A GIS-based data expression method and system for geological disaster monitoring points

Abstract

The present invention relates to the technical field of data representation, and specifically to a method and system for representing geological disaster monitoring point data based on GIS, including the following steps: obtaining the detection data of geological disaster monitoring points, calling the spatial coordinates of the monitoring points and the corresponding monitoring data, calculating the spatial correlation according to the spatial distance between the monitoring points, calculating the monitoring data of the uncollected points based on the spatial correlation, and generating interpolation monitoring values. In the present invention, by calculating the monitoring data of the uncollected points based on the spatial correlation between the monitoring points, the integrity of the spatial data is improved, and the missing of monitoring information caused by incomplete data collection is avoided. Analyze the local density of the monitoring points, divide different grid scales according to the density characteristics, improve the partition expression accuracy of the data, and construct a multi-level visual expression based on the spatial coordinates, timestamps and disaster intensity data of the monitoring points, so that the monitoring information is intuitive and the interpretability of the disaster monitoring data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data expression, and in particular to a method and system for expressing geological disaster monitoring point data based on GIS. Background Art

[0002] The field of data representation technology involves organizing, encoding, storing, transforming, and visualizing data to achieve efficient data management and information transfer. This area encompasses various data modeling methods, structured and unstructured data representation, data format conversion, spatial data representation, visualization techniques, and information retrieval optimization. It is widely used in fields such as geographic information systems, computer graphics, database management, machine learning, and engineering simulation. Through data structure optimization and graphical representation, it improves data readability, operability, and decision support capabilities.

[0003] Among these, the data representation method for geological hazard monitoring points is used to organize and visualize spatial and attribute data at these points to support monitoring, analysis, early warning, and management. This method typically combines GIS, 3D modeling, and spatial database technologies to achieve a multi-level representation of geological hazard information, including monitoring point locations, geological environmental parameters, and hazard evolution trends. Its primary applications include disaster risk assessment, monitoring data sharing, decision support, and emergency management, improving the scientific and real-time nature of geological hazard monitoring.

[0004] Traditional expression methods have defects in data integrity and fail to effectively fill data gaps of uncollected points, resulting in missing information in areas with uneven distribution of monitoring points, affecting the spatial continuity of the overall data. The data organization method does not extract the characteristic principal components, resulting in high data redundancy, affecting computational efficiency. At the same time, the local density-based grid division method is not adopted in data classification, and high-density and low-density areas cannot be differentiated. As a result, the data expression of high-density areas is overly simplified and the details of low-density areas are insufficient, affecting the refined expression ability of monitoring data. In terms of visual expression, after the data is mapped to the GIS platform, there is a lack of spatial and temporal hierarchical display capabilities, making it difficult to intuitively display the spatiotemporal change trends of monitoring data, affecting the practicality of the data in disaster monitoring, risk assessment and decision analysis. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a GIS-based geological disaster monitoring point data expression method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for expressing geological disaster monitoring point data based on GIS, comprising the following steps:

[0007] S1: Obtain the detection data of geological disaster monitoring points, call the spatial coordinates and corresponding monitoring data of the monitoring points, calculate the spatial correlation according to the spatial distance between the monitoring points, calculate the monitoring data of the uncollected points based on the spatial correlation, and generate interpolation monitoring values;

[0008] S2: Based on the interpolation monitoring values, obtain the time series data of the monitoring points, align the data according to the time series, analyze the change trend of adjacent moments, call the state estimation value of the time series, and adjust the interpolation monitoring values according to the change trend of the time series to obtain time series adjusted monitoring values;

[0009] S3: Based on the time series adjusted monitoring values, calculate the distance from each monitoring point to the cluster center according to the set number of clusters, classify the monitoring points into the corresponding clusters according to the shortest distance, call the classified monitoring data to calculate the feature change range, extract the feature principal components, and generate compressed monitoring data based on the feature principal components for dimensionality reduction;

[0010] S4: Based on the compressed monitoring data, calculate the local density of the monitoring points, analyze the spatial distribution characteristics, divide the grid according to the local density, and re-divide the grid according to the division scale of the differentiated area to obtain gridified monitoring data.

[0011] The improvements of the present invention are that the interpolation monitoring values include spatial prediction points, monitoring parameter interpolation values and spatial correlation weights, the time series adjusted monitoring values include time-aligned data, state estimation values and dynamically complemented monitoring parameters, the compressed monitoring data includes cluster center points, feature principal components and dimensionality reduction monitoring parameter sets, and the gridified monitoring data includes high-density area grids, low-density area grids and disaster risk distribution units.

[0012] The improvements of the present invention are that the specific steps for obtaining the interpolation monitoring values are as follows:

[0013] S101: Obtain the detection data of geological disaster monitoring points, call the spatial coordinates and corresponding monitoring data of the monitoring points, including spatial coordinates, geological activity intensity, rainfall and soil humidity, establish a monitoring point set according to the distribution range of the spatial coordinates, screen outliers according to the parameter distribution in the monitoring point set, call the outliers for deviation calculation, and adjust the parameter intervals of the monitoring point data according to the calculated deviation to obtain a monitoring data set;

[0014] S102: Based on the monitoring data set, calculate the spatial distance between the monitoring points, call the spatial coordinates of the monitoring points, calculate the correlation weight between the monitoring points according to the distance between the coordinate points, compare with the preset correlation threshold according to the monitoring point correlation weight, screen the monitoring point pairs with strong spatial correlation, call the screened monitoring points, calculate the correlation contribution value, and adjust the influence weight between the monitoring points according to the contribution value to obtain the spatial correlation weight;

[0015] S103: Based on the spatial correlation weight, call the spatial coordinates of the uncollected points, and calculate the monitoring parameters of the uncollected points according to the monitoring data and correlation weight of the collected monitoring points, and generate interpolation monitoring values.

[0016] The improvement of the present invention is that the formula for calculating the monitoring parameters of the uncollected points is:

[0017] ;

[0018] Wherein, represents the interpolation of the monitoring parameters of the uncollected point j, represents the spatial correlation weight between the monitoring point i and the uncollected point j, [[ID=_{16}]] represents the monitoring data value of the i-th collected monitoring point, and respectively represent the spatial coordinate position values of the i-th collected monitoring point and the uncollected monitoring point j, represents a numerical stability constant, represents the number of collected monitoring points.

[0019] The improvement of the present invention is that the steps for obtaining the time series adjusted monitoring value are specifically as follows:

[0020] S201: Based on the interpolation monitoring value, combine the time series data index of the monitoring points, call the monitoring point coordinates and monitoring data in the time series, organize the monitoring point data list according to the time order, calculate the time step according to the acquisition time interval between adjacent time points, call the time step to screen the time interval with large data fluctuation range, and adjust the data sampling density according to the time interval to obtain a time series data set;

[0021] S202: Based on the time series data set, call the monitoring data in the time series, calculate the numerical change rate of the monitoring points at different time points, call the change rate to calculate the similarity between adjacent time points, screen the time period with stable data change trend in the time series according to the similarity, and call the data in the stable time period to generate a smooth change curve to obtain the time series trend feature;

[0022] S203: Based on the time series trend feature and the interpolation monitoring value, calculate the deviation amount of the monitoring data in the time series, call the deviation amount to adjust the state estimation value of the monitoring data, correct the monitoring data in the time series according to the state estimation value, and call the corrected data to generate a time series interpolation result to obtain the time series adjusted monitoring value.

