Big data-based glacial lake outburst risk evaluation, early warning and decision-making method and system

Abstract

The invention relates to the technical field of glacial lake outburst risk management, in particular to a glacial lake outburst risk evaluation, early warning and decision-making method and system based on big data, and the method comprises the steps: obtaining laser radar, satellite optical images and SAR data, extracting the ice layer thickness, water level change and water body color change of a glacial lake region, analyzing the ice layer structure in combination with SAR, and generating glacial lake depth change data. According to the invention, by acquiring the laser radar, the satellite optical image and the SAR data and combining the spatial weighted fusion and the corrected ice lake depth change data, the ice lake depth change can be identified more accurately, so that monitoring data with higher precision can be provided for ice lake stability risk assessment. The real-time meteorological data and the depth change of the ice lake are combined and analyzed, and the stability threshold value of the ice layer is adjusted, so that the stability risk result of the ice lake can reflect more dynamic and meticulous environment change.

Description

Technical Field

[0001] The present invention relates to the technical field of glacial lake outburst risk management, and particularly to a method and system for evaluating and warning decision-making of glacial lake outburst hazards based on big data. Background Art

[0002] The technical field of glacial lake outburst risk management includes related research on monitoring, evaluating, and warning the possibility of glacial lake outbursts using various technical means. With the intensification of climate change, the risk of glacial lake outburst disasters in alpine mountainous areas has gradually become an important issue for disaster prevention and reduction. The risk assessment and warning decision-making system for glacial lake outbursts plays an increasingly prominent role in preventing this natural disaster. This technical field involves the collection and analysis of remote sensing data, big data processing, the establishment of risk assessment models, and the development of emergency response systems. The core technologies include using remote sensing means such as satellite remote sensing images, lidar, and synthetic aperture radar to conduct long-term monitoring of the changes in glacial lakes, analyzing the distribution, dynamic changes, and evolution laws of glacial lakes, further evaluating the risk of glacial lake outbursts, and ultimately achieving targeted early warning and decision-making support.

[0003] Among them, the method for evaluating and warning decision-making of glacial lake outburst hazards based on big data refers to using big data analysis means to comprehensively evaluate the long-term changes of glacial lakes in the research area and constructing an outburst hazard evaluation model. The technical matters targeted by this patent include using multi-source data such as remote sensing data, meteorological data, and geographical information, combined with the historical change records of glacial lakes, to establish a multi-dimensional risk assessment model to evaluate the possibility of glacial lake outbursts. In addition, through big data analysis methods, the patent solution adopts technical means of real-time monitoring and dynamic tracking in the identification and prediction of glacial lake outburst risks, systematically classifies the risk levels of glacial lake disasters in the region and predicts outbursts, and then provides decision-making support. The application of these methods combines big data technology and long-term monitoring to provide a more accurate theoretical basis and technical guarantee for the risk management of glacial lake outbursts in alpine mountainous areas.

[0004] Although the prior art can monitor the dynamic changes of glacial lakes through remote sensing data and meteorological data, there are still certain limitations in the actual application process. Since most of the prior art relies on a single data source of glacial lakes and relatively rough evaluation models, the adaptability in dealing with complex environmental changes is poor. The monitoring of the changes in glacial lake depth and stability mostly depends on static data, ignoring the impact of real-time meteorological changes on the ice layer, which makes the traditional methods unable to make timely and effective adjustments in the face of extreme weather or rapidly changing environmental conditions. Due to the deficiencies in data fusion and model correction, the evaluation and prediction of glacial lake outburst often lag behind, and cannot provide sufficiently accurate information for emergency response. More critically, it is difficult for the prior art to accurately predict the specific outburst path, resulting in the difficulty in implementing early warning and intervention measures before the disaster occurs, thus affecting the overall effect of disaster prevention and reduction. For example, when the climate changes violently, the dynamic changes in glacial lake depth may exceed the scope of existing monitoring, resulting in the failure to detect potential outburst risks in time, and ultimately leading to serious consequences. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the embodiments of the present invention provide a method for evaluating, warning and making decisions on the risk of glacial lake outburst based on big data. The technical solution is as follows: A method for evaluating, warning and making decisions on the risk of glacial lake outburst based on big data, comprising the following steps: S1: Obtain lidar, satellite optical images and SAR data, extract the ice layer thickness, water level change and water body color change in the glacial lake area, analyze the ice layer structure in combination with SAR, and generate glacial lake depth change data; S2: Perform spatial weighted fusion on the glacial lake depth change data and correct the errors, identify the glacial lake depth change according to the corrected data, and obtain the monitoring result of the glacial lake depth change; S3: According to the monitoring result of the glacial lake depth change and real-time meteorological data, analyze the impact of environmental factors in the glacial lake area on the ice layer, adjust the stability threshold of the ice layer, and generate the glacial lake stability risk result; S4: Based on the glacial lake stability risk result, simulate the outburst path under each environmental condition, analyze the correlation between environmental factors, glacial lake slope, soil and the outburst path, predict the outburst path under each climate and environmental condition, and obtain the outburst path prediction result; S5: Evaluate the outburst risk index according to the outburst path prediction result, compare it with the preset outburst risk threshold, screen the risk areas higher than the preset outburst risk threshold, generate warning level, warning area and recommended measure information, and obtain the outburst risk warning decision information.

[0006] The improvements of the present invention are as follows. The ice lake depth change data includes ice layer thickness, water level change, water body color change, and ice layer structure analysis. The ice lake depth change monitoring results include depth change and monitoring data correction. The ice lake stability risk results are ice layer stability assessment and risk analysis results. The predicted results of the breach path include the breach path, the correlation analysis between environmental factors and the breach path, and the simulation of the breach path under climate and environmental conditions. The early warning decision-making information for breach danger includes breach risk assessment indicators and decision support information.

[0007] The improvements of the present invention are as follows. Obtain lidar, satellite optical images, and SAR data, extract the ice layer thickness, water level change, and water body color change in the ice lake area, and combine SAR to analyze the ice layer structure. The specific steps for generating the ice lake depth change data are as follows: S101: Obtain lidar, satellite optical images, and SAR data, adjust the geospatial coordinates of each data point in the lidar data, and correct the pixel values in the satellite optical images, and adjust the brightness and contrast of the images to obtain the corrected data; S102: Based on the corrected data, extract the ice layer thickness, ice lake water level, and water body color in the ice lake area, perform pixel-by-pixel analysis on the data images, obtain the thickness value of the ice layer and the dynamic color change data of the water body, and obtain the ice lake area change data; S103: According to the ice lake area change data and referring to the SAR data analysis of the ice layer structure characteristics, obtain the internal structure change pattern of the ice layer, and compare and fuse the data with the extracted water level change and ice layer thickness data to generate the ice lake depth change data.

