Geological disaster monitoring and early warning method and system based on beidou signal

Abstract

This invention provides a geological disaster monitoring and early warning method and system based on BeiDou signals, belonging to the field of data monitoring technology. It includes: extracting spectral, texture, and shape features from monitored real-time images for analysis to identify abnormal areas and corresponding geological disaster types in the monitored region; analyzing surface deformation data of the identified abnormal areas based on BeiDou satellite data to obtain deformation data features of the abnormal areas, assessing the degree of deformation, and obtaining a deformation degree assessment value; determining the geological disaster index of the monitored region based on the deformation degree assessment value and the geological disaster type, and generating a corresponding early warning strategy. This invention achieves early automatic delineation of potential hazards by analyzing image features from BeiDou satellite imagery, and combines BeiDou deformation data to quantitatively analyze the activity status of disaster bodies, generating a tiered early warning strategy, thus improving the spatiotemporal coverage, accuracy, and timeliness of geological disaster monitoring and early warning.

Description

Technical Field

[0001] This invention relates to the field of data monitoring technology, specifically to a geological disaster monitoring and early warning method and system based on BeiDou signals. Background Technology

[0002] Geological disasters, as global natural disasters, cause numerous casualties and huge economic losses worldwide every year. Due to complex geological conditions, widespread mountainous and plateau regions, and the influence of extreme climates and human engineering activities, landslides, collapses, debris flows, and ground subsidence occur frequently and are highly sudden, posing a serious threat to people's lives and property, engineering operations, and socio-economic development.

[0003] Traditional monitoring and early warning methods mainly rely on manual inspections, simple monitoring equipment, and analysis of single data sources. They generally suffer from bottlenecks such as large monitoring blind spots, poor early warning timeliness, and low automation, making it difficult to meet the urgent need for early identification and accurate early warning of geological disasters in large-scale and complex environments. Summary of the Invention

[0004] The purpose of this invention is to provide a geological disaster monitoring and early warning method and system based on BeiDou signals. This method and system can automatically delineate potential hazards in the early stage by analyzing the image features of BeiDou satellite images, and combine BeiDou deformation data to quantitatively analyze the activity status of disaster bodies, thereby generating a graded early warning strategy. This can improve the spatiotemporal coverage, accuracy and timeliness of geological disaster monitoring and early warning, and improve the intelligence level of geological disaster risk prevention and control and the efficiency of emergency response.

[0005] To address the aforementioned technical problems, one embodiment of the present invention provides a geological disaster monitoring and early warning method based on BeiDou signals, comprising: Acquire real-time images of the area to be monitored, and extract spectral, texture, and shape features from the real-time images; Based on the analysis of spectral features, texture features, and shape features, the monitored real-time images are identified to determine the abnormal areas and corresponding geological hazard types in the area to be monitored; Based on the BeiDou satellite, surface deformation data of the abnormal area was determined, and the surface deformation data was analyzed to determine the deformation data characteristics of the abnormal area. The degree of deformation in abnormal areas is assessed based on the characteristics of deformation data, and the deformation degree assessment value of abnormal areas is obtained. The geological hazard index of the area to be monitored is determined based on the deformation degree assessment value and geological hazard type of each abnormal area, and the corresponding early warning strategy is generated based on the geological hazard index.

[0006] Optionally, the monitored images are analyzed based on spectral features, texture features, and shape features to identify anomalous areas and corresponding geological hazard types in the monitored area, including: Determine the original monitoring images of the pre-defined area to be monitored, and compare the original monitoring images with the monitoring images to identify the discrepancies between the monitoring images and the original monitoring images; In the original monitoring images, the original regions corresponding to the regions of difference are identified, and the spectral, texture, and shape features of the regions of difference and the original regions are determined respectively. Difference analysis and calculation are performed on the spectral, texture and shape characteristics of the difference region and the original region to obtain the difference value. The difference region with the difference value greater than the preset threshold is identified as the abnormal region in the area to be monitored. The spectral, textural, and shape features of the anomalous area are determined, and these features are matched with the preset geological hazard types in the preset geological hazard database to obtain the geological hazard type corresponding to the anomalous area.

[0007] Optionally, difference analysis and calculation are performed on the spectral, texture, and shape features of the difference region and the original region to obtain difference values, including: The average spectral index of the difference region and the original region is determined based on spectral characteristics, and the difference between the average spectral index of the difference region and the average spectral index of the original region is determined to obtain the change in spectral index. The average contrast of the difference region and the original region is determined based on the texture features, and the difference between the average contrast of the difference region and the average contrast of the original region is determined to obtain the change in average contrast. Based on shape features, the compactness of the difference region and the original region is determined, and the difference between the compactness of the difference region and the compactness of the original region is determined to obtain the amount of compactness change; The changes in spectral index, average contrast, and compactness are normalized to obtain normalized values ​​for each feature, and the preset weights for each feature are determined. The difference value is obtained by weighting the normalized value of each feature with its corresponding preset weight.