[0023] The improvement of the present invention is that the steps for obtaining the compressed monitoring data are specifically as follows:

[0024] S301: Based on the timing-adjusted monitoring values, obtain the spatial coordinates, disaster intensity, and rainfall monitoring indicators of the monitoring points. Call the spatial coordinates of the monitoring points to calculate the Euclidean distance between the monitoring points. Construct a monitoring point distance matrix based on the Euclidean distance. Call the distance matrix to screen the pairs of monitoring points with close spatial distances. Establish a spatial relationship mapping of the monitoring points based on the screening results to obtain the spatial distance distribution of the monitoring points.

[0025] S302: Based on the spatial distance distribution of the monitoring points, call the set number of clusters to calculate the distance from each monitoring point to the center of each cluster. Screen the cluster center with the shortest distance based on the calculation results. Call the screening results to classify the monitoring points. Adjust the distribution range of the monitoring points within each cluster based on the classification results. Call the adjusted cluster information to establish the classification result of the monitoring points to obtain the spatial clustering distribution of the monitoring points.

[0026] S303: Based on the spatial clustering distribution of the monitoring points, call the classified monitoring data to calculate the range of feature changes. Extract the key influencing factors of the monitoring points based on the range of feature changes. Call the key influencing factors for dimensionality reduction operations. Screen the feature principal components based on the results of the dimensionality reduction operations. Call the feature principal components to reconstruct the monitoring point data table to generate compressed monitoring data.

[0027] The improvement of the present invention is that the steps for obtaining the gridified monitoring data are specifically as follows:

[0028] S401: Based on the compressed monitoring data, obtain the spatial coordinates and disaster intensity data of the monitoring points. Call the spatial coordinates of the monitoring points to calculate the distance between adjacent monitoring points. Calculate the number density of local monitoring points based on the distance. Call the number density of the monitoring points to screen the areas where the aggregation degree of the monitoring points within the area exceeds the preset density threshold. Establish the local density distribution of the monitoring points based on the screening results to obtain the local density values of the monitoring points.

[0029] S402: Based on the local density values of the monitoring points, call the spatial distribution data of the monitoring points within the area. Divide the dense area and the sparse area according to the local density range. Calculate the area division threshold based on the distribution boundaries of the dense area and the sparse area. Adjust the spatial range of each area based on the division threshold. Call the adjusted area division results to establish a differential density area to obtain the area density division result.

[0030] S403: Based on the area density division result, perform grid division according to the local density, calculate the grid scale. Call the dense area to set a small grid division scale, call the sparse area to set a large grid division scale. Generate grid division information based on the grid scale of each area. Call the grid division scheme to readjust the grid range to which the monitoring points belong. Reconstruct the spatial mapping relationship of the monitoring data based on the adjustment results to obtain the gridified monitoring data.

[0031] The formula for calculating the grid scale is:

[0032] ;

[0033] Among them, represents the grid scale value of the th area, represents the scale adjustment constant, represents the local density value of the th area, represents a small quantity constant to prevent the denominator from being zero, represents the average disaster intensity value of the th area, represents the average value of the regional disaster intensity, represents the standard deviation of the regional disaster intensity.

[0034] The improvement of the present invention is that the method further includes:

[0035] S5: Based on the grid monitoring data, map the data to the GIS platform according to the spatial coordinates, call the map hierarchical processing of the GIS platform, display the monitoring point data according to the spatial distribution and time variation, and generate the visualization expression information of geological disaster data;

[0036] The visualization expression information of the geological disaster data includes spatially mapped monitoring points, time evolution curves, and disaster intensity distribution maps.

[0037] The improvement of the present invention is that the acquisition steps of the visualization expression information of the geological disaster data are specifically as follows:

[0038] S501: Based on the grid monitoring data, obtain the spatial coordinates, timestamps, and disaster intensity data of the monitoring points, call the spatial coordinate data to match the geographic reference coordinate system of the GIS platform, calculate the longitude and latitude conversion values of the monitoring points according to the geographic reference coordinate system, call the converted longitude and latitude data to map to the spatial database of the GIS platform, and obtain the GIS mapped monitoring data;

[0039] S502: Based on the GIS mapped monitoring data, call the map hierarchical information of the GIS platform, calculate the map display range according to the spatial distribution of the monitoring points, call the map display range data to match the spatial coordinates of the monitoring points, adjust the map display ratio according to the distribution density of the spatial coordinates, and divide the map hierarchy according to the adjusted ratio to obtain the map hierarchical monitoring data;

[0040] S503: Based on the map hierarchical monitoring data, call the timestamps and disaster intensity data of the monitoring points, calculate the time variation trend of the monitoring points according to the timestamps, call the time variation trend data to match the spatial coordinates, and display the monitoring point data according to the spatial distribution and time variation to obtain the visualization expression information of the geological disaster data.

[0041] A data expression system for geological disaster monitoring points based on GIS, the data expression system for geological disaster monitoring points based on GIS is used to execute the above-mentioned data expression method for geological disaster monitoring points based on GIS, and the system includes:

[0042] The data interpolation processing module obtains the detection data of geological disaster monitoring points, calculates the monitoring data of uncollected points according to spatial correlation, and generates interpolation monitoring values;

[0043] The time series optimization processing module aligns the data according to the time series based on the interpolation monitoring values, analyzes the change trend of adjacent moments, calls the state estimation value of the time series, and adjusts the interpolation monitoring values according to the change trend of the time series to obtain time series adjusted monitoring values;

[0044] The data compression processing module classifies the monitoring points into corresponding clusters based on the shortest distance based on the time series adjusted monitoring values, calls the classified monitoring data to calculate the characteristic change range, extracts the characteristic principal components, and reduces the dimension based on the characteristic principal components to generate compressed monitoring data;

[0045] The grid division module divides the grid based on the compressed monitoring data according to the local density, and re-divides the grid according to the division scale of the differential area to obtain gridified monitoring data;

[0046] The data mapping and expression module maps the data to the GIS platform based on the gridified monitoring data, displays the monitoring point data according to the spatial distribution and time change, and generates visual expression information of geological disaster data.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0048] In the present invention, by calculating the monitoring data of uncollected points according to the spatial correlation between monitoring points, the integrity of spatial data is improved, the monitoring information missing caused by incomplete data collection is avoided, the interpolation monitoring values are dynamically adjusted in combination with time series data, the spatio-temporal consistency of monitoring data is enhanced, the influence of single collection error is reduced, by extracting the characteristic principal components, while reducing data redundancy, the core characteristic information is retained, the calculation efficiency and storage efficiency are improved, the local density of monitoring points is analyzed, different grid scales are divided according to density characteristics, so that the high-density area has the ability of refined processing, the low-density area maintains the overall overview, the partition expression accuracy of data is improved, ensuring that the data expression can cover a large area and can accurately depict the key areas, based on the spatial coordinates, timestamps and disaster intensity data of monitoring points, a multi-level visual expression is constructed, so that the monitoring information is intuitive, can reflect the change trend in space and time, improve the interpretability of disaster monitoring data, and support multi-level data analysis and decision-making. Brief Description of the Drawings