[0008] The improvements of the present invention are as follows. Perform spatial weighted fusion on the ice lake depth change data, correct the errors, and identify the ice lake depth change based on the corrected data. The specific steps for obtaining the ice lake depth change monitoring results are as follows: S201: According to the ice lake depth change data, the terrain, ice layer thickness, and water level change in the ice lake area, perform spatial allocation and weighting processing on the depth data in the ice lake area, adjust the data through spatial weighted fusion, and generate a weighted data set; S202: Based on the weighted data set, use the average value of the ice layer thickness and the change trend of the water level as the correction benchmark to correct the errors in the data to obtain the corrected data; S203: Refer to the spatial weights of the weighted data set for the corrected data to identify the temporal change trend and spatial variation of the ice lake depth data, analyze the depth change trend in the ice lake area, obtain the corresponding change data, and generate the ice lake depth change monitoring results.

[0009] The improvements of the present invention are as follows. For the weighted calculation of depth, the formula is used: ; Among them, is the weighted value of the depth, is the weight of the ice layer thickness, is the weight of the water level change, is the influence weight of the terrain, is the ice layer thickness, is the water level change, is the value of the influence of the terrain; For the corrected depth data, the formula is used: ; Among them, is the corrected depth data, is the preliminary depth data, is the average ice layer thickness, is the correction coefficient.

[0010] The improvement of the present invention is that, according to the monitoring results of the ice lake depth change and the real-time meteorological data, analyzing the influence of the environmental factors in the ice lake area on the ice layer, adjusting the stability threshold of the ice layer, and generating the specific steps of the ice lake stability risk result are as follows: S301: According to the monitoring results of the ice lake depth change, obtain real-time meteorological data, including precipitation, temperature, and wind speed, as the basic data for analyzing environmental factors, and obtain environmental factor data; S302: Based on the environmental factor data, analyze the influence of the area, slope direction, temperature, and characteristics of dangerous ice bodies of the parent glacier on the stability of the ice lake, calculate the change trend of the parent glacier under each environmental factor with reference to precipitation, temperature, and wind speed factors, evaluate the role of each environmental factor on the stability of the ice lake, and generate the analysis result of the environmental factor and the influence of the parent glacier; S303: Evaluate the stability of the moraine dam according to the analysis result of the environmental factor and the influence of the parent glacier, analyze the influence of the backwater slope gradient on erosion, evaluate the stability of loose sediments, identify the risks of cracks, piping, and ablation of dead ice, calculate the change trend of the dam body permeability, predict the precursor of ice lake outburst, and adjust the stability threshold of the ice lake ice layer to generate the ice lake stability risk result.

[0011] The improvement of the present invention is that, based on the ice lake stability risk result, simulating the outburst path under each environmental condition, analyzing the correlation between environmental factors, ice lake slope, soil and the outburst path, and predicting the outburst path under each climate and environmental condition to obtain the specific steps of the outburst path prediction result are as follows: S401: Based on the ice lake stability risk result, use the environmental factor data associated with the outburst path simulation as the basic data for outburst path prediction, and obtain environmental factor adjustment data; S402: Adjust the data based on the environmental factors, analyze the correlation between the environmental factors, ice lake slope, soil type and the breach path, obtain the key factors of the ice lake breach path, and generate the analysis result of the key factors of the breach path; S403: According to the analysis result of the key factors of the breach path, and referring to the adjusted data of the environmental factors, predict the ice lake breach path under each climate and environmental condition, call the ice lake geographic information and climate data for path calculation, and generate the breach path prediction result.

[0012] The improvement of the present invention is that, according to the breach path prediction result, evaluate the breach risk index, compare it with the preset breach risk threshold, screen the risk areas higher than the preset breach risk threshold, generate the warning level, warning area, and recommended measure information, and obtain the specific steps of the breach danger warning decision-making information as follows: S501: According to the breach path prediction result, obtain the breach risk assessment index of the corresponding area, compare the assessment index with the preset breach risk threshold, screen the risk areas higher than the breach risk threshold, calculate the breach risk value of the risk areas, and obtain the risk coefficient data set; S502: Classify the breach risk value according to intervals based on the risk coefficient data set, and assign the corresponding warning level to each area according to the risk interval to obtain the warning level of the breach risk area; S503: According to the warning level of the breach risk area, generate the corresponding warning measure information, refer to the breach risk characteristics of the risk area, formulate the corresponding emergency response plan for each area, and obtain the breach danger warning decision-making information.

[0013] The improvement of the present invention is that, for calculating the breach risk value of the risk area, the formula is used: ; Wherein, represents the breach risk value, represents the destructive influence factor of the th potential breach area, represents the probability of the breach occurring, represents the exposure degree within the corresponding area, represents the emergency resource coverage coefficient of the area, represents the environmental obstacle factor, is the total number of risk areas.

[0014] The ice lake breach danger evaluation and warning decision-making system based on big data, the system includes: The data acquisition and processing module obtains lidar, satellite optical imagery, and SAR data, performs geometric and radiometric corrections, extracts data on ice thickness and water level changes in the ice lake area, analyzes the color changes of the ice lake water body, analyzes the ice layer structure in combination with SAR data, and generates data on ice lake depth changes; The depth change monitoring module spatially weights and fuses the data based on the ice lake depth change data, corrects errors, identifies ice lake depth changes through the corrected data, and obtains the ice lake depth change monitoring results; The environmental factor analysis module obtains real-time meteorological data according to the ice lake depth change monitoring results, and analyzes the impact of environmental factors such as precipitation, temperature, and wind speed in the ice lake area on the stability of the ice lake ice layer, adjusts the stability threshold of the ice lake ice layer, and generates an ice lake stability risk assessment result; The breach path simulation module simulates the ice lake breach paths under different environmental conditions according to the ice lake stability risk assessment results, analyzes the risks of the ice lake breach paths in combination with factors such as environmental data, ice lake slope, and soil structure, and obtains the breach path prediction results; The risk assessment and early warning module obtains multi-level breach risk assessment indicators according to the breach path prediction results, compares them with the set breach risk thresholds, screens out high-risk areas, generates information such as early warning levels, early warning areas, and response measures based on the risk areas, and obtains the breach hazard early warning decision-making information.