[0008] Optionally, surface deformation data of the anomalous area is determined based on BeiDou satellite data, and the surface deformation data is analyzed to determine the deformation data characteristics of the anomalous area, including: The surface deformation data of the abnormal area was determined based on the Beidou satellite, and a data change curve with time progress was constructed based on the surface deformation data; Deformation rate, deformation acceleration, and cumulative deformation are determined from the data change curves, and these three parameters are identified as deformation data characteristics of the abnormal region.

[0009] Optionally, the degree of deformation in the abnormal region is assessed based on the deformation data characteristics to obtain an assessment value of the degree of deformation in the abnormal region, including: Determine the reference deformation rate, reference deformation acceleration, and reference cumulative deformation, and calculate the differences between the deformation rate and the reference deformation rate, the deformation acceleration and the reference deformation acceleration, and the cumulative deformation and the reference cumulative deformation, respectively. The obtained differences are evaluated and values ​​are taken respectively to obtain the deformation rate evaluation value, deformation acceleration evaluation value and cumulative deformation evaluation value, and the preset weight of each deformation data feature is determined. The deformation degree assessment value of the abnormal area is obtained by weighting and summing the evaluation values ​​of each deformation data feature with the corresponding preset weights.

[0010] Optionally, the geological hazard index of the area to be monitored is determined based on the deformation degree assessment value and geological hazard type of each anomaly area, including: The disaster coefficient of each anomalous region is determined based on the geological disaster type of each anomalous region, and the area of ​​each anomalous region is determined accordingly; The geological hazard index of the monitored area is calculated based on the disaster coefficient, area and deformation degree assessment values ​​of each abnormal area.

[0011] Optionally, the hazard coefficient of each anomalous region is determined based on the geological hazard type of each anomalous region, and the area of ​​each anomalous region is determined, including: A pre-defined correspondence between preset disaster coefficients and geological disaster types is established. For each geological disaster type, a corresponding preset disaster coefficient is associated with it. The geological hazard types in the anomalous area are determined, and based on the mapping relationship between the geological hazard types in the anomalous area and the pre-set hazard coefficient-geological hazard type correspondence, the pre-set hazard coefficient corresponding to the geological hazard type is selected as the hazard coefficient of the anomalous area.

[0012] Optionally, the geological hazard index of the monitored area is calculated based on the hazard coefficient, area, and deformation degree assessment values ​​of each anomaly region, including: The geological hazard index is obtained according to formula (1). (1) Where Z is the geological disaster index of the area to be monitored, ki is the disaster coefficient of the i-th abnormal area, mi is the area of ​​the i-th abnormal area, Pi is the deformation degree assessment value of the i-th abnormal area, and n is the number of abnormal areas.

[0013] Optionally, a corresponding early warning strategy is generated based on the geological hazard index, including: A first preset index and a second preset index are determined, and an early warning strategy is generated based on the relationship between the geological disaster index and the first preset index and the second preset index. If the geological disaster index is less than or equal to the first preset index, the generated early warning strategy is to issue a blue early warning and remind that the current monitored area is a low-risk area; If the geological disaster index is greater than the first preset index but less than the second preset index, the generated early warning strategy is to issue a yellow warning and remind that the current monitored area is a medium-risk area. If the geological disaster index is greater than or equal to the second preset index, the generated early warning strategy will be to issue a red warning and remind that the current monitored area is a high-risk area.

[0014] On the other hand, embodiments of the present invention also provide a geological disaster monitoring and early warning system based on BeiDou signals, comprising: The extraction module is used to acquire real-time monitoring images of the area to be monitored and extract the spectral features, texture features, and shape features of the real-time monitoring images; The analysis module is used to analyze the monitored real-time images based on spectral features, texture features, and shape features to identify abnormal areas and corresponding geological disaster types in the area to be monitored. The determination module is used to determine the surface deformation data of the abnormal area based on the Beidou satellite, and to analyze the surface deformation data to determine the deformation data characteristics of the abnormal area; The evaluation module is used to assess the degree of deformation in abnormal areas based on the characteristics of deformation data, and obtain the evaluation value of the degree of deformation in abnormal areas; The generation module is used to determine the geological hazard index of the area to be monitored based on the deformation degree assessment value and geological hazard type of each abnormal area, and to generate corresponding early warning strategies based on the geological hazard index.