[0049] Figure 1 is the method flow chart of the present invention;

[0050] Figure 2 is the flow chart for the present invention to obtain interpolation monitoring values;

[0051] Figure 3 is the flow chart for the present invention to obtain time series adjustment monitoring values;

[0052] Figure 4 is the flow chart for the present invention to obtain compressed monitoring data;

[0053] Figure 5 is the flow chart for the present invention to obtain gridified monitoring data;

[0054] Figure 6 is the flow chart for the present invention to obtain visual expression information of geological disaster data;

[0055] Figure 7 is the system flow chart of the present invention. Detailed implementation manners

[0056] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0058] Please refer to Figure 1 , the present invention provides a technical solution: a method for expressing geological disaster monitoring point data based on GIS, including the following steps:

[0059] S1: Obtain the detection data of the geological disaster monitoring points, call the spatial coordinates and corresponding monitoring data of the monitoring points, including spatial coordinates, geological activity intensity, rainfall, and soil humidity, calculate the spatial correlation according to the spatial distance between the monitoring points, and calculate the monitoring data of the uncollected points based on the spatial correlation to generate interpolation monitoring values;

[0060] S2: Based on the interpolated monitoring values, obtain the time series data of the monitoring points, call the coordinates and monitoring data of the monitoring points in the time series, calculate the similarity between the data at multiple time points, align the data according to the time series, analyze the change trend at adjacent moments, call the state estimation value of the time series, adjust the interpolated monitoring values according to the change trend of the time series, and perform dynamic adjustment by combining the observed data and the estimated data to obtain the time series adjusted monitoring values;

[0061] S3: Based on the time series adjusted monitoring values, obtain the spatial coordinates, disaster intensity, and rainfall monitoring indicators of the monitoring points, calculate the Euclidean distance between the monitoring points according to the spatial coordinates, calculate the distance from each monitoring point to the cluster center according to the set number of clusters, classify the monitoring points into the corresponding clusters based on the shortest distance, call the classified monitoring data to calculate the characteristic change range, extract the characteristic principal components, and generate compressed monitoring data based on the dimensionality reduction of the characteristic principal components;

[0062] S4: Based on the compressed monitoring data, obtain the spatial coordinates and disaster intensity data of the monitoring points, calculate the local density of the monitoring points, analyze the spatial distribution characteristics, divide the high-density area and the low-density area by using the local density, perform grid division according to the local density, divide small grids for the high-density area and large grids for the low-density area, and re-divide the grids according to the division scale of the differential area to obtain the gridded monitoring data;

[0063] S5: Based on the gridded monitoring data, obtain the spatial coordinates, timestamps, and disaster intensity data of the monitoring points, map the data to the GIS platform according to the spatial coordinates, call the map hierarchical processing of the GIS platform, display the monitoring point data according to the spatial distribution and time change, and generate the visual expression information of the geological disaster data;

[0064] The interpolated monitoring values include spatial prediction points, interpolated values of monitoring parameters, and spatial correlation weights. The time series adjusted monitoring values include time-aligned data, state estimation values, and dynamically complemented monitoring parameters. The compressed monitoring data includes cluster center points, characteristic principal components, and a set of dimensionality-reduced monitoring parameters. The gridded monitoring data includes high-density area grids, low-density area grids, and disaster risk distribution units. The visual expression information of the geological disaster data includes spatially mapped monitoring points, time evolution curves, and disaster intensity distribution maps.

[0065] Please refer to Figure 2 , and the specific steps for obtaining the interpolated monitoring values are as follows:

[0066] S101: Obtain the detection data of geological disaster monitoring points, call the spatial coordinates and corresponding monitoring data of the monitoring points, including spatial coordinates, geological activity intensity, rainfall, and soil humidity. Establish a monitoring point set according to the distribution range of the spatial coordinates, screen out outliers based on the parameter distribution in the monitoring point set, call the outliers for deviation calculation, and adjust the parameter interval of the monitoring point data according to the calculated deviation to obtain a monitoring data set;

[0067] Obtain the detection data of geological disaster monitoring points, including calling the spatial coordinates, geological activity intensity, rainfall, and soil humidity of each monitoring point. Divide the monitoring points into multiple regions according to the longitude and latitude range based on the spatial coordinate values of each monitoring point, and establish a monitoring point set in each region. Organize and store the monitoring point data sets corresponding to different regions. For the data of each monitoring point, calculate the time series changes of geological activity intensity, rainfall, and soil humidity respectively, and extract the maximum value, minimum value, mean value, and standard deviation in the past period of time to form a data feature set. For the data in the data feature set, use the three - standard - deviation method to screen out outliers, that is, for each monitoring point data value if it exceeds three times the standard deviation of the mean value of this monitoring point, that is , then this data is determined as an outlier. Record all outliers and establish an abnormal data set. Calculate the deviation of each abnormal data point relative to the normal data. The deviation calculation uses absolute error calculation, that is . And further adjust the weight of the outliers according to the historical data trend of each monitoring point to reduce the impact of abnormal data on the overall monitoring data set. Among them, the setting of the outlier weight is based on the deviation degree between the outlier and the mean value, and the weight value is set according to the deviation ratio. For example, if the deviation of an outlier from the mean value is , then its weight is set to , to reduce the impact of the outlier in an exponential decay manner. Relatively speaking, the weight of the normal value is 1, ensuring that most data contributes the main information. If a certain abnormal data , mean value [[ID=2,5]]standard deviation , then , the corresponding weight calculation , that is, when calculating the corrected data, the impact of this abnormal data is negligible. The corrected monitoring data value is calculated by weighted average, that is . Finally, obtain the corrected monitoring data set.

[0068] S102: Based on the monitoring data set, calculate the spatial distance between monitoring points, call the spatial coordinates of the monitoring points, calculate the correlation weight between monitoring points according to the distance between coordinate points, compare with the preset correlation threshold according to the monitoring point correlation weight, screen out the monitoring point pairs with strong spatial correlation, call the screened monitoring points, calculate the correlation contribution value, and adjust the influence weight between monitoring points according to the contribution value to obtain the spatial correlation weight;

[0069] Based on the corrected monitoring data set, calculate the spatial distance between each monitoring point, call the spatial coordinates of each monitoring point, and use the Euclidean distance formula to calculate the straight-line distance between each monitoring point. The distance calculation formula is , where is the monitoring point and the monitoring point the spatial distance between them, is the monitoring point the spatial coordinate value of, is the monitoring point the spatial coordinate value of, calculate the distance matrix between all monitoring points, and calculate the correlation weight between each monitoring point according to the distance matrix. The correlation weight is calculated using an inverse proportional function, that is , where is a minimum value to prevent division by zero, and the preset correlation threshold is set based on the average distance between monitoring points and the spatial variability of the monitoring data. Usually, it is calculated according to the coefficient of variation of the monitoring data. If the coefficient of variation is large, the threshold is appropriately increased to exclude points with low correlation at long distances. Suppose the coefficient of variation of the monitoring points in a certain area is, then can be set. Subsequently, compare with . If , then it is determined that the monitoring point and the monitoring point are monitoring point pairs with strong spatial correlation. Screen out all monitoring point pairs that meet this condition, and call the data of these monitoring points. Calculate the correlation contribution value according to the difference in monitoring data between each pair of monitoring points. The contribution value is calculated using the covariance formula . Finally, adjust the influence weight between monitoring points according to the calculated contribution value, and update the spatial correlation weight matrix.