[0015] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include: In the present invention, by obtaining lidar, satellite optical imagery, and SAR data, and combining spatially weighted fusion and the corrected ice lake depth change data, the ice lake depth changes can be identified more accurately, thereby providing higher-precision monitoring data for the ice lake stability risk assessment. The combined analysis of real-time meteorological data and ice lake depth changes, by adjusting the stability threshold of the ice layer, enables the ice lake stability risk results to reflect more dynamic and detailed environmental changes. This refined risk assessment further improves the accuracy of the breach path simulation. Considering the comprehensive effects of environmental factors, ice lake slope, soil, etc., it can better predict the breach path and analyze the likelihood of breach under climate and environmental conditions. In addition, the prediction of the breach path can further evaluate the breach risk indicators, and through the screening of areas above the preset risk threshold, provide accurate early warning levels, early warning areas, and response measures. Through this series of optimizations, not only the prediction accuracy and real-time response ability of the ice lake breach risk are improved, but also the overall risk management decision-making is more scientific and targeted, which helps to identify potential disasters in advance and formulate effective response strategies. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0017] Figure 1 is the method flowchart of the present invention; Figure 2 is the schematic diagram of the refined process of step S1 of the present invention; Figure 3 is the schematic diagram of the refined process of step S2 of the present invention; Figure 4 is the schematic diagram of the refined process of step S3 of the present invention; Figure 5 is the schematic diagram of the refined process of step S4 of the present invention; Figure 6 is the schematic diagram of the refined process of step S5 of the present invention; Figure 7 is the system module diagram of the present invention. Detailed implementation manners

[0018] The following will describe the technical solutions in the present invention with reference to the accompanying drawings.

[0019] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as more preferred or more advantageous than other embodiments or design solutions. Exactly, the use of the word "example" aims to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0020] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meaning they express is the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meaning they express is the same.

[0021] In the embodiments of the present invention, sometimes subscripts such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0022] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0023] Please refer to Figure 1 , the present invention provides a technical solution: a method for evaluating and warning decision-making on the risk of ice lake outburst based on big data, including the following steps: S1: Obtain lidar, satellite optical images and SAR data, extract the ice layer thickness, water level change and water body color change in the ice lake area, analyze the ice layer structure in combination with SAR, and generate ice lake depth change data; S2: Perform spatial weighted fusion on the ice lake depth change data and correct the error. Identify the ice lake depth change based on the corrected data to obtain the monitoring result of the ice lake depth change; S3: Analyze the influence of environmental factors in the ice lake area on the ice layer according to the monitoring result of the ice lake depth change and real-time meteorological data, adjust the stability threshold of the ice layer, and generate the ice lake stability risk result; S4: Based on the ice lake stability risk result, simulate the outburst path under each environmental condition, analyze the correlation between environmental factors, ice lake slope, soil and the outburst path, predict the outburst path under each climate and environmental condition, and obtain the outburst path prediction result; S5: Evaluate the outburst risk index according to the outburst path prediction result, compare it with the preset outburst risk threshold, screen the risk areas higher than the preset outburst risk threshold, generate warning level, warning area, and recommended measure information, and obtain the outburst risk warning decision-making information.

[0024] The ice lake depth change data is the ice layer thickness, water level change, water body color change, and ice layer structure analysis. The monitoring result of the ice lake depth change includes depth change and monitoring data correction. The ice lake stability risk result is the ice layer stability assessment and risk analysis result. The outburst path prediction result includes the outburst path, the correlation analysis between environmental factors and the outburst path, and the simulation of the outburst path under climate and environmental conditions. The outburst risk warning decision-making information includes the outburst risk assessment index and decision support information.

[0025] Please refer to Figure 2 , the specific steps for obtaining lidar, satellite optical images and SAR data, extracting the ice layer thickness, water level change and water body color change in the ice lake area, and analyzing the ice layer structure in combination with SAR to generate ice lake depth change data are as follows: S101: Obtain lidar, satellite optical images and SAR data, adjust the geospatial coordinates of each data point in the lidar data, and correct the pixel values in the satellite optical image, and adjust the brightness and contrast of the image to obtain the corrected data; After obtaining lidar, satellite optical imagery, and SAR data, it is first necessary to adjust the geospatial coordinates of each data point in the lidar data to conform to the actual geographical location and correct the pixel values in the satellite optical imagery. During this process, the lidar data involves converting the geographical coordinates of each data point into a unified geographical standard coordinate system by comparing coordinate systems from different sources. Common practices include using the WGS84 or UTM coordinate systems. This process is completed through a georegistration algorithm, and common registration methods include the least squares method, affine transformation, or projective transformation, etc. For the correction of the pixel values in the satellite imagery, it is mainly through radiometric correction technology. This technology corrects the brightness values in the imagery by using the reflectance values of known ground control points and the radiometric characteristics of the sensor. During this process, it is assumed that the brightness values during satellite image acquisition are affected by various factors, such as the atmosphere, solar angle, etc. Therefore, standard ground reflectance values are needed to adjust the brightness of each pixel, usually by comparing the measured ground reflectance data. For example, for a specific pixel in a satellite imagery, assuming its initial brightness value is 200 and the ground reflectance corresponding to this pixel is 0.8, using the known standard reflectance value of 0.9, after calculating the adjustment coefficient, the brightness value of this pixel is corrected to obtain the corrected imagery data. During the correction, the brightness and contrast of the imagery are also appropriately adjusted to ensure that the imagery clarity meets the analysis requirements, which is usually achieved through methods such as histogram equalization or Gamma correction. In this way, geospatial data with high precision can be obtained, which can accurately reflect the true situation of the region. The data after this process can provide a reliable data basis for further analyzing the changes in the ice lake area.

[0026] S102: Based on the corrected data, extract the ice layer thickness, ice lake water level, and water body color in the ice lake area, perform pixel-by-pixel analysis on the data imagery to obtain the ice layer thickness value and the dynamic color change data of the water body, and obtain the ice lake area change data; When extracting the ice layer thickness, ice lake water level, and water body color in the ice lake area based on the corrected data, the image data is first analyzed pixel by pixel. In this process, the extraction of the ice layer thickness usually relies on the height information in the lidar data. Using the point cloud data provided by the lidar, the surface height and base height of the ice layer can be calculated, and thus the thickness of the ice layer can be obtained. The calculation process is as follows: Set the height of the ice point cloud as H1 and the height of the base point cloud as H2. Then the calculation formula for the ice layer thickness T is T = H1 - H2. This process requires point cloud data accurate to the millimeter level. By comparing the point cloud data at different positions, the ice layer thickness at different locations can be obtained. For example, if the surface height of the ice layer in a certain area is 500 meters and the base height is 470 meters, then the thickness of the ice layer in this area is 30 meters. The extraction of the water level is achieved by analyzing the water body color changes in the satellite images. These changes reflect the water level changes and are usually analyzed through the water body reflectance in the remote sensing images. In this process, the color changes of the water body are closely related to the water level changes. Based on this information, the rise and fall of the water level can be determined. The extraction of the water body color changes is mainly carried out through image processing algorithms. These algorithms identify the color differences at different water levels by calculating the changes in the RGB values of the images and conduct dynamic monitoring. For example, when the water level rises, the reflectance of the water body may increase and the color will become darker blue; conversely, it may become lighter. These changes can provide dynamic data support for the changes in the ice lake area.

