A method and system for monitoring land subsidence by integrating Beidou and InSAR data

Abstract

The present application provides a method and system for monitoring surface subsidence by integrating Beidou and InSAR data. Among them, positioning data from the Beidou satellite system and surface deformation data obtained by the synthetic aperture radar interferometry system are received; based on the positioning data and the surface deformation data, the surface deformation data is corrected according to environmental factors through a spatio-temporal fusion model to obtain the corrected surface deformation data; using the corrected surface deformation data, a multi-period analysis technique is adopted to determine the development trend of surface subsidence and generate a surface subsidence distribution map, and the surface subsidence distribution map is used to display the spatial distribution characteristics of surface subsidence; according to the surface subsidence distribution map, the spatio-temporal fusion model is used to monitor the future surface subsidence situation, and the surface subsidence monitoring report can provide a scientific basis for the early warning and prevention of geological disasters. The present application improves the efficiency and effect of surface subsidence monitoring.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of surface subsidence monitoring, and in particular, to a method and system for surface subsidence monitoring that integrates Beidou and InSAR data. Background Art

[0002] With the acceleration of the urbanization process, surface subsidence has become one of the important factors affecting urban safety and sustainable development. Surface subsidence not only causes direct economic losses such as building damage and underground pipeline rupture, but may also induce geological disasters and threaten life and property safety.

[0003] Currently, surface subsidence monitoring mainly relies on traditional ground measurement techniques and space observation techniques. Ground measurement techniques such as leveling and GPS measurement, although having high accuracy, are costly and difficult to achieve large-scale continuous monitoring. And space observation techniques mainly include using synthetic aperture radar interferometry (InSAR) technology, which can achieve large-scale and high-resolution surface deformation monitoring. However, the InSAR technology is greatly affected by factors such as atmospheric delay and terrain undulation, resulting in certain errors in its monitoring results.

[0004] Although traditional ground measurement techniques have high accuracy, due to the need for a large amount of human and material resources input, it is difficult to promote and apply them on a large scale, and long-term continuous monitoring cannot be achieved. Existing InSAR technology can achieve large-scale surface deformation monitoring, but in practical applications, it is easily affected by environmental factors such as atmospheric delay and terrain undulation, resulting in deviations in monitoring results. Summary of the Invention

[0005] The embodiments of the present application provide a method and system for surface subsidence monitoring that integrates Beidou and InSAR data to solve the problem of poor technical level of surface subsidence monitoring in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a method for surface subsidence monitoring that integrates Beidou and InSAR data, including:

[0007] Receiving positioning data from the Beidou satellite system and surface deformation data obtained by a synthetic aperture radar interferometry system;

[0008] Based on the positioning data and the surface deformation data, constructing a spatio-temporal fusion model to correct the surface deformation data according to environmental factors through the spatio-temporal fusion model, so as to obtain corrected surface deformation data, where the environmental factors at least include atmospheric delay and terrain undulation;

[0009] Using the corrected surface deformation data and adopting multi-period analysis technology, the development trend of surface subsidence is determined, and a surface subsidence distribution map is generated, which is used to display the spatial distribution characteristics of surface subsidence;

[0010] According to the surface subsidence distribution map, the spatio-temporal fusion model is used to monitor the future surface subsidence situation, and a surface subsidence monitoring report is generated, which can provide a scientific basis for the early warning and prevention of geological disasters.

[0011] In a second aspect, an embodiment of the present application provides a surface subsidence monitoring system that integrates Beidou and InSAR data, including:

[0012] A receiving module for receiving positioning data from the Beidou satellite system and surface deformation data obtained by an interferometric synthetic aperture radar system;

[0013] A construction module for constructing a spatio-temporal fusion model based on the positioning data and the surface deformation data, so as to correct the surface deformation data according to environmental factors through the spatio-temporal fusion model, and obtain corrected surface deformation data, where the environmental factors at least include atmospheric delay and terrain undulation;

[0014] A generation module for using the corrected surface deformation data and adopting multi-period analysis technology to determine the development trend of surface subsidence and generate a surface subsidence distribution map, which is used to display the spatial distribution characteristics of surface subsidence; according to the surface subsidence distribution map, the spatio-temporal fusion model is used to monitor the future surface subsidence situation, and a surface subsidence monitoring report is generated, which can provide a scientific basis for the early warning and prevention of geological disasters.

[0015] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a surface subsidence monitoring method that integrates Beidou and InSAR data as described in the first aspect above.

[0016] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it implements a surface subsidence monitoring method that integrates Beidou and InSAR data as described in the first aspect.

[0017] In the embodiments of the present application, by fusing the positioning data of the Beidou satellite system with the surface deformation data obtained by InSAR (Interferometric Synthetic Aperture Radar), a spatio-temporal fusion model is constructed, which can effectively reduce the errors brought by a single data source and improve the accuracy of surface subsidence monitoring. Considering the influence of environmental factors such as atmospheric delay and terrain undulation on the surface deformation data, these factors are corrected through the model, making the monitoring results closer to the actual situation, and enhancing the environmental adaptability and reliability of the system. The generated surface subsidence distribution map can visually display the spatial distribution characteristics of surface subsidence, while the surface subsidence monitoring report provides a scientific basis, which helps to carry out geological disaster early warning and prevention work and improves the decision-making support ability of the government and relevant departments.