[0015] Through the above technical solution, this invention provides a geological disaster monitoring and early warning method and system based on BeiDou signals. Compared with the prior art, its advantages are as follows: This invention achieves automated interpretation and change detection by fusing spectral, texture, and shape multidimensional features from real-time monitored images. It can efficiently screen out early anomalies in land cover and morphology over a wide area, overcoming the limitations of traditional manual patrols, such as limited field of vision, low efficiency, and difficulty in discovering hidden hazards. It advances hazard identification from the period of significant deformation to the period of slight surface change. Furthermore, it performs quantitative diagnosis on the screened abnormal areas using high-precision deformation data, achieving a deeper understanding from identifying surface anomalies to assessing internal mechanical processes. This significantly improves the accuracy of target locking and the scientific nature of risk assessment, and effectively reduces the false alarm rate. This invention innovatively extracts temporal deformation characteristics into calculable deformation degree assessment values, and further integrates disaster type information to construct a comprehensive regional geological disaster index. This transforms the originally vague qualitative risk judgment, which relies on personal experience, into a grade evaluation based on unified quantitative standards, thereby achieving objectivity and comparability of risk assessment. This invention, based on a quantified geological disaster index, can automatically match and generate tiered early warning strategies, changing the traditional one-size-fits-all approach to early warning. This makes early warning information dissemination more targeted and emergency resource allocation more optimized, forming a closed-loop management process of intelligent monitoring, automatic assessment, precise early warning, and strategy feedback, which greatly improves the intelligence level of geological disaster risk prevention and control and the efficiency of emergency response.

[0016] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a geological disaster monitoring and early warning method based on BeiDou signals, according to one embodiment of the present invention; Figure 2 This is a flowchart illustrating the process of obtaining the geological hazard type corresponding to an abnormal area according to one embodiment of the present invention; Figure 3 This is a flowchart illustrating the process of obtaining difference values ​​according to one embodiment of the present invention; Figure 4 This is a flowchart illustrating the deformation data features of an abnormal region according to one embodiment of the present invention. Figure 5 This is a flowchart illustrating the process of obtaining an assessment value for the degree of deformation in an abnormal region according to one embodiment of the present invention. Figure 6 This is a flowchart illustrating the process of determining the geological hazard index of a monitored area according to one embodiment of the present invention. Figure 7 This is a flowchart illustrating the determination of disaster coefficients for each abnormal region according to one embodiment of the present invention; Figure 8 This is a flowchart illustrating the generation of a corresponding early warning strategy according to one embodiment of the present invention; Figure 9 This is a schematic diagram of the composition of a geological disaster monitoring and early warning system based on BeiDou signals, according to one embodiment of the present invention. Detailed Implementation

[0018] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0019] In the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.

[0020] like Figure 1 The diagram shows a flowchart of a geological disaster monitoring and early warning method based on BeiDou signals, according to one embodiment of the present invention. Figure 1 In this context, the geological disaster monitoring and early warning method may include: In step S1, real-time images of the area to be monitored are acquired, and the spectral features, texture features, and shape features of the real-time images are extracted. In step S2, the monitored real-shot images are analyzed based on spectral features, texture features, and shape features to determine the abnormal areas in the area to be monitored and the corresponding geological disaster types; In step S3, surface deformation data of the abnormal area is determined based on BeiDou satellite, and the surface deformation data is analyzed to determine the deformation data characteristics of the abnormal area; In step S4, the degree of deformation in the abnormal area is evaluated based on the deformation data characteristics to obtain the deformation degree evaluation value of the abnormal area; In step S5, the geological hazard index of the area to be monitored is determined based on the deformation degree assessment value and geological hazard type of each abnormal area, and a corresponding early warning strategy is generated based on the geological hazard index.

[0021] This invention utilizes the fusion of spectral, texture, and shape multidimensional features from monitored real-time images for automated interpretation and change detection. This enables efficient screening of early anomalies in land cover and morphology over large areas, overcoming the limitations of traditional manual patrols, such as limited visibility, low efficiency, and difficulty in detecting hidden hazards. It advances hazard identification from the period of significant deformation to the period of minor surface changes. Furthermore, for the screened anomaly areas, quantitative diagnosis is performed using high-precision deformation data, achieving a deeper understanding from identifying surface anomalies to assessing internal mechanical processes. This significantly improves the accuracy of target locking and the scientific rigor of risk assessment, effectively reducing the false alarm rate. This invention innovatively extracts temporal deformation features into calculable... This invention assesses the degree of deformation and further integrates disaster type information to construct a comprehensive regional geological disaster index. This transforms the previously vague qualitative risk judgment, which relied on personal experience, into a graded evaluation based on unified quantitative standards, thus achieving objectivity and comparability in risk assessment. Based on the quantitative geological disaster index, this invention can automatically match and generate graded early warning strategies, changing the traditional one-size-fits-all approach to early warning. This makes early warning information dissemination more targeted and emergency resource allocation more optimized, forming a closed-loop management process of intelligent monitoring, automatic assessment, precise early warning, and strategy feedback. This greatly improves the intelligence level of geological disaster risk prevention and control and the efficiency of emergency response.

