidean distance between the new data and the historical data feature vectors, and d max_e is the maximum value of the corresponding Euclidean distance.

[0026] Preferably, the first superposition scoring threshold and the superposition scoring difference threshold are associated and dynamically adjusted based on different geological disaster types, the geological conditions of the monitoring area, and historical disaster data. This associated dynamic adjustment includes the following steps:

[0027] B1: Calculate the first superposition scoring threshold by using the quantization indexes corresponding to different geological disaster types, the geological conditions of the monitoring area, and historical disaster data;

[0028] B2: Calculate the superposition score difference threshold by using different types of geological disaster, geological conditions of the monitoring area, and amplitude quantization indexes corresponding to historical disaster data;

[0029] B3: When the first superposition score threshold changes, update the calculation of the superposition score difference threshold in step B2 by using the change rate of the first superposition score threshold.

[0030] Preferably, when generating a new first superposition strategy, the iteration module adjusts the initial weights of different types of data based on the data change trend in the preprocessing process. The adjustment includes the following steps:

[0031] C1: Calculate the weight adjustment factor by using the data change trend in the preprocessing process;

[0032] C2: Adjust the corresponding initial weights based on the weight adjustment factor.

[0033] Preferably, the second superposition data output by the monitoring and early warning data output module is presented in any one or more of the forms of digital orthophoto map, digital elevation model, and real scene three-dimensional model.

[0034] Preferably, the early warning platform further includes a data storage module for storing the original data, the first superposition strategy, the first superposition data, the first superposition score, the second superposition strategy, the second superposition data, the second superposition score, and the corresponding log data.

[0035] Preferably, after the monitoring and early warning data output module outputs data, early warning information for geological disasters of different levels is generated based on a preset early warning level calculation method.

[0036] Preferably, the early warning platform is applied to the monitoring and early warning of high-incidence areas of geological disasters, and the high-incidence areas of geological disasters at least include mountainous areas, river banks, and earthquake-prone areas.

[0037] Beneficial effects: The geological disaster monitoring and early warning platform using dynamic superposition of the present application uses the initial module to collect original data and generate the first superposition strategy. The dynamic superposition module processes data, scores, and generates the second superposition strategy and data according to the strategy. The iteration module judges the score difference and optimizes the strategy. The monitoring and early warning data output module outputs the final data, realizing the dynamic optimization processing of geological disaster monitoring data. Based on collaborative work, the superposition strategy is continuously adjusted according to data characteristics and processing effects to ensure higher accuracy of the output monitoring and early warning data, thereby fully excavating the value of multi-source data, presenting the true situation of geological disasters more accurately, effectively improving the accuracy and reliability of geological disaster monitoring and early warning, and providing strong support for disaster prevention and control decision-making. Description of the Drawings

[0038] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a structural block diagram of a geological disaster monitoring and early warning platform using dynamic superposition provided by an embodiment of the present application. Specific implementation manners

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0041] In this article, the term "including" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without more limitations, the elements defined by the statement "including..." do not exclude the existence of other identical elements in the process, method, article or device including the said elements.

[0042] The first aspect of this embodiment discloses a geological disaster monitoring and early warning platform using dynamic superposition as shown in Figure 1 The early warning platform includes:

[0043] An initial module is configured to: collect original data and generate a first superposition strategy based on the type of the original data;

[0044] A dynamic superposition module is configured to: process the original data based on the first superposition strategy to generate first superposition data, score the first superposition data to generate a first superposition score; when the first superposition score does not meet the preset first superposition score threshold, generate a second superposition strategy based on the type of the original data, the first superposition score and the threshold difference, where the threshold difference is the difference between the first superposition score and the first superposition score threshold; process the original data based on the second superposition strategy to generate second superposition data, score the second superposition data to generate a second superposition score, and calculate the superposition score difference between the first superposition score and the second superposition score;

[0045] The iterative module is configured to: determine whether the superimposed score difference meets a preset superimposed score difference threshold. When it does not meet the threshold, generate a new first superimposed strategy based on the type of the original data and the superimposed score difference, and feedback it to the dynamic superimposition module, and repeat the process until the superimposed score difference threshold is met;

[0046] The monitoring and early warning data output module is configured to: when the superimposed score difference meets the superimposed score difference threshold, output the second superimposed data as the data for geological disaster monitoring and early warning.