[0018] Furthermore, in the present application, the Kalman filter algorithm is used to suppress the noise of the surface deformation data set, improving the data quality and ensuring the accuracy of subsequent analysis. Through the GIS spatial analysis tool, key feature data of surface subsidence can be accurately extracted, such as the location of the subsidence center, the maximum subsidence amount, the subsidence rate, and the subsidence range, providing a solid data foundation for the analysis of the subsidence trend. By adopting the autoregressive integrated moving average model combined with wavelet transform technology, not only can the long-term development trend of surface subsidence be analyzed, but also the subsidence patterns at different frequencies can be captured, realizing a comprehensive analysis of the surface subsidence trend. The surface subsidence distribution map drawn by using 3D visualization technology can more intuitively display the subsidence area division, subsidence intensity distribution, subsidence rate distribution, and time variation, which helps professionals quickly understand the surface subsidence situation.

[0019] Even further, in the present application, by analyzing the long-term development trend and periodic changes of surface subsidence, and combining with the subsidence patterns at different time scales obtained by wavelet transform technology, the short-term development trend of surface subsidence can be predicted more accurately, improving the timeliness and accuracy of the prediction. By synthesizing the long-term and short-term development trends, the generated surface subsidence analysis conclusion is more comprehensive and in-depth, providing strong support for formulating effective geological disaster prevention and control strategies. The surface subsidence development trend report generated based on the detailed analysis conclusion not only contains rich charts and data, but also provides a clear trend judgment, which helps relevant institutions and personnel better understand and deal with the surface subsidence problem.

[0020] The above beneficial effects together constitute an efficient, accurate and widely applicable surface subsidence monitoring system, which has important practical significance for preventing and reducing geological disasters.

[0021] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a flowchart of a method for monitoring surface subsidence by fusing Beidou and InSAR data provided by an embodiment of the present application;

[0024] Figure 2 It is a schematic structural diagram of a system for monitoring surface subsidence by fusing Beidou and InSAR data provided by an embodiment of the present application;

[0025] Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of the present application. Specific embodiments

[0026] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application.

[0027] In some processes described in the specification, claims and the above-mentioned accompanying drawings of the present application, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0029] Figure 1 A flowchart of a method for monitoring surface subsidence by fusing Beidou and InSAR data is provided for an embodiment of the present application. As Figure 1 shown, the method includes:

[0030] 101. Receive positioning data from the Beidou Satellite System and surface deformation data obtained by an Interferometric Synthetic Aperture Radar (InSAR) system;

[0031] In this step, the Beidou Satellite System is a global satellite navigation system independently developed in China, which can provide accurate position information and services. The system consists of three parts: a space segment, a ground segment, and a user segment, and can provide all-weather, all-time, and high-precision positioning, navigation, and timing services for global users. The Interferometric Synthetic Aperture Radar (InSAR) system is a remote sensing technology that detects small changes on the Earth's surface by using two or more Synthetic Aperture Radar (SAR) images. These images are usually taken by satellites at different time points, and by comparing the phase differences between these images, the deformation of the Earth's surface can be calculated.

[0032] In the embodiments of this application, in the field of urban planning, by combining the accurate position information provided by the Beidou Satellite System with the high-resolution surface deformation data obtained by InSAR technology, the settlement of the urban surface can be effectively monitored, providing important data support for the safety assessment and maintenance of urban infrastructure.

[0033] 102. Based on the positioning data and the surface deformation data, construct a spatio-temporal fusion model to correct the surface deformation data according to environmental factors through the spatio-temporal fusion model, and obtain the corrected surface deformation data, where the environmental factors at least include atmospheric delay and terrain undulation;

[0034] In this step, the spatio-temporal fusion model refers to a method of combining data in two dimensions of time and space and analyzing and processing surface deformation data through mathematical modeling. This model can more accurately reflect the actual situation of surface deformation and reduce data errors caused by environmental factors such as atmospheric delay and terrain undulation.

[0035] In the embodiments of this application, in seismological research, researchers can use the spatio-temporal fusion model to analyze the surface deformation data before and after an earthquake to help understand the earthquake occurrence mechanism and its impact on the Earth's surface, thereby improving the accuracy of earthquake prediction.

[0036] Optionally, the step of "correcting the surface deformation data according to environmental factors by using the spatio-temporal fusion model in step 102 to obtain corrected surface deformation data" includes: using the spatio-temporal fusion model, combining the preset meteorological data and atmospheric model, to correct the atmospheric delay effect in the surface deformation data, reducing the influence of atmospheric delay on the surface deformation data, to obtain preliminarily corrected surface deformation data; using the spatio-temporal fusion model, combining the preset elevation data and terrain model, to correct the terrain undulation effect in the preliminarily corrected surface deformation data, reducing the influence of terrain undulation on the surface deformation data, to obtain finally corrected surface deformation data.