[0070] S103: Based on the spatial correlation weight, call the spatial coordinates of the uncollected points, and calculate the monitoring parameters of the uncollected points according to the monitoring data and correlation weight of the collected monitoring points to generate interpolation monitoring values;

[0071] The formula for calculating the monitoring parameters of the uncollected points is:

[0072] ;

[0073] Among them, represents the interpolation of the monitoring parameter at the uncollected point j, represents the spatial correlation weight between the monitoring point i and the uncollected point j, represents the monitoring data value of the i-th collected monitoring point, and respectively represent the spatial coordinate position values of the i-th collected monitoring point and the uncollected monitoring point ; represents the numerical stability constant, represents the number of collected monitoring points;

[0074] Based on the spatial correlation weight, call the spatial coordinates of the uncollected points, and calculate the monitoring parameters of the uncollected points according to the data and correlation weights of the collected monitoring points. The calculation process first calls the spatial coordinates and monitoring data values of all collected monitoring points, and weights the data of each monitoring point according to the spatial correlation weight. The interpolation calculation formula is:

[0075] ;

[0076] Among them, represents the numerical stability constant, and its setting is based on the numerical range of the spatial coordinates. To prevent abnormal oscillations in the interpolation calculation caused by extremely small denominators, usually set to 10% of the minimum spatial distance as the stability term. Set the minimum spatial distance to 2, then .

[0077] In the area, there are 5 collected monitoring points, and their monitoring data values are as follows:

[0078] ;

[0079] The corresponding spatial correlation weights:

[0080] ;

[0081] Spatial coordinates:

[0082] ;

[0083] Set , then calculate:

[0084] ;

[0085] ;

[0086] ;

[0087] Final calculation:

[0088] ;

[0089] Therefore, for the monitoring parameter interpolation calculation result of the uncollected point is 0.849.

[0090] Please refer to Figure 3 , the specific steps for obtaining the time series adjusted monitoring values are as follows:

[0091] S201: Based on the interpolation monitoring values, combined with the monitoring point time series data index, call the monitoring point coordinates and monitoring data in the time series, organize the monitoring point data list according to the time order, calculate the time step according to the acquisition time interval between adjacent time points, call the time step to filter the time interval with a large data fluctuation range, and adjust the data sampling density according to the time interval to obtain the time series data set;

[0092] Based on the interpolation monitoring values, combined with the monitoring point time series data index, call the monitoring point coordinates and monitoring data in the time series, organize the data of each monitoring point into a monitoring point data list according to the time order, and calculate the time step according to the acquisition time of adjacent time points. The calculation method of each time step is the time difference between two adjacent sampling points, that is , where and represent the timestamps of two consecutive time points respectively. Calculate the time step set for all monitoring point data, and count the distribution range of the time steps. Filter out the time interval with a large data fluctuation range. The judgment basis for the fluctuation range is the coefficient of variation (CV) of adjacent time steps, and the calculation method is , where is the standard deviation of the time step, is the mean value of the time step. Set the threshold to judge the interval with large fluctuations. If the of a certain time interval, then it is determined that the time interval has large fluctuations. The threshold is set according to the distribution range of historical data. For example, if the mean value of the time step in a certain area minutes, and the standard deviation minutes, then its coefficient of variation . If is set, then the time interval is determined to have large fluctuations. Adjust the data sampling density for the time interval with large fluctuations. If the time step exceeds the set threshold, for example, the maximum allowable step minutes, then increase the data sampling points in this interval, and use linear interpolation to generate additional time sampling points to make the time step meet the set range, and finally obtain the time series data set.

[0093] S202: Based on the time series dataset, call the monitoring data in the time series, calculate the rate of change of the values at the monitoring points at different time points, call the rate of change to calculate the similarity between adjacent time points, screen the time periods with stable data change trends in the time series according to the similarity, call the data in the stable time periods to generate a smooth change curve, and obtain the time series trend feature;

[0094] Based on the time series dataset, call the monitoring data in the time series, calculate the rate of change of the values at the monitoring points at different time points. The calculation method of the rate of change for each monitoring point is , where and are respectively the monitoring data values at time and . Calculate the set of rates of change of all monitoring points at different time points, and calculate the similarity between adjacent time points based on the rate of change. The similarity calculation uses the cosine similarity formula , where and are respectively the rates of change of two adjacent time points. Set the similarity threshold . If , it is determined that the data change trend in this time period is stable. The threshold is set according to the mean value of the rate of change. For example, if the mean value of the rate of change in a certain area is and the standard deviation is , then is set to screen out the stable time periods. Call the data of all time periods that meet the similarity threshold to generate a smooth change curve. The generation of the smooth curve uses the weighted moving average method, and the weights are set according to the similarity. If the similarity at a certain time point is high, a higher weight is given. Finally, the time series trend feature is obtained.

[0095] S203: Based on the time series trend feature and the interpolated monitoring value, calculate the deviation amount of the monitoring data in the time series, call the deviation amount to adjust the state estimation value of the monitoring data, correct the monitoring data in the time series according to the state estimation value, call the corrected data to generate the time series interpolation result, and obtain the time series adjusted monitoring value;

[0096] Based on the time series trend feature and the interpolated monitoring value, calculate the deviation amount of the monitoring data in the time series. The calculation method of the deviation amount is , where is the monitoring data value, is the value of the time series trend feature at time . Calculate the set of deviation amounts at all time points, and call the deviation amount to adjust the state estimation value of the monitoring data. The adjustment of the state estimation value is based on the deviation compensation coefficient , and its calculation method is , where is the maximum absolute value of the deviation at all time points. If the deviation at a certain time point is large, its compensation coefficient is small to reduce the weight influence of this time point. Set the maximum deviation within a certain time period as , the deviation at a certain time point is , then the compensation coefficient of this time point is calculated as , and the corrected calculation of the compensated data is . Based on the state estimation value, correct the monitoring data in the time series, call the corrected data to generate the time series interpolation result, and finally obtain the time series adjusted monitoring value.