[0027] S103: According to the ice lake area change data and with reference to the SAR data, analyze the structural characteristics of the ice layer, obtain the internal structural change pattern of the ice layer, and compare and fuse the data with the extracted water level change and ice layer thickness data to generate ice lake depth change data; Based on the data of the changes in the ice lake area and SAR data, analyzing the structural characteristics of the ice layer aims to obtain the internal structural change patterns of the ice layer. SAR data has the ability to penetrate, and can effectively obtain the structural information under the ice layer. During the analysis process, by comparing the SAR data at different time nodes, the changes in cracks, cavities, and areas with different densities inside the ice layer can be identified. The specific analysis methods include registering the SAR images taken at different times, and then analyzing the differences through change detection algorithms. Suppose at a certain time point, the SAR image shows obvious deformation of the ice layer in a certain area. Analysts can further use the change detection algorithm to calculate the change amount in this area, and then obtain the structural change pattern of the ice layer. For the comparison and fusion of water level changes and ice layer thickness data, a multiple regression model can be established, taking the water level change, ice layer thickness, and structural characteristics in the SAR data as input variables. Through regression analysis, the depth change of the ice layer can be calculated. Suppose in the model, the weight of the ice layer thickness is set to 0.5, the weight of the water level change is 0.3, and the weight of the structural characteristics of the SAR data is 0.2. Then, through the regression analysis formula, the depth change data of the ice lake can be obtained. Suppose at a certain time point, the ice layer thickness is 30 meters, the water level change is 2 meters, and the cavity density under the ice layer in this area obtained from the SAR data analysis is 0.4. Then, through the calculation of the regression model, the change amount of the ice lake depth is obtained as 5 meters. This process provides an accurate measurement basis for the depth change data of the ice lake.

[0028] Please refer to Figure 3 , the specific steps for spatially weighted fusion of the ice lake depth change data, correcting the errors, and identifying the ice lake depth change based on the corrected data to obtain the ice lake depth change monitoring results are as follows: S201: According to the terrain, ice layer thickness, and water level change in the ice lake area, spatially allocate and weight the depth data of the ice lake area for the ice lake depth change data, adjust the data through spatial weighted fusion, and generate a weighted data set; When spatially allocating and weighting the ice lake depth change data based on the terrain, ice layer thickness, and water level changes in the ice lake area, it is first necessary to obtain the spatial data of these influencing factors, compare and combine it with the ice lake depth change data, and perform weighting processing. In actual operations, terrain data usually comes from lidar or satellite data. By analyzing the characteristics of the terrain such as slope and undulation, the weights to be assigned to different regions during the weighting process can be determined. For example, if the slope at a certain location in the ice lake area is large and its impact on the water flow is significant, then a larger weight should be assigned to the depth data of that region. The ice layer thickness and water level changes are also important factors affecting the depth change. For example, areas with thicker ice layers may experience greater depth changes when the water level rises. Therefore, it is necessary to calculate the ice layer thickness and water level changes at different positions and fuse these data through weighting. When performing weighting processing, weight values with different parameters can be set. For example, the influence of the ice layer thickness on the ice lake depth is generally large, so its weight value is set relatively high, usually between 0.4 and 0.6; the water level change will affect the ice lake depth, but its influence degree is smaller than that of the ice layer thickness, so the weight value of the water level change can be set between 0.2 and 0.4; the weight value of the terrain influence is relatively low, usually set between 0.2 and 0.3. Assuming that in actual application, the weight of the ice layer thickness is , the weight of the water level change is , and the influence weight of the terrain is , the depth change data of each region is adjusted using the weighted average method. Assuming that the ice layer thickness at a certain region is meters, the water level change is meters, and the numerical value of the terrain influence is , then the weighted calculation formula for the depth is: ; For example, if the ice layer thickness at a certain region is meters, the water level change is meters, and the numerical value of the terrain influence is , then the depth change of this region is: ; Through this method, the ice lake depth data can be effectively adjusted to conform to the actual situation of the region.

[0029] S202: Based on the weighted data set, using the average value of the ice layer thickness and the change trend of the water level as the correction benchmark, correct the errors in the data to obtain the corrected data; When correcting the average ice thickness and water level change trend based on a weighted dataset as the correction benchmark, it is first necessary to calculate the average ice thickness and the trend of water level change through statistical methods, which will be used as the correction benchmark for data error correction. The average ice thickness can be calculated by taking the arithmetic mean of the thickness data at all observation points. For example, assuming that in a certain area, the ice thicknesses at five different points are , then the average ice thickness in this area is: ; Assuming that in a certain area, the ice thicknesses at five different points are 28 meters, 30 meters, 32 meters, 29 meters, and 31 meters respectively, then the average ice thickness in this area is: ; The water level change trend can be obtained by analyzing data at multiple time nodes and using methods such as linear regression to fit a trend line. For example, if the water levels in the past three months are , , , the water level change trend obtained by linear regression is an increase of per month. The formula for calculating the trend is: ; Assuming that the water levels in the past three months are 2.5 meters, 3 meters, and 3.5 meters respectively, then the water level change trend is: ; Based on these averages and trends, the errors in the data can be further adjusted. Assuming that the preliminary depth data in a certain area is , and the average ice thickness in this area is , the error correction formula can be adjusted by calculating the difference from the benchmark value, and the correction coefficient is which can be set according to the reliability of the data. Assuming that in practical applications, the correction coefficient is set to 0.8, which means that during the error correction process, the difference between the actually measured value and the benchmark value will be corrected according to 80% of the ratio. Then the depth correction formula is: ; Assuming meters, meters, , the corrected depth data is: ; By this method, the accuracy and consistency of the data can be significantly improved, and the corrected data can be obtained.