[0037] In the field of geographic information science and remote sensing, surface deformation data refers to the information on the change of the Earth's surface position obtained through satellite or ground measurement techniques, which can reflect surface changes caused by crustal movement, geological disasters, human activities, etc. The spatio-temporal fusion model is a data processing method that combines the time and space dimensions, aiming to improve the spatial resolution and time continuity of data. In the process of correcting surface deformation data, meteorological data and atmospheric models are used to evaluate and correct the signal delay caused by changes in atmospheric conditions (such as temperature, humidity, air pressure), that is, the atmospheric delay effect. And elevation data and terrain models are used to analyze and adjust the observation errors caused by terrain differences, that is, the terrain undulation effect.

[0038] The process of correcting surface deformation data first involves using the spatio-temporal fusion model to combine the preset meteorological data and atmospheric model to correct the atmospheric delay effect caused by changes in atmospheric conditions in the original surface deformation data. This step can significantly reduce the influence of atmospheric conditions on the surface deformation measurement results, so as to obtain preliminarily corrected surface deformation data. Next, based on the preliminarily corrected data, the spatio-temporal fusion model is used again, this time combining the preset elevation data and terrain model to correct the terrain undulation effect. This process helps to further eliminate the interference of terrain factors on the surface deformation data, and finally outputs comprehensively corrected surface deformation data, providing more accurate basic data for subsequent analysis and research.

[0039] The above steps are described in more detail below:

[0040] Receive the positioning data from the Beidou satellite system and the surface deformation data obtained by the synthetic aperture radar interferometry system.

[0041] Then preprocess the above data, where the preprocessing includes: time synchronization, noise removal, missing value filling, format conversion and other processing.

[0042] Time synchronization: Ensure that the timestamps of all data points are consistent for subsequent analysis.

[0043] Noise removal: Use the Kalman filtering algorithm to reduce random errors or outliers in the observed data.

[0044] Missing value imputation: For data records with missing values, use interpolation or other statistical methods to estimate reasonable values.

[0045] Format conversion: Unify the formats of data from different sources so that they can be processed on the same platform.

[0046] Next, calculate the specific impact of the atmospheric delay effect on the surface deformation data, and then make corrections accordingly to obtain the preliminarily corrected surface deformation data.

[0047] Based on the preliminarily corrected data, apply the spatio-temporal fusion model again, paying particular attention to how terrain undulations affect the measurement results of surface deformation, and finally output the comprehensively corrected surface deformation data.

[0048] Then use the autoregressive integrated moving average model (ARIMA) to process time series data with trends and seasonality to help predict surface subsidence in a future time period.

[0049] Use the multi-resolution analysis of wavelet transform technology for non-stationary signals to reveal subsidence patterns at different frequencies.

[0050] Finally, use the spatial analysis tools of geographic information system (GIS) to process and analyze geospatial data, and extract key features such as the location of the subsidence center, the maximum subsidence amount, the subsidence rate, and the subsidence range.

[0051] Train the selected model using historical data and evaluate its performance through means such as cross-validation to ensure that the model can accurately reflect the actual situation.

[0052] The model parameters or structure can also be continuously optimized according to the feedback until a satisfactory accuracy is achieved.

[0053] The corrected surface deformation data is organized into a multi-period dataset according to the time series, and the Kalman filtering algorithm is used to perform noise suppression processing on each period of the surface deformation dataset to obtain an optimized surface deformation dataset.

[0054] Based on the optimized surface deformation dataset, apply the spatial analysis tools of GIS to extract the key feature data of surface subsidence for each period, including the location of the subsidence center, the maximum subsidence amount, the subsidence rate, and the subsidence range.

[0055] Using the autoregressive integrated moving average model (ARIMA) combined with wavelet transform technology, comprehensively analyze multi-period surface deformation datasets, analyze long-term development trends, periodic changes, and settlement patterns at different frequencies to comprehensively understand surface settlement, determine the development trend of surface settlement, and generate a development trend report of surface settlement. The final output is comprehensively corrected surface deformation data, which is closer to the real surface settlement situation and provides a solid foundation for subsequent trend analysis.

[0056] The following further explains the construction process of the spatio-temporal fusion model, meteorological data, and atmospheric model, as well as the process of using these models to correct surface deformation data:

[0057] First, high-precision positioning data need to be obtained, which usually come from global navigation satellite systems (GNSS), such as GPS, GLONASS, Galileo, or the Beidou system. These data provide time series measurements of surface positions. Collect surface deformation data obtained through various remote sensing technologies (such as InSAR). Such data can reflect the changes of the surface at different time points. Clean the original data, including removing noise, filling in missing values, and unifying the time and space coordinate systems to ensure data quality and consistency.

[0058] Second, extract time series features (such as timestamps, rates of change) and spatial features (such as position coordinates, deformation amounts) from the preprocessed data. These features will be used in the subsequent modeling process. At the same time, collect meteorological data (temperature, humidity, air pressure, etc.) and elevation data (DEM) to prepare for the correction of atmospheric delay and terrain relief effects.