[0097] Please refer to Figure 4 . The specific steps for obtaining the compressed monitoring data are as follows:

[0098] S301: Based on the time series adjusted monitoring value, obtain the spatial coordinates, disaster intensity, and rainfall monitoring indicators of the monitoring points. Call the spatial coordinates of the monitoring points to calculate the Euclidean distance between the monitoring points, construct a monitoring point distance matrix based on the Euclidean distance, call the distance matrix to screen pairs of monitoring points with close spatial distances, and establish a mapping of the spatial relationship of the monitoring points based on the screening results to obtain the spatial distance distribution of the monitoring points;

[0099] Based on the time series adjusted monitoring value, obtain the spatial coordinates, disaster intensity, and rainfall monitoring indicators of the monitoring points. Call the spatial coordinates of the monitoring points to calculate the Euclidean distance between the monitoring points. The calculation method of the Euclidean distance is , where is the Euclidean distance between monitoring point and monitoring point , and are the spatial coordinate values of monitoring points and respectively. Calculate the Euclidean distance between all pairs of monitoring points, construct a monitoring point distance matrix, and call the distance matrix to screen pairs of monitoring points with close spatial distances. The screening criterion is based on the preset distance threshold , and its setting method is 70% to 90% of the average distance of the monitoring points in the region. For example, if the average distance between all monitoring points in a certain region is 10 kilometers, then kilometers can be set to screen out the mutually close monitoring points, call the screening results to establish a mapping of the spatial relationship of the monitoring points, construct the connection relationship between adjacent monitoring points, and finally obtain the spatial distance distribution of the monitoring points.

[0100] S302: Based on the spatial distance distribution of the monitoring points, call the set number of clusters to calculate the distance from each monitoring point to the center of each cluster, screen the cluster center with the shortest distance based on the calculation results, call the screening results to classify the monitoring points, adjust the distribution range of the monitoring points within each cluster based on the classification results, call the adjusted cluster information to establish the classification result of the monitoring points, and obtain the spatial clustering distribution of the monitoring points;

[0101] Based on the spatial distance distribution of the monitoring points, call the set number of clusters to calculate the distance from each monitoring point to the center of each cluster. The calculation method also uses the Euclidean distance formula , where is the monitoring point to the cluster center distance, is the spatial coordinate of the cluster center. Calculate the distance set from all monitoring points to the cluster center, and screen the cluster center with the shortest distance according to the calculation results. The screening of the shortest distance is based on the set clustering convergence threshold , and its setting method is the mean value of the distances between the monitoring points within the cluster plus the standard deviation. For example, if the mean value of the distances between the monitoring points within the initially divided cluster in a certain area is 8 kilometers and the standard deviation is 2 kilometers, then set kilometers to screen out the most reasonable cluster attribution. Call the screening results to classify the monitoring points, and adjust the distribution range of the monitoring points within each cluster according to the classification results. If the number of monitoring points in a certain cluster exceeds the preset upper limit , then the excess monitoring points are re-divided into adjacent clusters, is set according to the density of the regional monitoring points, generally taking 120% of the regional average density. For example, if the average density of the monitoring points in a certain area is 30 monitoring points / cluster, then set points to ensure the reasonable distribution of the clusters. Call the adjusted cluster information to establish the monitoring point classification results and obtain the spatial clustering distribution of the monitoring points;

[0102] S303: Based on the spatial clustering distribution of the monitoring points, call the classified monitoring data to calculate the range of feature changes, extract the key influencing factors of the monitoring points according to the range of feature changes, call the key influencing factors for dimensionality reduction operation, screen the main feature components according to the results of the dimensionality reduction operation, and call the main feature components to reconstruct the monitoring point data table to generate compressed monitoring data;

[0103] Based on the spatial clustering distribution of the monitoring points, call the classified monitoring data to calculate the range of feature changes. The calculation method of the range of feature changes is , where is the set of monitoring data of each monitoring point. Calculate the set of the range of feature changes of all monitoring points, extract the key influencing factors of the monitoring points according to the range of feature changes. The extraction of the key influencing factors is based on the contribution threshold , and the contribution calculation method is , where is the variance of the feature . Set , that is, the features with a contribution exceeding 10% are selected as the key influencing factors. Call the key influencing factors for dimensionality reduction operation. The dimensionality reduction operation is screened based on the variance contribution rate of the main feature components. The threshold for screening the main components Set the principal components with the cumulative variance contribution rate reaching 90%. For example, if the variance contribution rates of the first three principal components are 50%, 30%, and 10% respectively, then retain the first three principal components for dimensionality reduction. Select the characteristic principal components based on the dimensionality reduction operation results, call the characteristic principal components to reconstruct the monitoring point data table, and finally generate the compressed monitoring data.

[0104] Please refer to Figure 5 , and the specific steps for obtaining the grid monitoring data are as follows:

[0105] S401: Based on the compressed monitoring data, obtain the spatial coordinates and disaster intensity data of the monitoring points. Call the spatial coordinates of the monitoring points to calculate the distances between adjacent monitoring points. Calculate the number density of local monitoring points based on the distances. Call the number density of monitoring points to screen the areas where the aggregation degree of monitoring points in the area exceeds the preset density threshold. Establish the local density distribution of monitoring points based on the screening results to obtain the local density values of monitoring points.

[0106] Based on the compressed monitoring data, obtain the spatial coordinates and disaster intensity data of the monitoring points. Call the spatial coordinates of the monitoring points to calculate the distances between adjacent monitoring points. The Euclidean distance formula is used in the calculation process. , where and are the coordinates of monitoring points i and j respectively. Calculate the distances between all pairs of monitoring points to construct a distance matrix. Calculate the number density of each monitoring point based on this matrix. The number density is defined as the number of monitoring points per unit area, and the calculation formula is , where is the number of monitoring points within the distance from monitoring point i. is the distance to the nearest neighbor monitoring point. Call the calculated number density of monitoring points to screen the areas where the aggregation degree of monitoring points in the area exceeds the preset density threshold . This threshold is set according to the average density of the area. For example, if the average density of monitoring points in a certain area is 100 per square kilometer, the density threshold can be set to 120 per square kilometer. If the calculated density in a certain area is 140 per square kilometer, exceeding the threshold, then this area is classified as a dense area of monitoring points. Establish the local density distribution of monitoring points based on the screening results to finally obtain the local density values of monitoring points.

[0107] S402: Based on the local density values of monitoring points, call the spatial distribution data of monitoring points in the area. Divide the dense area and the sparse area according to the local density range. Call the distribution boundaries of the dense area and the sparse area to calculate the area division threshold. Adjust the spatial range of each area according to the division threshold. Call the adjusted area division results to establish a differential density area to obtain the area density division result.

[0108] Based on the local density values of the monitoring points, call the spatial distribution data of the monitoring points within the area, divide the dense area and the sparse area according to the local density range, and the division process depends on density comparison. Through the set density interval threshold carry out. If the density of a certain area is greater than this threshold, it is divided into a dense area, otherwise it is a sparse area. The threshold is set based on the statistical analysis of the average density of the area. For example, if the average density of the area is 100 monitoring points per square kilometer, the threshold can be set to 80 monitoring points per square kilometer. Calculate the boundary of the dense area and the sparse area to determine the optimal spatial distribution, use morphological operations to determine the area boundary, adjust the spatial range of each area, call the adjusted area division result to establish a differential density area, and finally obtain the area density division result.