[0030] S203: Refer to the spatial weights of the weighted dataset for the corrected data to identify the temporal change trend and spatial variation of the ice lake depth data, analyze the depth change trend in the ice lake area, obtain the corresponding change data, and generate the ice lake depth change monitoring results; When identifying the temporal change trend and spatial variation of the ice lake depth data by referring to the spatial weights of the weighted dataset for the corrected data, it is first necessary to analyze by combining the weights of the temporal data and spatial data to identify the changes in the ice lake depth in different time periods. Specifically, the temporal change trend can be achieved by comparing the depth data in different periods. For example, in a certain area, the depth in January is , and the depth in February is . Through this time series data, it can be concluded that the depth in this area has increased by within a month. The calculation formula for the temporal change is: ; For example, if the depth in January is , and the depth in February is , then the depth change amount is: ; The spatial variation analysis is to compare the depth data changes at different positions by combining the spatial weight values in the weighted dataset to identify which areas have more significant changes. Specifically, through regional division, calculate the depth change amount of each region and perform weighted averaging according to its spatial weight. For example, the depth change in a certain area is , but due to the high weight of its location, the final depth change value may need to be weighted to : ; Assume that the spatial weight of this area is , meters, then the final weighted depth change is: ; By this method, combining the temporal change trend and spatial variation, it is possible to effectively identify the depth change trend in the ice lake area and generate the monitoring results. For example, if the monitoring results show that the depth change in a certain area is , and the spatial weight of this area is high, the final depth change value will be weighted and adjusted to ensure that the monitoring results reflect the actual changes in this area.

[0031] Please refer to Figure 4 , and according to the ice lake depth change monitoring results and real-time meteorological data, analyze the impact of environmental factors in the ice lake area on the ice layer, adjust the stability threshold of the ice layer, and the specific steps to generate the ice lake stability risk results are as follows: S301: Obtain real-time meteorological data, including precipitation, temperature, and wind speed, as the basic data for analyzing environmental factors, and obtain environmental factor data according to the monitoring results of the ice lake depth change; Extract the water level change data of the ice lake area according to the monitoring results of the ice lake depth change, and screen out the data points with the water level rising or falling rate exceeding the set threshold from the monitoring records, where the water level change rate is calculated using the formula where is the water level change amount, is the time interval. If is higher than the set critical value , it is determined that the ice lake water level change is abnormal. At the same time, obtain the real-time meteorological data within the corresponding time range, including parameters such as precipitation, temperature, and wind speed. Cumulate the precipitation data hourly, calculate the total precipitation in 24 hours and the cumulative precipitation in the most recent 3 days , and compare with the historical average precipitation. If or exceeds the set ratio compared with the historical average value, it is marked as precipitation anomaly. The temperature data calculates the daily average temperature using the hourly recorded values , and determines whether it is higher than the set ratio of the average temperature in the same period over the years . If , it is marked as temperature anomaly. The wind speed data calculates the daily average wind speed using the hourly average , and compares with the set extreme wind speed threshold . If , it is marked as wind speed anomaly. Finally, screen out the data points that meet the abnormal conditions to form an environmental factor data set.

[0032] S302: Analyze the influence of the area, aspect, temperature, and characteristics of dangerous ice bodies of the parent glacier on the stability of the ice lake based on the environmental factor data. Calculate the change trend of the parent glacier under each environmental factor with reference to precipitation, temperature, and wind speed factors, evaluate the role of each environmental factor in the stability of the ice lake, and generate the analysis results of the influence of environmental factors on the parent glacier; Analyze the influence of the area, aspect, temperature, and characteristics of dangerous ice bodies of the parent glacier on the stability of the ice lake based on the environmental factor data obtained in S301. Extract the area and aspect data of the parent glacier, and compare with the historical data. If the current area varies by more than the set ratio compared with the average value over the yearsIf so, it is determined that the glacier area is abnormal. At the same time, the relationship between the slope aspect and the solar radiation angle is judged, and the slope aspect angle is calculated. and the solar radiation angle between the included angle If it indicates that the glacier receives a relatively high radiation, which may affect the glacier ablation rate. Further analyze the characteristics of dangerous ice bodies, including the area and volume and slope of the dangerous ice body, judge whether the volume of the dangerous ice body is at an extreme value, and calculate its change ratio compared with the historical average If it is determined that there is an abnormal change in the ice body volume. At the same time, calculate the movement angle between the dangerous ice body and the ice lake, where is the height difference between the ice body and the ice lake, is the horizontal distance. If exceeds the set threshold it is considered that the risk of ice avalanche increases. Combine the air temperature data to calculate the rate of change of glacier temperature If the rate of change of temperature exceeds the set critical value, it indicates that the glacier temperature may affect the stability of the ice lake. Finally, integrate the calculation results of each parameter, evaluate the impact of environmental factors on the change of the parent glacier, and generate the analysis results of environmental factors and the impact on the parent glacier.

[0033] S303: Evaluate the stability of the moraine dam according to the analysis results of the environmental factors and the impact on the parent glacier, analyze the impact of the backwater slope gradient on erosion, evaluate the stability of loose sediments, identify the risks of cracks, piping and dead ice ablation, calculate the changing trend of the dam body permeability, predict the precursors of ice lake outburst and adjust the stability threshold of the ice lake ice layer, and generate the ice lake stability risk results; Evaluate the stability of the moraine dam according to the analysis results of S302. First, extract the backwater slope gradient of the moraine dam and calculate its relationship with the water erosion rate. Use the gradient value and the hydrodynamic formula to calculate the erosion rate where is the soil erodibility coefficient. If it is determined that the dam body erosion rate is abnormal. Further evaluate the stability of the dam body composition materials and calculate the sediment particle size distribution If the particle size is less than the set threshold, it is determined as an easily eroded material. At the same time, extract the dam body crack data and analyze the crack density and calculate the crack permeability If is higher than the set value , it is determined that the crack may trigger piping, the ablation rate of dead ice is judged by combining temperature data, and the relationship between ice temperature change and depth is calculated. If , it indicates that the ablation of dead ice may lead to internal collapse of the dam body. After integrating all data, the changing trend of the dam body permeability is calculated, and the precursors of ice lake outburst are predicted by combining the historical data of the ice lake. Finally, the stability threshold of the ice lake ice layer is adjusted to generate the ice lake stability risk result.