[0059] Furthermore, according to the characteristics and requirements of the study area, select a suitable spatio-temporal fusion model, such as the spatio-temporal autoregressive moving average model (STARMA), spatio-temporal Kriging interpolation method, or machine learning / deep learning model. Use the extracted time series features and spatial features as inputs, combined with some known surface deformation results as output labels, to train and construct the spatio-temporal fusion model. In addition, evaluate the model performance through methods such as cross-validation and adjust the parameters to optimize the model.

[0060] Even further, select a suitable atmospheric model (such as GPT2, VMF3), which should be able to simulate the delays caused by the ionosphere and troposphere. Calibrate the atmospheric model using meteorological data, and combine the atmospheric model with the spatio-temporal fusion model to form an atmospheric delay correction model to automatically consider the impact of atmospheric delay during the analysis process. And construct a terrain model based on DEM data to quantify the impact of terrain relief on the observed data. Integrate the terrain model into the spatio-temporal fusion model to form a terrain relief correction model to correct the deviation caused by the terrain.

[0061] Furthermore, an atmospheric delay correction model is used to calculate the atmospheric delay impact at each observation point, and based on this, the preliminary surface deformation data is adjusted to reduce the impact caused by atmospheric delay, obtaining the preliminarily corrected surface deformation data. Further, a terrain undulation correction model is used to process the preliminarily corrected surface deformation data to eliminate the errors brought by terrain undulation, obtaining the finally corrected surface deformation data.

[0062] Finally, during the entire correction process, result verification is continuously carried out to ensure that each step has achieved the expected effect. When necessary, return to the previous step for parameter adjustment or model improvement. According to the verification feedback, continuously optimize the model structure and parameter settings until the model performance reaches the best state.

[0063] This process ensures that every link from feature extraction to the final correction result is systematically considered and processed, thereby improving the accuracy of surface deformation monitoring.

[0064] It should be noted that in the above process, the process of combining the atmospheric model with the spatio-temporal fusion model mainly includes the following processes:

[0065] First, select a suitable atmospheric model (such as GPT2, VMF3), which can calculate the delay effects of the ionosphere and troposphere based on geographical location, time, and meteorological parameters (temperature, humidity, pressure, etc.). Use historical meteorological data (which can be obtained from global or regional meteorological services) to calibrate the atmospheric model to ensure its applicability to the study area.

[0066] Secondly, add a new input dimension in the spatio-temporal fusion model to represent the atmospheric delay value at each observation point. This can be achieved by adding the delay value calculated by the atmospheric model as an additional feature to the spatio-temporal fusion model. Modify the structure or algorithm of the spatio-temporal fusion model so that it can consider the impact of atmospheric delay when predicting surface deformation. For example, new features can be added in a machine learning model, or a mathematical expression of atmospheric delay can be introduced in a physical model.

[0067] Finally, construct an atmospheric delay correction model that takes the output of the spatio-temporal fusion model (uncorrected surface deformation data) and the delay estimate provided by the atmospheric model as inputs and outputs the corrected surface deformation data. This correction process can be achieved by directly subtracting the estimated atmospheric delay amount from the original measurement value, or by more complex mathematical operations, such as iterative least squares method, to improve the accuracy.

[0068] In the above process, the process of integrating the terrain model into the spatio-temporal fusion model mainly includes the following processes:

[0069] First, construct a terrain model based on DEM data, which can accurately represent the elevation changes of the earth's surface. Analyze the relationship between the terrain model and surface deformation, and identify terrain factors that may affect the observation results, such as slope, curvature, etc.

[0070] Secondly, similar to the atmospheric model, the outputs of the terrain model (such as slope, elevation difference, etc.) are added as new features to the spatio-temporal fusion model. Adjust the spatio-temporal fusion model so that it can take into account the impact of terrain undulations on the observed data during the prediction process. This may involve modifying the parameter settings of the model or adopting algorithms more suitable for handling complex spatial correlations.

[0071] Finally, create a terrain undulation correction model that adjusts the surface deformation data based on the output of the terrain model. This process can also be a simple numerical subtraction or may involve more complex statistical or physical methods, with the aim of removing systematic biases caused by the terrain.

[0072] In the above process, the process of using two correction models for data correction respectively includes:

[0073] First, for each observation point, first calculate the atmospheric delay impact at this point using the atmospheric delay correction model. This usually involves the following steps:

[0074] Input the timestamp, geographical location, and relevant meteorological parameters of the observation point into the atmospheric model to obtain the atmospheric delay estimate at this point.

[0075] Apply the atmospheric delay estimate to the uncorrected surface deformation data, and reduce the impact caused by the atmospheric delay through appropriate methods (such as subtraction or more complex adjustment formulas, which can be set according to requirements).

[0076] Output the preliminarily corrected surface deformation data.

[0077] Next, for the preliminarily corrected data, further process it using the terrain undulation correction model:

[0078] Input the geographical location of the observation point into the terrain model to obtain the terrain information of the observation point (such as elevation, slope, etc.).