[0022] In Figure 1 In the method shown, step S1 can be used to acquire real-time monitoring images of the area to be monitored and extract spectral features, texture features, and shape features from the real-time monitoring images. Step S2 can be used to analyze the real-time monitoring images based on spectral features, texture features, and shape features to determine the abnormal areas in the area to be monitored and the corresponding geological hazard types. The specific method for obtaining the geological hazard types corresponding to the abnormal areas can be of various forms known to those skilled in the art. In one example of the present invention, it may include, for example... Figure 2 The steps are shown. Specifically: In step S11, the original monitoring images of the pre-defined area to be monitored are determined, and the original monitoring images are compared with the monitoring images to identify the discrepancies between the monitoring images and the original monitoring images. In step S12, the original region corresponding to the difference region is determined in the original monitoring real-shot image, and the spectral features, texture features and shape features of the difference region and the original region are determined respectively; In step S13, the spectral features, texture features and shape features of the difference region and the original region are analyzed and calculated to obtain the difference value. The difference region with the difference value greater than the preset threshold is identified as the abnormal region in the area to be monitored. In step S14, the spectral features, texture features, and shape features of the abnormal area are determined, and the spectral features, texture features, and shape features of the abnormal area are matched with the preset geological hazard types in the preset geological hazard database to obtain the geological hazard type corresponding to the abnormal area.

[0023] Specifically, by accurately comparing real-time monitoring images of the monitored area with historical real-time monitoring images, the system automatically locates areas of significant change in the land surface, replacing traditional manual visual interpretation and enabling rapid and objective initial screening of areas with large-scale changes. It quantifies and calculates the differences between the differing areas and their corresponding original areas using multi-dimensional features such as spectral density (e.g., vegetation cover, humidity), texture (roughness, homogeneity), and shape (boundary morphology, area). Through preset thresholds, it objectively screens out anomalous areas with engineering geological significance, effectively overcoming misjudgments caused by seasonal changes and differences in lighting, and enhancing the robustness and accuracy of anomaly identification. Furthermore, it intelligently matches the multi-feature spectra of the screened anomalous areas with a preset geological hazard database, achieving preliminary automatic identification of hazard types such as landslides, collapses, and debris flows. This provides precise targets and key prior knowledge for subsequent targeted deployment of deformation monitoring equipment and risk level assessment.

[0024] In such Figure 2 In the method shown, step S11 can be used to determine the original monitoring image of a pre-defined area to be monitored, and compare the original monitoring image with the monitoring image to identify the difference areas in the monitoring image that are inconsistent with the original monitoring image. Step S12 can be used to determine the original area corresponding to the difference area in the original monitoring image, and to determine the spectral features, texture features, and shape features of the difference area and the original area respectively. Step S13 can be used to perform difference analysis and calculation on the spectral features, texture features, and shape features of the difference area and the original area to obtain the difference value, and to determine the difference area with the difference value greater than a preset threshold as an abnormal area in the area to be monitored. The specific method for obtaining the difference value can be of various forms known to those skilled in the art. In one example of the present invention, it can include, for example... Figure 3 The steps are shown. Specifically: In step S21, the average spectral index of the difference region and the original region is determined based on spectral characteristics, and the difference between the average spectral index of the difference region and the average spectral index of the original region is determined to obtain the change in spectral index. In step S22, the average contrast of the difference region and the original region is determined based on the texture features, and the difference between the average contrast of the difference region and the average contrast of the original region is determined to obtain the change in average contrast. In step S23, the compactness of the difference region and the original region is determined based on shape features, and the difference between the compactness of the difference region and the compactness of the original region is determined to obtain the compactness change amount; In step S24, the changes in spectral index, average contrast, and compactness are normalized to obtain normalized values ​​for each feature, and the preset weights for each feature are determined. In step S25, the normalized values ​​of each feature are weighted and added together with their corresponding preset weights to obtain the difference value.

[0025] Specifically, the changes in three core remote sensing features—spectral, texture, and shape—are systematically integrated. The changes in spectral indices reflecting changes in the composition of land cover are obtained by calculating the difference between the difference region and the original region in average spectral indices (such as NDVI and NDWI). The changes in average contrast, characterizing changes in surface roughness and fragmentation, are obtained by comparing the differences in average contrast between the two regions. The changes in compactness, describing changes in the regularity of land parcel morphology and the complexity of boundaries, are extracted by comparing compactness indices. The changes in each feature are normalized to eliminate dimensional differences, making them comparable, and appropriate preset weights are assigned to each feature based on prior geoscientific knowledge. Finally, a weighted summation model is used to fuse the normalized multi-feature changes into a single difference value. This step transforms subjective and ambiguous image change interpretation into objective and accurate numerical assessment, significantly improving the repeatability and consistency of anomaly identification. Through multi-feature fusion decision-making, it overcomes the limitations of single feature indicators being susceptible to interference in complex environments, enhancing the robustness and noise resistance of anomaly detection. The weighted model allows for flexible adjustments based on the differences in sensitive features of different types of geological hazards, making the assessment framework both universal and targeted.