[0034] Please refer to Figure 5 , based on the ice lake stability risk result, simulate the outburst path under each environmental condition, analyze the correlation between environmental factors, ice lake slope, soil and the outburst path, and predict the outburst path under each climate and environmental condition. The specific steps to obtain the outburst path prediction result are as follows: S401: Based on the ice lake stability risk result, use the environmental factor data associated with the outburst path simulation as the basic data for outburst path prediction to obtain the adjusted environmental factor data; Based on the ice lake stability risk result, first, it is necessary to obtain the environmental factor data associated with the outburst path simulation. These data mainly include factors such as precipitation, temperature, and wind speed, and the collection method is real-time data acquisition and historical data archiving. Combining these environmental factor data with the outburst path simulation requires fine screening and verification of the environmental factor data first. Assume that the temperature is -10°C, precipitation is 15 mm, and wind speed is 7 m / s in a certain period. Combining these data, the adjusted environmental factor data for the corresponding period is obtained through the meteorological simulation interface. These adjusted data need to be further corrected based on the real-time collected meteorological data and the ice lake stability risk data to provide accurate basic data for outburst path prediction. In this process, the relationship between meteorological factors such as precipitation and ice layer stability can be quantified through statistical methods such as regression analysis, and the obtained adjusted data will be an important basis for path simulation. The process of obtaining the adjusted environmental factor data includes comparing each factor data and calculating the adjustment factor. For example, the ice layer stability coefficient is adjusted to 1.2 at a temperature of -20°C, and the stability weight is adjusted to 1.5 when the precipitation is greater than 20 mm, and so on, to ensure that the adjustment of each environmental factor reflects the actual change trend of the ice lake. Finally, through this adjusted data, a reliable basis is provided for subsequent path prediction.

[0035] S402: Based on the adjusted environmental factor data, analyze the correlation between environmental factors, ice lake slope, soil type and the outburst path, and obtain the key factors of the ice lake outburst path to generate the analysis result of the key factors of the outburst path; To adjust data based on environmental factors, it is first necessary to analyze the correlations among environmental factors, ice lake slope, soil type, and breach path. During the analysis process, it is required to comprehensively correlate environmental factor data with ice lake slope and soil type. Ice lake slope is usually obtained through Geographic Information System (GIS) data, while soil type is obtained through soil surveys and sample analyses. By using methods such as multiple linear regression, analyze the impacts of precipitation, temperature, wind speed, slope, and soil type on the breach path item by item. Specifically, when implementing, use the slope as the x-axis, precipitation as the y-axis, and soil type as the control variable, and calculate the correlation coefficient between them and the breach path. For example, assuming the slope is between 5° and 10° and the precipitation is 25 mm, the analysis results show that there is a strong positive correlation between precipitation and the change in the breach path. The steeper the slope, the greater the likelihood of a breach occurring. According to the results of the correlation analysis, obtain the influence weights of each environmental factor in the ice lake breach path, and determine the key factors of the breach path through these data. For instance, if the slope is 10°, the precipitation is 30 mm, and the wind speed is 15 m / s, the weight coefficients obtained through model analysis may be 0.3 for slope, 0.5 for precipitation, and 0.2 for wind speed. Through comprehensive analysis, it is concluded that precipitation is the key factor, which determines the main direction of the breach path. Finally, this process generates the analysis results of the key factors of the breach path, providing a basis for predicting the path.

[0036] S403: According to the analysis results of the key factors of the breach path and referring to the data adjusted by environmental factors, predict the ice lake breach path under each climate and environmental condition, call the ice lake geographic information and climate data for path calculation, and generate the prediction results of the breach path; According to the analysis results of the key factors of the breach path and referring to the environmental factors to adjust the data, to predict the ice lake breach path under each climate and environmental condition, it is first necessary to set up a prediction model. The model includes multiple input data such as climate conditions, environmental factors, and geographical information. In this process, first, set the data ranges of temperature, precipitation, wind speed, etc. according to each climate condition required for prediction (such as extremely cold, temperate, tropical). Assume that under extremely cold climate, the temperature is -30°C, the precipitation is 5 mm, and the wind speed is 3 m / s. Geographical information such as the slope is 15° and the soil type is clay. Then, call the geographical information data of the ice lake and the real-time climate data for path calculation. During the calculation process, it is necessary to consider the influence of the slope and soil type on the path direction. For example, assume that under extremely cold climate, the ice layer is not likely to breach easily, but due to the large wind speed, it may cause the expansion of cracks on the ice layer surface, and the path shows a relatively concentrated breach trend. Through the path calculation under different climate and environmental conditions, predict the specific direction of the breach path, and compare and calibrate it with the historical breach records and simulated paths. Finally, generate the prediction results of the breach path based on these data. For example, under extremely cold climate conditions, the breach path direction of the ice lake may be concentrated in the southeast direction, while under temperate climate conditions, the breach path may show a scattered state.

[0037] Please refer to Figure 6 , evaluate the breach risk indicators according to the breach path prediction results, compare them with the preset breach risk thresholds, screen the risk areas higher than the preset breach risk thresholds, generate warning level, warning area, and recommended measure information. The specific steps to obtain the breach hazard warning decision information are as follows: S501: According to the breach path prediction results, obtain the breach risk assessment indicators of the corresponding area, compare the assessment indicators with the preset breach risk thresholds, screen the risk areas higher than the breach risk thresholds, calculate the breach risk values of the risk areas, and obtain the risk coefficient data set; Screen the risk areas higher than the breach risk thresholds, according to the formula: ; Calculate the breach risk value of the risk area .

[0038] Among them, represents the destructive influence factor of the th potential breach area, represents the probability of the breach occurring, represents the exposure degree within the corresponding area, represents the emergency resource coverage coefficient of this area, represents the environmental obstacle factor (such as the obstacle degree of terrain, traffic, etc. to the emergency rescue speed), is the total number of risk areas. In this formula, the destructive influence factor Obtained by monitoring the possible damage range of each breach area, with the unit being the affected area (square kilometers), and the probability factor Calculated from historical data, monitoring values, early warning models, etc., the exposure degree Quantified by statistically counting the total population, buildings, and economic assets that may be affected, with the unit being the exposure value, and the emergency resource coverage coefficient Indicates the amount of rescue resources that can be quickly allocated within the region, determined by indicators such as rescue vehicles and material reserves, and the environmental obstacle factor Indicates the negative impact on rescue and evacuation due to complex terrain, traffic congestion, etc., using a proportional factor from 0 to 1, where 0 represents no obstacle and 1 represents complete obstacle.

[0039] For example, there are three breach risk areas in a certain region, and the monitored impact factors (square kilometers), , ; the breach probability , , ; the exposure degree (unit of economic loss unit), , ; the emergency resource coverage coefficient , , ; the environmental obstacle factor , , .

[0040] Substitute into the formula: ; The result shows that the comprehensive breach risk value of this region is 442.401. According to the preset risk level threshold, subsequent judgments and screenings can be carried out, and corresponding risk emergency strategies can be further formulated.