[0079] Adjust the preliminarily corrected surface deformation data according to the terrain information to eliminate the errors caused by terrain undulations. This involves adjusting based on the deformation offset predicted by the terrain model, which can be set specifically according to requirements.

[0080] Output the finally corrected surface deformation data.

[0081] In the embodiments of the present application, it is assumed that in a seismic monitoring project, researchers need to accurately understand the changes in the surface of a certain area to predict possible geological disasters. First, they collected the surface deformation data of the area, and at the same time obtained the corresponding meteorological data (such as temperature, humidity, air pressure, etc.), atmospheric model parameters, as well as detailed topographic maps and elevation data. Then, applying the spatio-temporal fusion model, the researchers first calculated the specific impact of the atmospheric delay effect on the surface deformation data based on the meteorological data and the atmospheric model, and made corrections accordingly to obtain a preliminary corrected data set. Subsequently, using the same spatio-temporal fusion model, combined with the topographic map and elevation data, the preliminary corrected data was further adjusted, with particular attention paid to how the terrain undulations affect the measurement results of the surface deformation. After these two steps of correction, the researchers obtained more accurate surface deformation data, which is of great significance for accurately assessing seismic risks and guiding disaster prevention and mitigation work.

[0082] 103. Using the corrected surface deformation data, adopting the multi-period analysis technique, determine the development trend of the surface subsidence, and generate a surface subsidence distribution map, which is used to show the spatial distribution characteristics of the surface subsidence;

[0083] In this step, the multi-period analysis technique refers to a technique that identifies the trends and development patterns of surface changes by comparing and analyzing the surface deformation data in different time periods. This method can more clearly show the change process of the surface subsidence and help evaluate the speed and scope of the subsidence.

[0084] In the embodiments of the present application, in the environmental protection of mining areas, the multi-period analysis technique can be used to regularly monitor the surface subsidence situation around the mining areas, timely discover potential geological disaster risks, take corresponding preventive measures, and protect the lives and property safety of the mining areas and the surrounding residents.

[0085] Optionally, the step of "using the corrected surface deformation data, adopting multi-period analysis technology, determining the development trend of surface subsidence, and generating a surface subsidence distribution map" in step 103 includes: organizing the corrected surface deformation data into a multi-period surface deformation data set according to the time series, and adopting the Kalman filter algorithm to perform noise suppression processing on each period of the surface deformation data set to obtain an optimized surface deformation data set; based on the optimized surface deformation data set, applying the spatial analysis tool of the geographic information system to extract the key feature data of surface subsidence for each period, and the key feature data includes the settlement center position, the maximum settlement amount, the settlement rate, and the settlement range; using the key feature data, adopting the autoregressive integrated moving average model to comprehensively analyze the multi-period surface deformation data set, and combining the wavelet transform technology to analyze the settlement patterns at different frequencies to determine the development trend of surface subsidence, and generating a development trend report of surface subsidence; based on the key feature data and the development trend report, using three-dimensional visualization technology to draw a surface subsidence distribution map, and the surface subsidence distribution map is used to display the spatial distribution characteristics of surface subsidence.

[0086] Among them, the displayed spatial distribution characteristics include settlement area division, settlement intensity distribution, settlement rate distribution, and time variation. The settlement area division refers to dividing the surface subsidence area into different sub-areas according to the settlement center position and the settlement range; the settlement intensity distribution refers to displaying the maximum settlement amount and the average settlement amount in each sub-area, and using colors or heights to represent the settlement intensity; the settlement rate distribution refers to displaying the settlement rate in each sub-area, and using colors or arrows to represent the direction and magnitude of the settlement rate; the time variation refers to displaying the surface subsidence conditions at different time points, and showing the dynamic changes of surface subsidence through animations or time series graphs.

[0087] The analysis of the development trend of land subsidence refers to identifying the trend and development pattern of land subsidence by analyzing the changes in land deformation data at multiple time points. The corrected land deformation data is a more accurate data set obtained by removing the influence of atmospheric delay effect and topographic undulation effect. The multi-period analysis technique means arranging the land deformation data collected at different time points in chronological order to form a series of data sets for tracking the changes of the land surface over time. The Kalman filter algorithm is a method for estimating the state of a system from a series of incomplete and noisy measurements and is used here to reduce the noise in the land deformation data. The autoregressive integrated moving average model (ARIMA) is a statistical model commonly used in time series data analysis and can help predict future trends. The wavelet transform technique is a signal processing technique suitable for analyzing different frequency components of non-stationary signals. The spatial analysis tools of Geographic Information System (GIS) can be used to process and analyze geospatial data and extract key feature data of land subsidence, such as the location of the subsidence center, the maximum subsidence amount, the subsidence rate, and the subsidence range. The three-dimensional visualization technique is used to create an intuitive graphical representation to help understand and display the spatial distribution characteristics of land subsidence.