[0026] Step S3 can be used to determine surface deformation data of anomaly areas based on BeiDou satellites, and to analyze the surface deformation data to determine the deformation data characteristics of the anomaly areas. The specific method for determining the deformation data characteristics of anomaly areas can be of various forms known to those skilled in the art. In one example of the present invention, it may include, for example... Figure 4 The steps are shown. Specifically: In step S31, surface deformation data of the abnormal area is determined based on BeiDou satellite, and a data change curve with time progress is constructed based on the surface deformation data; In step S32, the deformation rate, deformation acceleration, and cumulative deformation are determined from the data change curve, and the deformation rate, deformation acceleration, and cumulative deformation are identified as deformation data characteristics of the abnormal region.

[0027] Specifically, continuous surface deformation data of the anomalous area is acquired based on BeiDou satellites, and a data curve of deformation changing over time is constructed. From this curve, three core deformation data features are extracted through mathematical analysis: deformation rate (i.e., the first derivative of the curve, reflecting the speed of movement), deformation acceleration (i.e., the second derivative of the curve, revealing whether the movement trend is acceleration, uniformity, or deceleration), and cumulative deformation (reflecting the total amount of deformation during the monitoring period). This step realizes a leap from static and discrete monitoring to dynamic and continuous monitoring, intuitively displaying the complete activity trajectory of the disaster body through the time curve, providing a data foundation for understanding its evolution law; it completes the extraction of information from raw data to decision features, condensing massive amounts of time-series data into feature parameters with clear physical meaning and early warning value, significantly improving data usability and interpretability; and it provides quantitative and standardized input for risk assessment, enabling objective comparison and classification of deformation activities in different regions and at different times based on unified indicators such as rate and acceleration.

[0028] Step S4 can be used to assess the degree of deformation in anomaly regions based on deformation data characteristics, thereby obtaining an assessment value for the degree of deformation in the anomaly regions. The specific method for obtaining the assessment value for the degree of deformation in anomaly regions can be of various forms known to those skilled in the art. In one example of the present invention, it may include, for example... Figure 5 The steps are shown. Specifically: In step S41, the reference deformation rate, reference deformation acceleration, and reference cumulative deformation are determined, and the differences between the deformation rate and the reference deformation rate, the deformation acceleration and the reference deformation acceleration, and the cumulative deformation and the reference cumulative deformation are calculated respectively. In step S42, the obtained differences are evaluated and values ​​are obtained to obtain deformation rate evaluation value, deformation acceleration evaluation value and cumulative deformation evaluation value, and the preset weight of each deformation data feature is determined. In step S43, the evaluation values ​​of each deformation data feature and the corresponding preset weights are weighted and summed to obtain the deformation degree evaluation value of the abnormal area.

[0029] Specifically, the three core features currently acquired through monitoring—deformation rate, acceleration, and cumulative deformation—are compared with preset geological safety thresholds or regional historical stability benchmarks (i.e., benchmark deformation rate, benchmark deformation acceleration, and benchmark cumulative deformation), and their relative differences are calculated. The degree of deviation of each feature from the normal range is quantified through a computational model. Based on the physical significance of each deformation feature's contribution to disaster risk, the three assessment values ​​are weighted and fused to generate a comprehensive deformation degree assessment value. This step transforms the assessment from absolute measurement to relative anomaly, effectively eliminating the influence of regional geological background differences through benchmark comparison, making the assessment results more universal and comparable. Secondly, by normalizing the assessment function, features with different dimensions and physical meanings are uniformly transformed into dimensionless risk scores, laying a mathematical foundation for multi-indicator fusion decision-making. The weighted fusion model scientifically integrates features reflecting different aspects of the disaster dynamic process, assigning higher weight to deformation acceleration, making the assessment model extremely sensitive to accelerated deformation signals characterizing instability precursors, significantly improving the model's early warning foresight.

[0030] Step S5 can be used to determine the geological hazard index of the area to be monitored based on the deformation degree assessment value and geological hazard type of each abnormal area, and to generate a corresponding early warning strategy based on the geological hazard index. The specific method for determining the geological hazard index of the area to be monitored can be of various forms known to those skilled in the art. In one example of the present invention, it may include, for example... Figure 6 The steps are shown. Specifically: In step S51, the disaster coefficient of each abnormal region is determined based on the geological disaster type of each abnormal region, and the area of ​​each abnormal region is determined. In step S52, the geological disaster index of the area to be monitored is calculated based on the disaster coefficient, area and deformation degree assessment values ​​of each abnormal area.

[0031] Specifically, different disaster coefficients are assigned to different types of hazards based on a pre-defined mapping relationship to reflect the differences in their inherent disaster-causing capabilities. Simultaneously, the area of ​​each anomalous region is obtained to characterize the spatial extent of its potential impact. This is then combined with the deformation assessment value obtained from the preceding steps to reflect the strength of its current activity. A comprehensive geological hazard index is calculated. This step upgrades risk assessment from discrete hazard points to continuous regional surfaces, generating a single quantitative indicator that can macroscopically characterize the overall risk level of the entire monitored area, providing a direct basis for regional risk comparison and management priority allocation. Through multi-dimensional factor fusion, it overcomes the one-sidedness of relying solely on deformation degree or only considering disaster type, making the risk assessment results more comprehensive and reliable by simultaneously taking into account the disaster background, spatial scale, and dynamic evolution. It provides scientific decision support for the spatial optimization of early warning resources. Decision-makers can adopt differentiated monitoring intensity and early warning strategies for different regions based on the index level, thereby achieving efficient and precise allocation of disaster prevention and mitigation resources.