[0042] S502: Perform interval grading on the breach risk value according to the risk coefficient dataset, and assign corresponding early warning levels to each region according to the risk intervals to obtain the early warning levels of the breach risk areas; The breach risk value is classified into intervals according to the risk coefficient dataset. First, the risk value is divided into intervals, multiple risk intervals are set, and by comparing the breach risk value of each area with the preset threshold, it is classified to determine the risk level it belongs to. By setting intervals and thresholds, the risk level of each area is obtained and different warning levels are assigned. First, a suitable set of intervals needs to be set, and these intervals can be divided based on historical data analysis, combined with actual geological, climatic, environmental and other factors. Then, according to the breach risk value of each area, it is compared with the preset risk interval threshold to determine its risk level. For example, assume that the preset risk levels are divided into three intervals: low risk (0 - 300), medium risk (300 - 600), and high risk (above 600). If the breach risk value of a certain area is 442.401, it belongs to the medium - risk interval and the corresponding warning level is obtained. For other risk values, they can be compared and assigned warning levels similarly, and finally the warning level dataset of the breach - risk area is obtained.

[0043] S503: Generate corresponding warning measure information according to the warning level of the breach - risk area. Refer to the breach - risk characteristics of the risk area, formulate corresponding emergency response plans for each area, and obtain the warning decision - making information on breach hazard. Generate corresponding warning measure information according to the warning level of the breach - risk area. First, it is necessary to determine the emergency response plan according to the warning level of each area. Considering different warning levels and area characteristics, targeted emergency response plans are formulated respectively. The formulation of the emergency response plan needs to be based on multiple factors, including the breach risk value of the area, geographical environment, resident distribution, and local emergency response capabilities. First, according to the warning level of the area, judge whether the breach risk level of the area is high risk, medium risk or low risk. For example, for high - risk areas, it may be necessary to evacuate residents in advance, strengthen the reinforcement of infrastructure, and launch emergency rescue plans. For medium - risk areas, monitoring and warnings can be strengthened, evacuation plans can be formulated and preparations for rapid response to emergencies can be made. Low - risk areas may only require routine monitoring and regular inspections. By comprehensively considering these factors, a set of emergency response plans that meet the characteristics of each area is generated and dynamically adjusted during the implementation process. In addition, warning measures need to be formulated to issue early warnings to relevant departments and residents to ensure a rapid response in case of disasters and minimize casualties and property losses to the greatest extent.

[0044] Please refer to Figure 7 , the ice - lake breach hazard assessment and warning decision - making system based on big data, the system includes: The data acquisition and processing module obtains lidar, satellite optical imagery, and SAR data, performs geometric and radiometric corrections, extracts data on ice thickness and water level changes in the ice lake area, analyzes the color changes of the ice lake water body, analyzes the ice layer structure in combination with SAR data, and generates data on ice lake depth changes; The depth change monitoring module spatially weights and fuses the data based on the ice lake depth change data, corrects the errors, identifies the ice lake depth changes through the corrected data, and obtains the ice lake depth change monitoring results; The environmental factor analysis module obtains real-time meteorological data according to the ice lake depth change monitoring results, combines environmental factors such as precipitation, temperature, and wind speed in the ice lake area, analyzes the impact of environmental factors on the stability of the ice lake ice layer, adjusts the stability threshold of the ice lake ice layer, and generates the ice lake stability risk assessment results; The breach path simulation module simulates the ice lake breach paths under different environmental conditions according to the ice lake stability risk assessment results, combines factors such as environmental data, ice lake slope, and soil structure, analyzes the risks of the ice lake breach paths, and obtains the breach path prediction results; The risk assessment and early warning module obtains multi-level breach risk assessment indicators according to the breach path prediction results, compares them with the set breach risk thresholds, screens out high-risk areas, generates information such as early warning levels, early warning areas, and countermeasures based on the risk areas, and obtains the breach hazard early warning decision-making information.

[0045] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for evaluating, warning and making decisions on the risk of glacial lake outburst based on big data, characterized in that, Including the following steps: S1: Obtain lidar, satellite optical images and SAR data, extract the ice layer thickness, water level change and water body color change in the ice lake area, analyze the ice layer structure in combination with SAR, and generate ice lake depth change data; S2: Perform spatial weighted fusion on the ice lake depth change data, correct the error, identify the ice lake depth change based on the corrected data, and obtain the ice lake depth change monitoring result; S3: According to the ice lake depth change monitoring result and real-time meteorological data, analyze the impact of environmental factors in the ice lake area on the ice layer, adjust the stability threshold of the ice layer, and generate the ice lake stability risk result; S4: Based on the ice lake stability risk result, simulate the breach path under each environmental condition, analyze the correlation between environmental factors, ice lake slope, soil and the breach path, predict the breach path under each climate and environmental condition, and obtain the breach path prediction result; S5: Evaluate the breach risk index according to the breach path prediction result, compare it with the preset breach risk threshold, screen the risk areas higher than the preset breach risk threshold, generate warning level, warning area, and recommended measure information, and obtain the breach hazard warning decision-making information.

2. The method for evaluating and warning decision-making of glacial lake outburst hazard based on big data according to claim 1, wherein: The ice lake depth change data is the ice layer thickness, water level change, water body color change, and ice layer structure analysis. The ice lake depth change monitoring result includes depth change and monitoring data correction. The ice lake stability risk result is the ice layer stability assessment and risk analysis result. The breach path prediction result includes the breach path, the correlation analysis between environmental factors and the breach path, and the simulation of the breach path under climate and environmental conditions. The breach hazard warning decision-making information includes the breach risk assessment index and decision support information.

3. The method for evaluating and warning decision-making on the risk of glacial lake outburst based on big data according to claim 1, wherein: The specific steps to obtain lidar, satellite optical images and SAR data, extract the ice layer thickness, water level change and water body color change in the ice lake area, and analyze the ice layer structure in combination with SAR to generate ice lake depth change data are as follows: S101: Obtain lidar, satellite optical images and SAR data, adjust the geospatial coordinates of each data point in the lidar data, and correct the pixel values in the satellite optical image, and adjust the brightness and contrast of the image to obtain the corrected data; S102: Based on the corrected data, extract the ice layer thickness, ice lake water level and water body color in the ice lake area, perform pixel-by-pixel analysis on the data image, obtain the thickness value of the ice layer and the dynamic color change data of the water body, and obtain the ice lake area change data; S103: According to the ice lake area change data and referring to the SAR data, analyze the structural characteristics of the ice layer, obtain the internal structural change mode of the ice layer, and compare and fuse the data with the extracted water level change and ice layer thickness data to generate ice lake depth change data.