[0088] First, organize the corrected land deformation data into multi-period data sets according to the time series and apply the Kalman filter algorithm for processing to reduce the noise and obtain an optimized land deformation data set. Then, based on the optimized data set, use the spatial analysis tools of GIS to extract the key feature data of land subsidence for each period, including the location of the subsidence center, the maximum subsidence amount, the subsidence rate, and the subsidence range. Next, use the autoregressive integrated moving average model (ARIMA) combined with the wavelet transform technique to comprehensively analyze the multi-period land deformation data sets, determine the development trend of land subsidence, and compile a development trend report. Finally, based on the extracted key feature data and the compiled development trend report, use the three-dimensional visualization technique to draw a land subsidence distribution map to intuitively show the spatial distribution characteristics of land subsidence, including the division of subsidence areas, the distribution of subsidence intensity, the distribution of subsidence rate, and the time variation.

[0089] In the embodiments of the present application, it is assumed that in an urban groundwater resource management project, in order to evaluate the impact of groundwater extraction on land subsidence, the project team collected and corrected land deformation data for multiple periods. First, they used the Kalman filtering algorithm to suppress the noise of these data to ensure the accuracy of the data. Then, through GIS software, the team extracted the key feature data of land subsidence for each period, such as the location of the subsidence center and the maximum subsidence amount. Next, the project team used the ARIMA model combined with wavelet transform technology to analyze the subsidence patterns at different frequencies, revealed the development trend of land subsidence over time, and prepared a detailed development trend report. Finally, based on the above analysis results, the team used 3D visualization technology to produce a land subsidence distribution map, which not only showed the division of the subsidence area, but also vividly presented the distribution of subsidence intensity and rate in the form of color and height, as well as the dynamic changes of land subsidence at different time points. This distribution map became an important reference basis for decision-makers to formulate groundwater management and urban planning strategies.

[0090] 104. According to the land subsidence distribution map, use the spatio-temporal fusion model to monitor the future land subsidence situation and generate a land subsidence monitoring report, which can provide a scientific basis for the early warning and prevention of geological disasters.

[0091] In this step, the land subsidence distribution map is a map drawn based on the corrected land deformation data, which is used to intuitively display the spatial distribution characteristics of land subsidence. Such a map can help decision-makers quickly understand which areas have relatively serious land subsidence and need to be focused on. The land subsidence monitoring report is a document compiled based on the analysis results of the land subsidence distribution map and the spatio-temporal fusion model, aiming to provide a scientific basis for the early warning and prevention of geological disasters. The report usually contains information such as specific data of land subsidence, development trends, and possible problems.

[0092] In the embodiments of the present application, in the flood control project of a coastal city, using the analysis results in the land subsidence monitoring report, preparations for the change of the groundwater level caused by the sea level rise can be made in advance, the drainage system design can be optimized, the coastline protection measures can be strengthened, and the risk of flood disasters can be effectively reduced.

[0093] Optionally, the step 104 of "monitoring the future ground settlement situation by using the spatio-temporal fusion model according to the ground settlement distribution map and generating a ground settlement monitoring report" includes: extracting the spatial distribution characteristics and settlement degree of the ground settlement from the ground settlement distribution map; based on the extracted spatial distribution characteristics and settlement degree of the ground settlement, using the spatio-temporal fusion model, combining historical ground deformation data and real-time ground deformation data, continuously monitoring and predicting the future ground settlement situation to obtain the latest short-term development trend and the latest long-term development trend; generating a ground settlement monitoring report based on the latest short-term development trend and long-term development trend of the ground settlement, and the ground settlement monitoring report details the current situation of the ground settlement, the latest short-term development trend and the latest long-term development trend.

[0094] Among them, the process of using the spatio-temporal fusion model, combining historical ground deformation data and real-time ground deformation data, continuously monitoring and predicting the future ground settlement situation to obtain the latest short-term development trend and the latest long-term development trend includes: using historical ground deformation data and real-time ground deformation data to prepare data and form a comprehensive data set; based on the comprehensive data set, updating the spatio-temporal fusion model to ensure that the spatio-temporal fusion model can capture the latest time and space change characteristics of the ground settlement; using the updated spatio-temporal fusion model to perform short-term prediction on the most recent ground deformation data set to obtain the latest short-term development trend of the ground settlement; using the updated spatio-temporal fusion model to perform long-term prediction on multi-period ground deformation data to obtain the latest long-term development trend of the ground settlement.

[0095] Ground settlement monitoring refers to the process of continuously monitoring and predicting the future ground settlement situation by analyzing the spatial distribution characteristics and settlement degree of the ground settlement, combining historical ground deformation data and real-time ground deformation data, and using a spatio-temporal fusion model. The spatial distribution characteristics of the ground settlement include the location, scope and layout of the settlement area on the map, while the settlement degree involves indicators such as the depth and speed of the settlement. The spatio-temporal fusion model is a prediction model that can simultaneously consider factors in the time and space dimensions, aiming to improve the accuracy and reliability of the prediction. Historical ground deformation data refers to the ground deformation data collected over a past period of time, while real-time ground deformation data refers to the most recently obtained data. The combination of the two helps to more comprehensively understand the development trend of the ground settlement. The ground settlement monitoring report is a detailed document that records the current situation of the ground settlement, the latest short-term development trend and the long-term development trend, providing a scientific basis for decision-making.