[0032] In Figure 6 In the method shown, step S51 can be used to determine the hazard coefficient of each anomalous region based on the geological hazard type of each anomalous region, and to determine the area of ​​each anomalous region. The specific method for determining the hazard coefficient of each anomalous region can be of various forms known to those skilled in the art. In one example of the present invention, it may include, for example... Figure 7 The steps are shown. Specifically: In step S61, a preset disaster coefficient-geological disaster type correspondence is set in advance. For each geological disaster type, the preset disaster coefficient-geological disaster type correspondence is associated with a corresponding preset disaster coefficient. In step S62, the geological hazard type of the abnormal area is determined, and based on the mapping relationship between the geological hazard type of the abnormal area and the preset hazard coefficient-geological hazard type correspondence, the preset hazard coefficient corresponding to the geological hazard type is selected as the hazard coefficient of the abnormal area.

[0033] Specifically, a pre-constructed correspondence between a hazard coefficient and a geological hazard type is established. For each typical geological hazard type, such as landslides, collapses, debris flows, and ground subsidence, a pre-constructed hazard coefficient representing its inherent relative risk level is scientifically assigned based on historical disaster statistics, causative mechanisms, movement characteristics, and disaster patterns. Once the geological hazard type of an abnormal area is identified, the corresponding pre-constructed hazard coefficient is automatically and unambiguously retrieved and assigned through this mapping relationship, serving as the hazard coefficient for that area. This step achieves a seamless transition from qualitative classification to quantitative assignment, directly transforming the identification of the hazard into standardized risk input parameters usable in mathematical models, ensuring the automation and consistency of the assessment process. It also ensures the scientific rigor and consistency of risk assessment, as the coefficients are pre-set based on historical data and expert knowledge, avoiding the potential subjectivity and inconsistency of manual ad hoc judgments, making assessment results from different regions and periods comparable. Furthermore, it significantly improves assessment efficiency and system robustness, enabling rapid response by replacing complex real-time calculations with a lookup-based mapping.

[0034] In step S52, the geological hazard index of the monitored area is calculated based on the disaster coefficient, area, and deformation degree assessment values ​​of each abnormal region. Specifically, the geological hazard index can be obtained according to formula (1). (1) Where Z is the geological disaster index of the area to be monitored, ki is the disaster coefficient of the i-th abnormal area, mi is the area of ​​the i-th abnormal area, Pi is the deformation degree assessment value of the i-th abnormal area, and n is the number of abnormal areas.

[0035] Step S5 can be used to determine the geological hazard index of the area to be monitored based on the deformation degree assessment value and geological hazard type of each abnormal area, and generate a corresponding early warning strategy based on the geological hazard index. The specific method for generating the corresponding early warning strategy can be of various forms known to those skilled in the art. In one example of the present invention, it may include, for example... Figure 8 The steps are shown. Specifically: In step S71, a first preset index and a second preset index are determined, and an early warning strategy is generated based on the relationship between the geological disaster index and the first preset index and the second preset index. In step S72, if the geological disaster index is less than or equal to the first preset index, the generated early warning strategy is to issue a blue early warning and remind that the current monitored area is a low-risk area. In step S73, if the geological disaster index is greater than the first preset index and less than the second preset index, the generated early warning strategy is to issue a yellow warning and remind that the current monitored area is a medium-risk area. In step S74, if the geological disaster index is greater than or equal to the second preset index, the generated early warning strategy is to issue a red warning and remind the current monitored area that it is a high-risk area.

[0036] Specifically, the calculated comprehensive geological hazard index is automatically compared with two preset indices. If the geological hazard index is lower than or equal to the first preset index, it is judged as low risk, triggering a blue alert, with the strategy focusing on routine monitoring and information dissemination. If the geological hazard index is between the two preset indices, it is judged as medium risk, triggering a yellow alert, with the strategy upgraded to strengthening monitoring, patrols, and preparations. If the geological hazard index reaches or exceeds the second preset index, it is judged as high risk, immediately triggering the highest level red alert, with the strategy focusing on emergency response and disaster prevention. This step achieves thresholding and automation of risk management, replacing subjective judgment with objective data to ensure consistent alert activation standards and rapid response, eliminating human delays or oversights. It constructs a precise action framework for tiered response, with different colored alerts directly associated with differentiated response measures and resource allocation plans, enabling limited disaster prevention resources to focus on the areas and time periods with the highest risk, greatly improving emergency response efficiency. The use of blue, yellow, and red colors to intuitively represent the overall risk status of the region greatly reduces the understanding threshold for decision-makers and the public, facilitating rapid communication and coordinated action.