[0109] S403: Based on the area density division result, conduct grid division according to the local density, calculate the grid scale, call the dense area to set a small grid division scale, call the sparse area to set a large grid division scale, generate grid division information according to the grid scale of each area, call the grid division scheme to readjust the grid range to which the monitoring points belong, and reconstruct the spatial mapping relationship of the monitoring data according to the adjustment result to obtain the gridded monitoring data;

[0110] The formula for calculating the grid scale is:

[0111] ;

[0112] Among them, represents the grid scale value of the th area, represents the scale adjustment constant, represents the th local density value of the area, represents the small quantity constant to prevent the denominator from being zero, represents the th average disaster intensity value of the area, represents the average value of the area disaster intensity, represents the standard deviation of the area disaster intensity;

[0113] Based on the area density division result, conduct grid division according to the local density. The formula for calculating the grid scale is:

[0114] ;

[0115] Among them, represents the grid scale value of the th area, is the scale adjustment constant, set to 1000 to ensure a moderate scale, is the th local density value of the area, is a small value to prevent division-by-zero errors, set to 0.01, is the average disaster intensity value of the th region, and are the average value and standard deviation of the disaster intensity of all regions respectively. Call the dense region to set the small grid division scale, call the sparse region to set the large grid division scale, and the grid scale of each region is calculated according to the above formula to generate grid division information. Call the grid division scheme to readjust the grid range to which the monitoring points belong, and reconstruct the spatial mapping relationship of the monitoring data according to the adjustment result to finally obtain the gridded monitoring data.

[0116] Set the monitoring point density and disaster intensity data of 5 sub-regions in a certain region as follows: local density , , , , (unit: monitoring points per square kilometer); the average disaster intensity of this region (unit: disaster level); the standard deviation of the disaster intensity of this region ; the average value of the disaster intensity of each sub-region , , , , ; set the adjustment constants , .

[0117] Substitute into the formula for calculation:

[0118] ;

[0119] ;

[0120] ;

[0121] ;

[0122] ;

[0123] Calculation results:

[0124] Dense region : , ;

[0125] Medium-density region : , ;

[0126] Sparse region : ;

[0127] A smaller grid scale is adopted for the dense area, a medium grid scale for the medium-density area, and a larger grid scale for the sparse area. According to the adjustment results, the spatial mapping relationship of the monitoring data is reconstructed, and finally the gridded monitoring data is obtained.

[0128] Please refer to Figure 6 , and the specific steps for obtaining the visualized expression information of geological disaster data are as follows:

[0129] S501: Based on the gridded monitoring data, obtain the spatial coordinates, timestamps, and disaster intensity data of the monitoring points. Call the spatial coordinate data to match the geographic reference coordinate system of the GIS platform. Calculate the longitude and latitude conversion values of the monitoring points according to the geographic reference coordinate system. Call the converted longitude and latitude data and map it to the spatial database of the GIS platform to obtain the GIS-mapped monitoring data;

[0130] Based on the gridded monitoring data, call the stored spatial coordinates of the monitoring points, extract the timestamp and disaster intensity data, traverse the monitoring point dataset, extract the spatial coordinate information of each monitoring point, including longitude and latitude values, call the geographic reference coordinate system of the GIS platform, and convert the spatial coordinates of the monitoring points according to the coordinate system format requirements. The conversion method is to call the coordinate system parameters to calculate the conversion values between the geographic coordinates (WGS84) and the GIS platform coordinate system (GCJ02 or BD09), perform a projection transformation on the longitude and latitude data, set the conversion accuracy threshold to 0.000001 to ensure that the coordinate deviation after conversion is less than this threshold, call the converted longitude and latitude data, map the converted coordinate information to the spatial database of the GIS platform, create a monitoring point information table in the GIS database, with fields including monitoring point number, longitude and latitude coordinates, timestamp, and disaster intensity value. Perform the coordinate mapping operation on all monitoring points in sequence to ensure that the data of all monitoring points establish a mapping relationship in the GIS platform. Traverse the mapped dataset, check the mapping completion degree, calculate the mapping error, and the error calculation method is to call the difference between the original coordinates and the converted coordinates. Set the error threshold to 0.0001. If the error exceeds the threshold, re-execute the coordinate conversion and update the GIS database, and finally obtain the GIS-mapped monitoring data.

[0131] S502: Based on the GIS-mapped monitoring data, call the map level information of the GIS platform, calculate the map display range according to the spatial distribution of the monitoring points, call the map display range data to match the spatial coordinates of the monitoring points, adjust the map display ratio according to the distribution density of the spatial coordinates, divide the map levels according to the adjusted ratio, and obtain the map-leveled monitoring data;

[0132] Based on the GIS mapping monitoring data, call the map level information of the GIS platform, traverse all the monitoring point data, call the spatial coordinate data, calculate the geographical distribution range of the monitoring points. The calculation method is to extract the minimum longitude and latitude values and the maximum longitude and latitude values of the monitoring points, calculate the longitude span and latitude span, and determine the map display range based on the span. Set the minimum and maximum boundaries of the map display range to ensure that the monitoring point data is completely covered within the map display range. Call the map display range data to match the spatial coordinates of the monitoring points, traverse the monitoring point data, and calculate the distribution density of the spatial coordinates within the map range. The calculation method is to divide the map range into 10×10 grid areas, count the number of monitoring points in each grid, calculate the average monitoring point density of each grid, and adjust the map display ratio according to the monitoring point density. Set the map scaling ratio threshold to 1:5000 to 1:50000. If the monitoring point density in a certain area grid exceeds 50, then reduce the map ratio to 1:5000. If the density is less than 5, then enlarge the map ratio to 1:50000. Divide the map levels according to the adjusted ratio. The division method is to set multiple ratio ranges, each range corresponding to a different level, and establish a hierarchical index for the adjusted map data. Finally, obtain the hierarchically monitored map data.

[0133] S503: Based on the hierarchically monitored map data, call the timestamp and disaster intensity data of the monitoring points, calculate the time change trend of the monitoring points according to the timestamp, call the time change trend data to match the spatial coordinates, and display the monitoring point data according to the spatial distribution and time change to obtain the visual expression information of the geological disaster data;

[0134] Based on the hierarchically monitored map data, call the timestamp and disaster intensity data of the monitoring points, traverse the monitoring point data set, extract the time series data of each monitoring point, and calculate the time change trend of the monitoring points. The calculation method is to sort the disaster intensity data of the same monitoring point according to the timestamp, calculate the intensity difference between adjacent time points, and calculate its change rate. Set the change rate threshold to ±10%. If the change rate of three consecutive time points exceeds this threshold, then mark this monitoring point as an abnormal point. Call the time change trend data to match the spatial coordinates, compare the time trends of the monitoring point data in the same area, and calculate the average time change of multiple monitoring points in the same area. The calculation method is to perform a weighted average on the monitoring data with the same timestamp, and set the weighting factor to the normalized value of the spatial correlation weight. Display the monitoring point data according to the spatial distribution and time change, establish a time series visualization layer in the GIS platform, sort the monitoring data according to the timestamp, and display the change trend of the disaster intensity in the form of a dynamic heat map or color gradient change. Finally, obtain the visual expression information of the geological disaster data.