[0096] First, extract the spatial distribution characteristics and settlement degree of ground settlement from the ground settlement distribution map. Then, based on the extracted information, combine the historical ground deformation data and real-time ground deformation data, and use the spatio-temporal fusion model to continuously monitor and predict the future ground settlement situation. Specifically, this includes a data preparation stage, that is, integrating historical and real-time data to form a comprehensive data set; subsequently, updating the spatio-temporal fusion model based on the comprehensive data set to ensure that the model can capture the latest temporal and spatial change characteristics of ground settlement. Then, use the updated model to make short-term predictions on the ground deformation data of the most recent period to obtain the latest short-term development trend; at the same time, also make long-term predictions on the ground deformation data of multiple periods to determine the latest long-term development trend. Finally, generate a ground settlement monitoring report based on these prediction results, which details the current situation and development trend.

[0097] In the embodiment of this application, it is assumed that in a ground settlement monitoring project in a coastal city, the research team first extracted the spatial distribution characteristics and settlement degree of ground settlement from the previously made ground settlement distribution map, such as which areas have the most serious settlement and what is the settlement speed. Subsequently, the team integrated the historical ground deformation data of the past few years and the real-time ground deformation data of the recent few months to form a comprehensive data set. Based on this comprehensive data set, the team updated their spatio-temporal fusion model to better reflect the current temporal and spatial change characteristics of ground settlement. Using the updated model, the team made short-term predictions on the ground deformation data of the most recent period, predicting the ground settlement trend in the next few months; at the same time, they also made long-term predictions on the ground deformation data of multiple past periods, predicting the ground settlement development in the next few years. Based on these prediction results, the team compiled a detailed ground settlement monitoring report, which not only summarized the current ground settlement situation but also provided the latest short-term and long-term development trends, providing important data support for urban planning and disaster prevention and mitigation.

[0098] Optionally, the development trend of the ground settlement includes a long-term development trend and a short-term development trend; by using the key feature data, an autoregressive integrated moving average model is adopted to comprehensively analyze multi-period ground deformation data sets, and the wavelet transform technology is combined to analyze the settlement patterns at different frequencies to determine the development trend of the ground settlement and generate a development trend report of the ground settlement, including: using the key feature data to construct an autoregressive integrated moving average model, where the autoregressive integrated moving average model is a model that can reflect the characteristics of the ground settlement time series; based on the autoregressive integrated moving average model, comprehensively analyze multi-period ground deformation data sets to obtain the long-term development trend and periodic changes of the ground settlement, where the long-term development trend of the ground settlement refers to the change situation of the ground settlement on a relatively long time scale; the periodic change refers to the regular change that the ground settlement repeats within a certain time period; using the wavelet transform technology to perform multi-resolution analysis on multi-period ground deformation data sets to obtain the settlement patterns at different time scales, where the settlement pattern refers to the manifestation form and characteristics of the ground settlement in time and space, including seasonal changes, short-term fluctuations and other periodic characteristics; comprehensively considering the long-term development trend, the periodic changes and the settlement patterns to determine the short-term development trend of the ground settlement; where the short-term development trend of the ground settlement refers to the change situation of the ground settlement on a relatively short time scale; according to the long-term development trend and the short-term development trend of the ground settlement, generate an analysis conclusion of the ground settlement; based on the analysis conclusion, generate a development trend report of the ground settlement.

[0099] The development trend of the ground settlement includes a long-term development trend and a short-term development trend. The long-term development trend refers to the overall change direction of the ground settlement over a relatively long time span (such as several years or longer), reflecting the basic trend of the ground settlement. The short-term development trend is the specific change situation of the ground settlement on a relatively short time scale (such as several months or within a year), usually affected by factors such as seasonal changes and short-term fluctuations. The autoregressive integrated moving average model (ARIMA model) is a statistical method used to process time series data, especially suitable for data with trends and seasonality. This model captures the characteristics of the time series through the autoregressive part (AR), the differencing part (I), and the moving average part (MA). The wavelet transform technology is a signal processing method that can perform multi-resolution analysis on data, is suitable for analyzing non-stationary signals, and can effectively reveal the settlement patterns at different time scales, including seasonal changes, short-term fluctuations and other periodic characteristics.

[0100] First, construct an ARIMA model using the key characteristic data of ground settlement, which can reflect the characteristics of the ground settlement time series. Based on the constructed ARIMA model, comprehensively analyze the multi-period ground deformation data sets to identify the long-term development trend and periodic changes of ground settlement. The long-term development trend reveals the overall change direction of ground settlement over time, while the periodic changes show the regular fluctuations of ground settlement within a specific time period. Next, apply wavelet transform technology to perform multi-resolution analysis on the same data set to identify settlement patterns at different time scales, including seasonal changes, short-term fluctuations, etc. Finally, combine the long-term development trend, periodic changes, and settlement patterns to determine the short-term development trend of ground settlement. According to these analysis results, generate a development trend report of ground settlement, which summarizes the current state of ground settlement and its possible future trends.