[0037] On the other hand, embodiments of the present invention also provide a geological disaster monitoring and early warning system based on BeiDou signals, which can, as Figure 9 As shown, it includes: The extraction module is used to acquire real-time monitoring images of the area to be monitored and extract the spectral features, texture features, and shape features of the real-time monitoring images; The analysis module is used to analyze the monitored real-time images based on spectral features, texture features, and shape features to identify abnormal areas and corresponding geological disaster types in the area to be monitored. The determination module is used to determine the surface deformation data of the abnormal area based on the Beidou satellite, and to analyze the surface deformation data to determine the deformation data characteristics of the abnormal area; The evaluation module is used to assess the degree of deformation in abnormal areas based on the characteristics of deformation data, and obtain the evaluation value of the degree of deformation in abnormal areas; The generation module is used to determine the geological hazard index of the area to be monitored based on the deformation degree assessment value and geological hazard type of each abnormal area, and to generate corresponding early warning strategies based on the geological hazard index.

[0038] Through the above technical solution, this invention provides a geological disaster monitoring and early warning method and system based on BeiDou signals. Compared with the prior art, its advantages are as follows: This invention achieves automated interpretation and change detection by fusing spectral, texture, and shape multidimensional features from real-time monitored images. It can efficiently screen out early anomalies in land cover and morphology over a wide area, overcoming the limitations of traditional manual patrols, such as limited field of vision, low efficiency, and difficulty in discovering hidden hazards. It advances hazard identification from the period of significant deformation to the period of slight surface change. Furthermore, it performs quantitative diagnosis on the screened abnormal areas using high-precision deformation data, achieving a deeper understanding from identifying surface anomalies to assessing internal mechanical processes. This significantly improves the accuracy of target locking and the scientific nature of risk assessment, and effectively reduces the false alarm rate. This invention innovatively extracts temporal deformation characteristics into calculable deformation degree assessment values, and further integrates disaster type information to construct a comprehensive regional geological disaster index. This transforms the originally vague qualitative risk judgment, which relies on personal experience, into a grade evaluation based on unified quantitative standards, thereby achieving objectivity and comparability of risk assessment. This invention, based on a quantified geological disaster index, can automatically match and generate tiered early warning strategies, changing the traditional one-size-fits-all approach to early warning. This makes early warning information dissemination more targeted and emergency resource allocation more optimized, forming a closed-loop management process of intelligent monitoring, automatic assessment, precise early warning, and strategy feedback, which greatly improves the intelligence level of geological disaster risk prevention and control and the efficiency of emergency response.

[0039] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0040] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0041] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0042] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0043] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0044] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0045] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0046] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0047] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A geological disaster monitoring and early warning method based on BeiDou signals, characterized in that, The geological disaster monitoring and early warning methods include: Acquire real-time images of the area to be monitored, and extract spectral, texture, and shape features from the real-time images; Based on the analysis of spectral features, texture features, and shape features, the monitored real-time images are identified to determine the abnormal areas and corresponding geological hazard types in the area to be monitored; Based on the BeiDou satellite, surface deformation data of the abnormal area was determined, and the surface deformation data was analyzed to determine the deformation data characteristics of the abnormal area. The degree of deformation in abnormal areas is assessed based on the characteristics of deformation data, and the deformation degree assessment value of abnormal areas is obtained. The geological hazard index of the area to be monitored is determined based on the deformation degree assessment value and geological hazard type of each abnormal area, and the corresponding early warning strategy is generated based on the geological hazard index.

2. The geological disaster monitoring and early warning method according to claim 1, characterized in that, Based on the analysis of spectral, texture, and shape features of the monitored images, abnormal areas and corresponding geological hazard types in the monitored area are identified, including: Determine the original monitoring images of the pre-defined area to be monitored, and compare the original monitoring images with the monitoring images to identify the discrepancies between the monitoring images and the original monitoring images; In the original monitoring images, the original regions corresponding to the regions of difference are identified, and the spectral, texture, and shape features of the regions of difference and the original regions are determined respectively. Difference analysis and calculation are performed on the spectral, texture and shape characteristics of the difference region and the original region to obtain the difference value. The difference region with the difference value greater than the preset threshold is identified as the abnormal region in the area to be monitored. The spectral, texture, and shape features of the anomalous area are determined, and these features are matched with the preset geological hazard types in the preset geological hazard database to obtain the geological hazard type corresponding to the anomalous area.

3. The geological disaster monitoring and early warning method according to claim 2, characterized in that, Difference analysis and calculation are performed on the spectral, textural, and shape characteristics of the difference region and the original region to obtain difference values, including: The average spectral index of the difference region and the original region is determined based on spectral characteristics, and the difference between the average spectral index of the difference region and the average spectral index of the original region is determined to obtain the change in spectral index. The average contrast of the difference region and the original region is determined based on the texture features, and the difference between the average contrast of the difference region and the average contrast of the original region is determined to obtain the change in average contrast. Based on shape features, the compactness of the difference region and the original region is determined, and the difference between the compactness of the difference region and the compactness of the original region is determined to obtain the amount of compactness change; The changes in spectral index, average contrast, and compactness are normalized to obtain normalized values ​​for each feature, and the preset weights for each feature are determined. The difference value is obtained by weighting the normalized value of each feature with its corresponding preset weight.