[0135] Please refer to Figure 7, a GIS-based geological disaster monitoring point data expression system. The GIS-based geological disaster monitoring point data expression system is used to execute the above-mentioned GIS-based geological disaster monitoring point data expression method. The system includes:

[0136] The data interpolation processing module obtains the detection data of geological disaster monitoring points, calls the spatial coordinates of the monitoring points and the corresponding monitoring data, calculates the spatial correlation according to the spatial distance between the monitoring points, calculates the monitoring data of the uncollected points based on the spatial correlation, and generates interpolation monitoring values;

[0137] The time series optimization processing module, based on the interpolation monitoring values, obtains the time series data of the monitoring points, aligns the data according to the time series, analyzes the change trend of adjacent moments, calls the state estimation value of the time series, and adjusts the interpolation monitoring values according to the change trend of the time series to obtain time series adjusted monitoring values;

[0138] The data compression processing module, based on the time series adjusted monitoring values, calculates the distance from each monitoring point to the cluster center according to the set number of clusters, classifies the monitoring points into the corresponding clusters according to the shortest distance, calls the classified monitoring data to calculate the feature change range, extracts the feature principal components, and generates compressed monitoring data based on the dimensionality reduction of the feature principal components;

[0139] The grid division module, based on the compressed monitoring data, calculates the local density of the monitoring points, analyzes the spatial distribution characteristics, divides the grid according to the local density, and re-divides the grid according to the division scale of the differentiated area to obtain gridified monitoring data;

[0140] The data mapping and expression module, based on the gridified monitoring data, maps the data to the GIS platform according to the spatial coordinates, calls the map hierarchical processing of the GIS platform, and displays the monitoring point data according to the spatial distribution and time change to generate geological disaster data visualization expression information.

[0141] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for expressing data of geological disaster monitoring points based on GIS, characterized in that It includes the following steps: S1: Obtain the detection data of geological disaster monitoring points, call the spatial coordinates and corresponding monitoring data of the monitoring points, calculate the spatial correlation according to the spatial distance between the monitoring points, calculate the monitoring data of the uncollected points based on the spatial correlation, and generate interpolation monitoring values; S2: Based on the interpolation monitoring values, obtain the time series data of the monitoring points, align the data according to the time series, analyze the change trends at adjacent moments, call the state estimation values of the time series, and adjust the interpolation monitoring values according to the change trends of the time series to obtain time series adjusted monitoring values; The specific steps for obtaining the time series adjusted monitoring values are as follows: S201: Based on the interpolation monitoring values, combined with the time series data index of the monitoring points, call the monitoring point coordinates and monitoring data in the time series, organize the monitoring point data list according to the time order, calculate the time step according to the acquisition time interval between adjacent time points, call the time step to screen the time intervals with data fluctuations, and adjust the data sampling density according to the time intervals to obtain a time series data set; S202: Based on the time series data set, call the monitoring data in the time series, calculate the numerical change rate of the monitoring points at different time points, call the change rate to calculate the similarity between adjacent time points, screen the time periods with stable data change trends in the time series according to the similarity, and call the data in the stable time periods to generate a smooth change curve to obtain time series trend characteristics; S203: Based on the time series trend characteristics and the interpolation monitoring values, calculate the deviation amount of the monitoring data on the time series, call the deviation amount to adjust the state estimation value of the monitoring data, correct the monitoring data in the time series according to the state estimation value, call the corrected data to generate a time series interpolation result, and obtain the time series adjusted monitoring values; S3: Based on the time series adjusted monitoring values, calculate the distance from each monitoring point to the cluster center according to the set number of clusters, classify the monitoring points into the corresponding clusters according to the shortest distance, call the classified monitoring data to calculate the characteristic change range, extract the characteristic principal components, and generate compressed monitoring data based on the dimensionality reduction of the characteristic principal components; S4: Based on the compressed monitoring data, calculate the local density of the monitoring points, analyze the spatial distribution characteristics, divide the grid according to the local density, and re-divide the grid according to the division scale of the differentiated area to obtain gridified monitoring data.

2. The method for expressing geological disaster monitoring point data based on GIS according to claim 1, wherein The interpolation monitoring values include spatial prediction points, monitoring parameter interpolation, and spatial correlation weights. The time series adjusted monitoring values include time-aligned data, state estimation values, and dynamically complemented monitoring parameters. The compressed monitoring data includes clustering center points, characteristic principal components, and a dimensionality reduction monitoring parameter set. The gridified monitoring data includes high-density area grids, low-density area grids, and disaster risk distribution units.

3. The method for expressing geological disaster monitoring point data based on GIS according to claim 1, wherein The specific steps for obtaining the interpolation monitoring values are as follows: S101: Obtain the detection data of geological disaster monitoring points, call the spatial coordinates of the monitoring points and the corresponding monitoring data, including spatial coordinates, geological activity intensity, rainfall, and soil humidity, establish a monitoring point set according to the distribution range of the spatial coordinates, screen out outliers based on the parameter distribution in the monitoring point set, call the outliers for deviation calculation, and adjust the parameter interval of the monitoring point data according to the calculated deviation to obtain a monitoring data set; S102: Based on the monitoring data set, calculate the spatial distance between monitoring points, call the spatial coordinates of the monitoring points, calculate the correlation weight between monitoring points according to the distance between coordinate points, compare with the preset correlation threshold according to the monitoring point correlation weight, screen out pairs of monitoring points with strong spatial correlation, call the selected pairs of monitoring points, calculate the correlation contribution value, and adjust the influence weight between monitoring points according to the contribution value to obtain the spatial correlation weight; S103: Based on the spatial correlation weight, call the spatial coordinates of the uncollected points, and calculate the monitoring parameters of the uncollected points according to the monitoring data and correlation weight of the collected monitoring points to generate interpolation monitoring values.

4. The method for expressing geological disaster monitoring point data based on GIS according to claim 3, wherein The formula for calculating the monitoring parameters of the uncollected points is: ； Among them, represents the interpolation of the monitoring parameter of the uncollected point j, represents the spatial correlation weight between the monitoring point i and the uncollected point j, represents the monitoring data value of the i-th collected monitoring point, and respectively represent the spatial coordinate position values of the i-th collected monitoring point and the uncollected monitoring point j, represents the numerical stability constant, represents the number of collected monitoring points.