4. The method for evaluating and warning decision-making of glacial lake outburst hazard based on big data according to claim 1, wherein: The specific steps for spatially weighted fusion of the ice lake depth change data, error correction, and identification of ice lake depth changes based on the corrected data to obtain the ice lake depth change monitoring results are as follows: S201: According to the terrain, ice layer thickness, and water level changes in the ice lake area, spatially allocate and weight the depth data of the ice lake area for the ice lake depth change data, adjust the data through spatially weighted fusion, and generate a weighted data set; S202: Based on the weighted data set, use the average value of the ice layer thickness and the change trend of the water level as the correction benchmark to correct the errors in the data and obtain the corrected data; S203: Refer to the spatial weights of the weighted data set for the corrected data to identify the temporal change trend and spatial variation of the ice lake depth data, analyze the depth change trend of the ice lake area, obtain the corresponding change data, and generate the ice lake depth change monitoring results.

5. The method for evaluating and pre-warning decision-making on the risk of glacial lake outburst based on big data according to claim 4, characterized in that: For the weighted calculation of depth, the formula is used: ; where is the weighted value of depth, is the weight of ice layer thickness, is the weight of water level change, is the influence weight of terrain, is the ice layer thickness, is the water level change, is the value of the influence of terrain; for the corrected depth data, the formula is used: ; where is the corrected depth data, is the preliminary depth data, is the average ice layer thickness, is the correction coefficient.

6. The method for evaluating and warning decision-making of glacial lake outburst hazard based on big data according to claim 1, wherein: The specific steps for analyzing the impact of environmental factors in the ice lake area on the ice layer based on the ice lake depth change monitoring results and real-time meteorological data, and adjusting the stability threshold of the ice layer to generate the ice lake stability risk results are as follows: S301: According to the ice lake depth change monitoring results, obtain real-time meteorological data, including precipitation, temperature, and wind speed, as the basic data for analyzing environmental factors, and obtain environmental factor data; S302: Based on the environmental factor data, analyze the impact of the area of the parent glacier, slope aspect, temperature, and characteristics of dangerous ice bodies on the stability of the ice lake, calculate the change trend of the parent glacier under each environmental factor change with reference to precipitation, temperature, and wind speed factors, evaluate the role of each environmental factor in the stability of the ice lake, and generate the analysis results of the impact of environmental factors on the parent glacier; S303: According to the analysis results of the impact of environmental factors on the parent glacier, evaluate the stability of the moraine dam, analyze the impact of the backwater slope gradient on erosion, evaluate the stability of loose sediments, identify the risks of cracks, piping, and ablation of dead ice, calculate the change trend of the dam permeability, predict the precursors of ice lake outburst, and adjust the stability threshold of the ice lake ice layer to generate the ice lake stability risk results.

7. The method for evaluating, warning and making decisions on the risk of glacial lake outburst based on big data according to claim 1, wherein: The specific steps for simulating the outburst path under each environmental condition based on the ice lake stability risk results, analyzing the correlation between environmental factors, ice lake slope, soil, and the outburst path, and predicting the outburst path under each climate and environmental condition to obtain the outburst path prediction results are as follows: S401: Based on the ice lake stability risk results, use the environmental factor data associated with the outburst path simulation as the basic data for outburst path prediction to obtain the environmental factor adjustment data; S402: Based on the environmental factor adjustment data, analyze the correlation between environmental factors, ice lake slope, and soil type and the outburst path, and obtain the key factors of the ice lake outburst path to generate the analysis results of the key factors of the outburst path; S403: According to the analysis results of the key factors of the outburst path and with reference to the environmental factor adjustment data, predict the ice lake outburst path under each climate and environmental condition, call the ice lake geographic information and climate data for path calculation, and generate the outburst path prediction results.

8. The method for evaluating and warning decision-making of glacial lake outburst danger based on big data according to claim 1, wherein: Evaluate the outburst risk indicators according to the predicted outburst path results, compare them with the preset outburst risk thresholds, screen the risk areas higher than the preset outburst risk thresholds, generate early warning levels, early warning areas, and recommended measure information, and obtain the specific steps of the outburst hazard warning decision-making information as follows: S501: According to the predicted outburst path results, obtain the outburst risk assessment indicators for the corresponding areas, compare the assessment indicators with the preset outburst risk thresholds, screen the risk areas higher than the outburst risk thresholds, calculate the outburst risk values of the risk areas, and obtain the risk coefficient data set; S5 02: Perform interval grading on the outburst risk values according to the risk coefficient data set, and assign corresponding early warning levels to each area according to the risk intervals to obtain the early warning levels of the outburst risk areas; S5 03: Generate corresponding early warning measure information according to the early warning levels of the outburst risk areas, formulate corresponding emergency response plans for each area with reference to the outburst risk characteristics of the risk areas, and obtain the outburst hazard warning decision-making information.

9. The method for ice lake outburst hazard assessment and early warning decision-making based on big data according to claim 8, wherein: For calculating the breach risk value of the risk area, the formula is used: ; where represents the breach risk value, represents the destructive force impact factor of the th potential breach area, represents the probability of breach occurrence, represents the exposure degree within the corresponding area, represents the emergency resource coverage coefficient of this area, represents the environmental obstacle factor, is the total number of risk areas.

10. The ice lake outburst hazard assessment and early warning decision-making system based on big data is characterized in that Execute according to the big data-based ice lake outburst hazard evaluation and warning decision-making method according to any one of claims 1-9. The system includes: a data acquisition and processing module that acquires lidar, satellite optical images, and SAR data, performs geometric and radiometric corrections, extracts ice layer thickness and water level change data in the ice lake area, analyzes the color change of the ice lake water body, analyzes the ice layer structure in combination with SAR data, and generates ice lake depth change data; a depth change monitoring module that performs spatial weighted fusion on the data based on the ice lake depth change data, corrects errors, and identifies the ice lake depth change through the corrected data to obtain the ice lake depth change monitoring results; an environmental factor analysis module that obtains real-time meteorological data according to the ice lake depth change monitoring results, analyzes the influence of environmental factors on the stability of the ice lake ice layer in combination with environmental factors such as precipitation, temperature, and wind speed in the ice lake area, adjusts the stability threshold of the ice lake ice layer, and generates an ice lake stability risk assessment result; an outburst path simulation module that simulates the outburst paths of the ice lake under different environmental conditions according to the ice lake stability risk assessment results, analyzes the risks of the ice lake outburst paths in combination with factors such as environmental data, ice lake slope, and soil structure, and obtains the outburst path prediction results; a risk assessment and warning module that obtains multi-level outburst risk assessment indicators according to the outburst path prediction results, compares them with the set outburst risk thresholds, screens out high-risk areas, generates information such as early warning levels, early warning areas, and countermeasures based on the risk areas, and obtains the outburst hazard warning decision-making information.

Images