[0047] With the above, in this embodiment, the initial module is used to collect the original data and generate the first superimposed strategy. The dynamic superimposition module processes the data, scores, and generates the second superimposed strategy and data according to the strategy. The iterative module judges the score difference and optimizes the strategy. The monitoring and early warning data output module outputs the final data, realizing the dynamic optimization processing of geological disaster monitoring data. Based on the collaborative work, continuously adjusts the superimposed strategy according to the data characteristics and processing effects, ensures that the accuracy of the output monitoring and early warning data is higher, thus fully exploiting the value of multi-source data, presenting the true situation of geological disasters more accurately, effectively improving the accuracy and reliability of geological disaster monitoring and early warning, and providing strong support for disaster prevention and control decision-making.

[0048] Specifically, the original data collected by the initial module at least includes InSAR data, optical remote sensing data, UAV LiDAR data, oblique photogrammetry data, and data collected by ground monitoring instruments.

[0049] With the above, in this embodiment, the initial module is used to collect InSAR data, optical remote sensing data, UAV LiDAR data, oblique photogrammetry data, and data collected by ground monitoring instruments, realizing the comprehensive acquisition of multi-source data. These data reflect geological disaster information from different angles and scales. For example, InSAR data can monitor large-area surface deformation, and UAV LiDAR data can obtain high-precision terrain information. The multi-source data complement each other, overcoming the limitations of a single data type, providing rich materials for subsequent data processing and analysis, enabling the monitoring and early warning platform to more comprehensively and accurately grasp the characteristics and change trends of geological disasters, and thus improving the comprehensiveness and scientific nature of geological disaster monitoring and early warning.

[0050] Specifically, when the dynamic superimposition module processes the original data based on the first superimposed strategy, it includes the following steps:

[0051] A1: Perform denoising, filtering, splicing, and fusion processing on the original data;

[0052] A2: Calculate the priority score of the original data processed in step A1. This priority score is used to characterize the priority of the original data when processed based on the first superposition strategy. Among them, the priority score is calculated using a preset data level, data timeliness, and the estimated relevance between the first superposed data and geological disasters.

[0053] A3: Based on the sorting of the priority scores, use the first superposition strategy to process the original data processed in step A1 to obtain the first superposed original data.

[0054] As a preferred implementation manner of this embodiment, the priority score is calculated using the priority score calculation formula. The priority score calculation formula is:

[0055] YXJ = (DJ * GLX) SXX

[0056] Among them, DJ is the data level, SXX is the data timeliness, GLX is the relevance between the first superposed data and geological disasters, and YXJ is the calculated priority score.

[0057] In a simple example, data A comes from a high-precision device, was collected 1 hour ago, is closely related to geological disasters, and has a data level of 5, timeliness of 0.9, and relevance of 0.8; data B comes from a general sensor, was collected 6 hours ago, has a certain association with geological disasters, has a data level of 3, timeliness of 0.6, and relevance of 0.5; data C comes from a low-precision device, was collected 12 hours ago, has a weak relevance to geological disasters, has a data level of 2, timeliness of 0.3, and relevance of 0.2. The calculated priority scores of data A, B, and C are approximately 3.77, 1.35, and 0.74 respectively. When processing, data A will be preferentially processed in this order.

[0058] Through the above, this embodiment uses the dynamic superposition module to perform denoising, filtering, stitching, and fusion processing on the original data using existing technologies, calculates the priority score and processes the data accordingly, realizing the efficient processing and reasonable utilization of the original data. Operations such as denoising and filtering improve the data quality. The priority score is determined based on the data level, timeliness, and relevance to geological disasters, ensuring that important data is processed first. For example, data with strong timeliness can be used in a timely manner during the critical period of disaster monitoring. This optimizes the data processing process, improves the data processing efficiency and accuracy, enables the first superposed data to better reflect the actual situation of geological disasters, and enhances the analysis and judgment ability of the monitoring and early warning platform for geological disasters.