5. The method for expressing geological disaster monitoring point data based on GIS according to claim 1, wherein The specific steps for obtaining the compressed monitoring data are as follows: S301: Based on the time series, adjust the monitoring values, obtain the spatial coordinates, disaster intensity, and rainfall monitoring indicators of the monitoring points, call the spatial coordinates of the monitoring points to calculate the Euclidean distance between the monitoring points, construct a monitoring point distance matrix based on the Euclidean distance, call the distance matrix to screen out pairs of monitoring points with close spatial distances, and establish a mapping of the spatial relationship of the monitoring points based on the screening results to obtain the spatial distance distribution of the monitoring points; S302: Based on the spatial distance distribution of the monitoring points, call the set number of clusters to calculate the distance from the monitoring points to the center of each cluster, screen out the cluster center with the shortest distance according to the calculation results, call the screening results to classify the monitoring points, adjust the distribution range of the monitoring points within each cluster according to the classification results, and call the adjusted cluster information to establish the classification result of the monitoring points to obtain the spatial clustering distribution of the monitoring points; S303: Based on the spatial clustering distribution of the monitoring points, call the classified monitoring data to calculate the range of feature changes, extract the key influencing factors of the monitoring points according to the range of feature changes, call the key influencing factors for dimensionality reduction operation, screen out the feature principal components according to the dimensionality reduction operation results, and call the feature principal components to reconstruct the monitoring point data table to generate compressed monitoring data.

6. The method for expressing geological disaster monitoring point data based on GIS according to claim 1, wherein, The specific steps for obtaining the gridified monitoring data are as follows: S401: Based on the compressed monitoring data, obtain the spatial coordinates and disaster intensity data of the monitoring points, call the spatial coordinates of the monitoring points to calculate the distance between adjacent monitoring points, calculate the number density of local monitoring points according to the distance, call the number density of monitoring points to screen out areas where the aggregation degree of monitoring points in the area exceeds the preset density threshold, and establish the local density distribution of the monitoring points based on the screening results to obtain the local density value of the monitoring points; S402: Based on the local density value of the monitoring point, call the spatial distribution data of the monitoring points within the area, divide the dense area and the sparse area according to the local density range, call the distribution boundaries of the dense area and the sparse area to calculate the area division threshold, adjust the spatial range of each area according to the division threshold, call the adjusted area division result to establish a differential density area, and obtain the area density division result; S403: Based on the area density division result, perform grid division according to the local density, calculate the grid scale, call the dense area to set a small grid division scale, call the sparse area to set a large grid division scale, generate grid division information according to the grid scale of each area, call the grid division scheme to readjust the grid range to which the monitoring point belongs, and reconstruct the spatial mapping relationship of the monitoring data according to the adjustment result to obtain the gridified monitoring data; The formula for calculating the grid scale is: ； Among them, represents the grid scale value of the th area, represents the scale adjustment constant, represents the local density value of the th area, represents a small quantity constant to prevent the denominator from being zero, represents the average disaster intensity value of the th area, represents the average value of the regional disaster intensity, represents the standard deviation of the regional disaster intensity.

7. The method for expressing geological disaster monitoring point data based on GIS according to claim 1, characterized in that The method further includes: S5: Based on the gridified monitoring data, map the data to the GIS platform according to the spatial coordinates, call the map hierarchical processing of the GIS platform, display the monitoring point data according to the spatial distribution and time change, and generate the visualization expression information of the geological disaster data; The visualization expression information of the geological disaster data includes the spatially mapped monitoring points, the time evolution curve, and the disaster intensity distribution map.

8. The method for expressing data of geological disaster monitoring points based on GIS according to claim 7, wherein, The specific steps for obtaining the visualization expression information of the geological disaster data are as follows: S501: Based on the gridified monitoring data, obtain the spatial coordinates, timestamps, and disaster intensity data of the monitoring points, call the spatial coordinate data to match the geographical reference coordinate system of the GIS platform, calculate the longitude and latitude conversion values of the monitoring points according to the geographical reference coordinate system, call the converted longitude and latitude data to map to the spatial database of the GIS platform, and obtain the GIS mapped monitoring data; S502: Based on the GIS mapped monitoring data, call the map hierarchical information of the GIS platform, calculate the map display range according to the spatial distribution of the monitoring points, call the map display range data to match the spatial coordinates of the monitoring points, adjust the map display ratio according to the distribution density of the spatial coordinates, divide the map hierarchy according to the adjusted ratio, and obtain the map hierarchically monitored data; S503: Based on the map hierarchically monitored data, call the timestamps and disaster intensity data of the monitoring points, calculate the time change trend of the monitoring points according to the timestamps, call the time change trend data to match the spatial coordinates, and display the monitoring point data according to the spatial distribution and time change to obtain the visualization expression information of the geological disaster data.

9. A data expression system for geological disaster monitoring points based on GIS, characterized in that, For implementing the GIS-based geological disaster monitoring point data expression method according to any one of claims 1-8, the system includes: The data interpolation processing module obtains the detection data of the geological disaster monitoring points, calls the spatial coordinates of the monitoring points and the corresponding monitoring data, calculates the spatial correlation according to the spatial distance between the monitoring points, calculates the monitoring data of the uncollected points according to the spatial correlation, and generates the interpolation monitoring value; The timing optimization processing module obtains the time series data of the monitoring points based on the interpolation monitoring values, aligns the data according to the time series, analyzes the change trend at adjacent times, calls the state estimation value of the time series, and adjusts the interpolation monitoring values according to the change trend of the time series to obtain the timing-adjusted monitoring values; The specific steps for obtaining the timing-adjusted monitoring values are as follows: Based on the interpolation monitoring values, combined with the time series data index of the monitoring points, call the monitoring point coordinates and monitoring data in the time series, sort the monitoring point data list according to the time order, calculate the time step according to the acquisition time interval between adjacent time points, call the time step to screen the time interval of data fluctuations, and adjust the data sampling density according to the time interval to obtain the time series data set; Based on the time series data set, call the monitoring data in the time series, calculate the numerical change rate of the monitoring points at different time points, call the change rate to calculate the similarity between adjacent time points, screen the time period with stable data change trend in the time series according to the similarity, and call the data in the stable time period to generate a smooth change curve to obtain the timing trend characteristics; Based on the timing trend characteristics and the interpolation monitoring values, calculate the deviation amount of the monitoring data on the time series, call the deviation amount to adjust the state estimation value of the monitoring data, correct the monitoring data in the time series according to the state estimation value, call the corrected data to generate the time series interpolation result, and obtain the timing-adjusted monitoring values; The data compression processing module calculates the distance from each monitoring point to the cluster center based on the timing-adjusted monitoring values according to the set number of clusters, classifies the monitoring points into the corresponding clusters according to the shortest distance, calls the classified monitoring data to calculate the feature change range, extracts the principal feature components, and reduces the dimension based on the principal feature components to generate the compressed monitoring data; The grid division module calculates the local density of the monitoring points based on the compressed monitoring data, analyzes the spatial distribution characteristics, divides the grid according to the local density, and re-divides the grid according to the division scale of the differentiated area to obtain the gridded monitoring data; The data mapping and expression module maps the data to the GIS platform based on the gridded monitoring data according to the spatial coordinates, calls the map hierarchical processing of the GIS platform, and displays the monitoring point data according to the spatial distribution and time change to generate the visualization expression information of the geological disaster data.

Images