4. The geological disaster monitoring and early warning method according to claim 1, characterized in that, Based on BeiDou satellite data, surface deformation data of anomaly areas were identified, and the data was analyzed to determine the deformation characteristics of the anomaly areas, including: The surface deformation data of the abnormal area was determined based on the Beidou satellite, and a data change curve with time progress was constructed based on the surface deformation data; Deformation rate, deformation acceleration, and cumulative deformation are determined from the data change curves, and these three parameters are identified as deformation data characteristics of the abnormal region.

5. The geological disaster monitoring and early warning method according to claim 4, characterized in that, The degree of deformation in abnormal regions is assessed based on deformation data characteristics, resulting in an assessment value for the degree of deformation in the abnormal regions, including: Determine the reference deformation rate, reference deformation acceleration, and reference cumulative deformation, and calculate the differences between the deformation rate and the reference deformation rate, the deformation acceleration and the reference deformation acceleration, and the cumulative deformation and the reference cumulative deformation, respectively. The obtained differences are evaluated and values ​​are taken respectively to obtain the deformation rate evaluation value, deformation acceleration evaluation value and cumulative deformation evaluation value, and the preset weight of each deformation data feature is determined. The deformation degree assessment value of the abnormal area is obtained by weighting and summing the evaluation values ​​of each deformation data feature with the corresponding preset weights.

6. The geological disaster monitoring and early warning method according to claim 5, characterized in that, Based on the deformation assessment values ​​and geological hazard types of each anomaly region, the geological hazard index of the area to be monitored is determined, including: The disaster coefficient of each anomalous region is determined based on the geological disaster type of each anomalous region, and the area of ​​each anomalous region is determined accordingly; The geological hazard index of the monitored area is calculated based on the disaster coefficient, area and deformation degree assessment values ​​of each abnormal area.

7. The geological disaster monitoring and early warning method according to claim 6, characterized in that, The hazard coefficient of each anomalous region is determined based on the geological hazard type of each anomalous region, and the area of ​​each anomalous region is also determined, including: A pre-defined correspondence between preset disaster coefficients and geological disaster types is established. For each geological disaster type, a corresponding preset disaster coefficient is associated with it. The geological hazard types in the anomalous area are determined, and based on the mapping relationship between the geological hazard types in the anomalous area and the pre-set hazard coefficient-geological hazard type correspondence, the pre-set hazard coefficient corresponding to the geological hazard type is selected as the hazard coefficient of the anomalous area.

8. The geological disaster monitoring and early warning method according to claim 6, characterized in that, Based on the disaster coefficient, area, and deformation degree assessment values ​​of each anomaly region, the geological disaster index of the monitored area is calculated, including: The geological hazard index is obtained according to formula (1). ，（1） Where Z is the geological disaster index of the area to be monitored, ki is the disaster coefficient of the i-th abnormal area, mi is the area of ​​the i-th abnormal area, Pi is the deformation degree assessment value of the i-th abnormal area, and n is the number of abnormal areas.

9. The geological disaster monitoring and early warning method according to claim 1, characterized in that, Early warning strategies based on geological hazard indices include: A first preset index and a second preset index are determined, and an early warning strategy is generated based on the relationship between the geological disaster index and the first preset index and the second preset index. If the geological disaster index is less than or equal to the first preset index, the generated early warning strategy is to issue a blue early warning and remind that the current monitored area is a low-risk area; If the geological disaster index is greater than the first preset index but less than the second preset index, the generated early warning strategy is to issue a yellow warning and remind that the current monitored area is a medium-risk area. If the geological disaster index is greater than or equal to the second preset index, the generated early warning strategy will be to issue a red warning and remind that the current monitored area is a high-risk area.

10. A geological disaster monitoring and early warning system based on BeiDou signals, characterized in that, include: The extraction module is used to acquire real-time monitoring images of the area to be monitored and extract the spectral features, texture features, and shape features of the real-time monitoring images; The analysis module is used to analyze the monitored real-time images based on spectral features, texture features, and shape features to identify abnormal areas and corresponding geological disaster types in the area to be monitored. The determination module is used to determine the surface deformation data of the abnormal area based on the Beidou satellite, and to analyze the surface deformation data to determine the deformation data characteristics of the abnormal area; The evaluation module is used to assess the degree of deformation in abnormal areas based on the characteristics of deformation data, and obtain the evaluation value of the degree of deformation in abnormal areas; The generation module is used to determine the geological hazard index of the area to be monitored based on the deformation degree assessment value and geological hazard type of each abnormal area, and to generate corresponding early warning strategies based on the geological hazard index.

Images