[0059] Specifically, when the dynamic superposition module scores the first superposition data and the second superposition data, the score is calculated based on a preset superposition data scoring formula using the data's completeness, accuracy, degree of reflection of geological hazard characteristics, and matching degree with historical data; wherein the matching degree is calculated using spatial feature matching degree, time series matching degree, and feature matching degree. The superposition data scoring formula is:

[0060] Sc=C*A*R*M

[0061] Among them, C is the quantitative index of data integrity and C∈(0,1), A is the quantitative index of accuracy and A∈(0,1), R is the quantitative index of the degree of reflection of geological hazard characteristics and R∈(0,1), and M is the comprehensive matching degree between data and historical data;

[0062] The comprehensive matching degree M between the data and the historical data is calculated based on the comprehensive matching degree calculation formula, which is:

[0063]

[0064] Among them, M s is the spatial feature matching degree, M t is the time series matching degree, M f is the feature matching degree;

[0065] Spatial feature matching degree M s use Calculate and get, where S new is the area of the new data space, S old is the spatial range of historical data, S over The overlapping area of the new data space range and the historical data space range;

[0066] Time series matching degree M t use Calculate and get, d rate is the absolute value of the difference in relative change rate between the new data and the historical data time series, d max_rate is the maximum difference in the absolute value of the corresponding relative change rate difference;

[0067] Feature matching degree M f use Calculate and get, d e is the Euclidean distance between the feature vectors of new data and historical data, d max_e is the maximum value of the corresponding Euclidean distance.

[0068] Based on the above, this embodiment utilizes a preset scoring formula for overlay data, combining data integrity, accuracy, degree of reflection of geological hazard characteristics, and matching with historical data to achieve a quantitative assessment of overlay data quality, thereby measuring the similarity between new data and historical data from different dimensions. Through accurate scoring, high-quality data can be selected for monitoring and early warning. In landslide monitoring, if the new data has a high degree of match with historical landslide data and other indicators are good, the development trend of the landslide can be more accurately judged, providing a scientific basis for geological hazard early warning and improving the accuracy of early warning.

[0069] Specifically, when generating a new first superposition strategy, the iteration module adjusts the initial weights of different types of data based on the data change trend in the previous processing process. The adjustment includes the following steps:

[0070] C1: Calculate the weight adjustment factor using the data change trend during the previous processing;

[0071] C2: Adjust the corresponding initial weight based on the weight adjustment factor.

[0072] As a preferred implementation of this embodiment, the weight adjustment factor is calculated using the following content:

[0073] In this embodiment, there are n different types of data, i represents the data type and i=1, 2, . . .

[0074] Among them, T i,t is the value of the i-th type of data at time t, T i,t-1 is the value of the i-th type of data at time t-1. Then the change ΔT of the i-th type of data in the time interval [t-1, t] is i,t =T i,t -T i,t-1 .

[0075] Calculate the mean of the change in the i-th type of data within a period of time m (from t0 to t0+m)

[0076] in, That is, the maximum value among the mean changes of all types of data.

[0077] Weight adjustment factor F i The calculation formula is:

[0078]

[0079] This calculation formula indicates that the weight adjustment factor of each type of data is the ratio of the average value of the data change over a period of time to the maximum value of the average value of the data change of all types. The more obvious the change trend of the data, the larger its weight adjustment factor.

[0080] With the above, in this embodiment, the iterative module is used to adjust the initial weights of different types of data according to the change trend of the previous data, realizing the dynamic optimization of the data weights. The change trend of the data reflects its importance and stability. For example, during the formation process of debris flow, the change trend of precipitation data is obvious, and the weight can be increased accordingly. Reasonably adjusting the weights enables various types of data to play appropriate roles in the superposition processing, further optimizing the data processing results, enhancing the monitoring and early warning platform's ability to capture geological disaster characteristics, and improving the accuracy of monitoring and early warning.

[0081] Specifically, the second superposition data output by the monitoring and early warning data output module is presented in any one or more forms of digital orthophoto map, digital elevation model, and real-scene three-dimensional model.

[0082] With the above, in this embodiment, the monitoring and early warning data output module is used to present the second superposition data in forms such as digital orthophoto map, digital elevation model, and real-scene three-dimensional model, realizing the intuitive visualization of the monitoring data. These models can display geological disaster information from different dimensions. The digital orthophoto map provides clear surface textures, the digital elevation model reflects the terrain undulation, and the real-scene three-dimensional model presents a realistic scene. The visual display facilitates the staff to intuitively understand the current situation and changes of geological disasters, assisting in making decisions quickly, and improving the practicality and decision-making efficiency of geological disaster monitoring and early warning.

[0083] Specifically, the early warning platform further includes a data storage module for storing the original data, the first superposition strategy, the first superposition data, the first superposition score, the second superposition strategy, the second superposition data, the second superposition score, and the corresponding log data.

[0084] With the above, in this embodiment, the data storage module is used to store the original data, strategies, data, scores, and log data at each stage, realizing the effective management and traceability of the data. The stored data provides a basis for subsequent analysis, verification, and optimization, and can review the monitoring and early warning process to check the accuracy of data processing and the rationality of strategies. If the monitoring results are abnormal, the data processing links can be traced back to find the reasons, which helps to continuously improve the performance of the monitoring and early warning platform and ensure the reliability and stability of the monitoring and early warning work.

[0085] Specifically, after the monitoring and early warning data output module outputs the data, early warning information for geological disasters of different levels is generated based on a preset early warning level calculation method.

[0086] Through the above, in this embodiment, after the monitoring and early warning data output module outputs data, different levels of geological disaster early warning information are generated based on a preset method, realizing hierarchical early warning of geological disasters. Different levels of early warning information enable relevant departments and personnel to quickly understand the severity of the disaster and take targeted countermeasures. For example, a red early warning corresponds to a high-risk disaster, and immediate evacuation of personnel needs to be organized; a yellow early warning indicates enhanced monitoring. Hierarchical early warning improves the timeliness and effectiveness of disaster response, minimizing casualties and property losses to the greatest extent possible.

[0087] Specifically, this early warning platform is applied to the monitoring and early warning of high-incidence areas of geological disasters, which at least include mountainous areas, river banks, and earthquake-prone areas.

[0088] Through the above, in this embodiment, the early warning platform is applied to high-incidence areas of geological disasters such as mountainous areas, river banks, and earthquake-prone areas, realizing precise monitoring and early warning of key areas. These areas have complex geological conditions and high disaster risks. Deploying the platform in these areas can timely obtain data, process and analyze it, discover disaster hidden dangers in advance, and issue early warnings. In mountainous areas, the risk of landslides can be monitored, and in river banks, geological disasters caused by floods can be prevented, providing strong protection for the lives and property safety of residents in high-incidence areas.

[0089] In summary, the dynamic superposition geological disaster monitoring and early warning platform of this embodiment uses the initial module to collect raw data and generate the first superposition strategy. The dynamic superposition module processes data, scores, and generates the second superposition strategy and data according to the strategy. The iteration module judges the score difference and optimizes the strategy. The monitoring and early warning data output module outputs the final data, realizing the dynamic optimization processing of geological disaster monitoring data. Based on collaborative work, the superposition strategy is continuously adjusted according to the data characteristics and processing effects to ensure higher accuracy of the output monitoring and early warning data, thereby fully excavating the value of multi-source data, presenting the true situation of geological disasters more accurately, effectively improving the accuracy and reliability of geological disaster monitoring and early warning, and providing strong support for disaster prevention and control decision-making.

[0090] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transmission of a computer program from one place to another. The storage media can be any available medium that can be accessed by a computer. The computer-readable storage medium can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM, or other optical disk storage, magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0091] Finally, it should be noted that the above are only the preferred embodiments of the present application and are not used to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A geological disaster monitoring and early warning platform using dynamic superposition, characterized in that, The early warning platform includes: The initial module is configured to: collect original data and generate a first superposition strategy based on the type of the original data; The dynamic superposition module is configured to: process the original data based on the first superposition strategy to generate first superposition data, score the first superposition data to generate a first superposition score; when the first superposition score does not meet the preset first superposition score threshold, generate a second superposition strategy based on the type of the original data, the first superposition score, and the threshold difference, where the threshold difference is the difference between the first superposition score and the first superposition score threshold; process the original data based on the second superposition strategy to generate second superposition data, score the second superposition data to generate a second superposition score, and calculate the superposition score difference between the first superposition score and the second superposition score; The iteration module is configured to: determine whether the superposition score difference meets the preset superposition score difference threshold, and when it does not meet, generate a new first superposition strategy based on the type of the original data and the superposition score difference, and feedback it to the dynamic superposition module, and repeat the process until the superposition score difference threshold is met; The monitoring and early warning data output module is configured to: when the superposition score difference meets the superposition score difference threshold, output the second superposition data as the data for geological disaster monitoring and early warning.

2. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that The original data collected by the initial module includes at least InSAR data, optical remote sensing data, UAV LiDAR data, oblique photogrammetry data, and data collected by ground monitoring instruments.

3. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that, When the dynamic superposition module processes the original data based on the first superposition strategy, it includes the following steps: A1: Denoise, filter, splice, and fuse the original data; A2: Calculate the priority score of the original data processed in step A1, where the priority score is used to characterize the priority of the original data when processed based on the first superposition strategy; wherein, the priority score is calculated using a preset data level, data timeliness, and the estimated relevance between the first superposition data and the geological disaster; A3: Based on the sorting of the priority scores, process the original data processed in step A1 using the first superposition strategy to obtain first superposition original data.

4. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that When the dynamic superposition module scores the first superposition data and the second superposition data, the score is calculated based on the integrity, accuracy, degree of reflection of geological disaster characteristics, and matching degree with historical data using a preset superposition data scoring formula; wherein, the matching degree is calculated using spatial feature matching degree, time series matching degree, and feature matching degree, and the superposition data scoring formula is: Sc = C * A * R * M where C is a data integrity quantification index and C ∈ (0, 1), A is an accuracy quantification index and A ∈ (0, 1), R is a quantification index for the degree of reflection of geological disaster characteristics and R ∈ (0, 1), and M is the comprehensive matching degree of the data with historical data; The comprehensive matching degree M of the data with historical data is calculated based on the comprehensive matching degree calculation formula, and the comprehensive matching degree calculation formula is: Among them, M s is the spatial feature matching degree, M t is the time series matching degree, M f is the feature matching degree; Spatial feature matching degree M s It is calculated by using , where S new is the area of the new data space range, S old is the area of the historical data space range, and S over is the overlapping area of the new data space range area and the historical data space range area; Time series matching degree M t Utilize to calculate and obtain d rate is the absolute value of the difference in the relative change rates of the new data and the historical data time series, and d max_rate is the maximum difference in the absolute values of the corresponding relative change rate differences; Feature matching degree M f It is calculated by using to obtain d e is the Euclidean distance between the feature vectors of the new data and the historical data, and d max_e is the maximum value of the corresponding Euclidean distance.

5. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that The first superimposed scoring threshold and the superimposed scoring difference threshold are associated and dynamically adjusted based on different types of geological disasters, geological conditions of the monitoring area, and historical disaster data. This associated dynamic adjustment includes the following steps: B1: Calculate the first superimposed scoring threshold using the quantization indicators corresponding to different types of geological disasters, geological conditions of the monitoring area, and historical disaster data; B2: Calculate the superimposed scoring difference threshold using the amplitude quantization indicators corresponding to different types of geological disasters, geological conditions of the monitoring area, and historical disaster data; B3: When the first superimposed scoring threshold changes, update the calculation of the superimposed scoring difference threshold in step B2 using the change rate of the first superimposed scoring threshold.

6. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that When generating a new first superimposed strategy, the iterative module adjusts the initial weights of different types of data based on the data change trend during the preprocessing process. This adjustment includes the following steps: C1: Calculate the weight adjustment factor using the data change trend during the preprocessing process; C2: Adjust the corresponding initial weights based on the weight adjustment factor.

7. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that The second superimposed data output by the monitoring and early warning data output module is presented in any one or more of the forms of digital orthophoto maps, digital elevation models, and real-scene three-dimensional models.

8. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that The early warning platform further includes a data storage module for storing the original data, the first superimposed strategy, the first superimposed data, the first superimposed score, the second superimposed strategy, the second superimposed data, the second superimposed score, and the corresponding log data.

9. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that, After the monitoring and early warning data output module outputs data, early warning information for geological disasters of different levels is generated based on a preset early warning level calculation method.

10. The geological disaster monitoring and early warning platform using dynamic superposition according to claim 1, characterized in that, This early warning platform is applied to the monitoring and early warning of high-incidence areas of geological disasters, which at least include mountainous areas, river banks, and earthquake-prone areas.

Images