[0101] In the embodiment of the present application, assume that a certain city is experiencing significant ground settlement problems. To better understand and predict this phenomenon, the relevant departments decide to adopt the above-mentioned solution. First, they collect the key characteristic data of ground settlement in this city in the past ten years, such as settlement rate, settlement area, etc., and use this data to construct an ARIMA model. Through the analysis of this model, they find that there is an obvious long-term downward trend in ground settlement, and at the same time, the phenomenon of accelerated settlement due to the increase in groundwater extraction in summer every year is also very obvious. Next, the research team uses wavelet transform technology to perform multi-resolution analysis on the same data set and finds that in addition to the significant settlement in summer, there is also a slight recovery trend in winter, which may be due to the natural rise of the groundwater level in winter. Combining these long-term trends, periodic changes, and settlement patterns, the research team predicts the short-term development trend of ground settlement in the next year, and it is expected that the settlement in summer will further intensify. Based on the above analysis, the relevant departments generate a detailed development trend report of ground settlement. This report not only provides an important reference for the city's water resource management and land use planning, but also provides a scientific basis for public safety and disaster prevention work.

[0102] Optionally, the determining the short-term development trend of ground settlement by integrating the long-term development trend, the periodic changes, and the settlement pattern includes: using the long-term development trend, the periodic changes, and the settlement pattern to form a comprehensive data set; according to the comprehensive data set, select a time series analysis model suitable for short-term prediction, and train the selected time series analysis model to ensure that the time series analysis model can capture the short-term change characteristics of ground settlement; based on the trained time series analysis model, perform short-term prediction on the most recent ground deformation data set to obtain the short-term development trend of ground settlement.

[0103] The short-term development trend of land subsidence refers to the specific changes in land subsidence within a relatively short period (such as several months or one year), which are usually affected by factors such as seasonal changes and short-term fluctuations. The long-term development trend refers to the overall change direction of land subsidence over a relatively long time span (such as several years or longer), reflecting the basic trend of land subsidence. Periodic changes refer to the regular changes that land subsidence repeats within a certain time period, such as seasonal changes. The subsidence pattern refers to the manifestation and characteristics of land subsidence in time and space, including seasonal changes, short-term fluctuations, and other periodic features. The comprehensive dataset is a dataset composed of various data such as long-term development trends, periodic changes, and subsidence patterns, which is used to comprehensively reflect the situation of land subsidence. The time series analysis model is a statistical model used to predict the future values of time series data. Common models include ARIMA, exponential smoothing method, etc.

[0104] First, a comprehensive dataset is formed using the long-term development trend, periodic changes, and subsidence pattern. This dataset contains information on the changes in land subsidence at various time scales, providing a basis for subsequent analysis. Then, according to the characteristics of the comprehensive dataset, a time series analysis model suitable for short-term prediction is selected and trained to ensure that the model can capture the short-term change characteristics of land subsidence. Common models include ARIMA, exponential smoothing method, etc. Finally, based on the trained time series analysis model, a short-term prediction is made for the most recent land deformation dataset to obtain the short-term development trend of land subsidence. This process can help decision-makers timely understand the latest dynamics of land subsidence and provide a basis for taking corresponding management and response measures.

[0105] In the embodiment of this application, it is assumed that a certain city is experiencing significant land subsidence problems. To predict the land subsidence situation in the next few months, the relevant department decides to adopt the above-mentioned scheme. First, they integrate the land subsidence data of the past ten years, including characteristics such as long-term development trends, seasonal changes, and short-term fluctuations, to form a comprehensive dataset. Then, according to the characteristics of the comprehensive dataset, the ARIMA model is selected as the time series analysis model for short-term prediction and the model is trained. During the training process, they ensure that the model can accurately capture the short-term change characteristics of land subsidence, especially seasonal changes and short-term fluctuations. Finally, based on the trained ARIMA model, a short-term prediction is made for the most recent land deformation dataset, and the short-term development trend of land subsidence in the next 6 months is obtained. The prediction results show that land subsidence will intensify in summer, especially in areas with large groundwater extraction. Based on these prediction results, the relevant department formulates specific response measures, such as adjusting the groundwater extraction plan and strengthening monitoring and early warning, to reduce the negative impact of land subsidence. This short-term development trend report provides an important scientific basis for the city's water resource management and land use planning.

[0106] Optionally, generating an analysis conclusion of ground settlement according to the long-term development trend and short-term development trend of the ground settlement, including: generating a short-term analysis conclusion of the ground settlement according to the short-term development trend of the ground settlement, wherein the short-term development trend includes the change rate of recent data, the fluctuation condition of recent data, and the periodic change of recent data; generating a long-term analysis conclusion of the ground settlement according to the long-term development trend of the ground settlement, wherein the long-term development trend includes the change rate of historical data, the fluctuation condition of historical data, and the periodic change of historical data; generating an analysis conclusion of the ground settlement according to the long-term analysis conclusion and the short-term analysis conclusion of the ground settlement.

[0107] Among them, generating a short-term analysis conclusion of the ground settlement according to the short-term development trend of the ground settlement includes: analyzing the ground settlement by using the change rate of recent data, judging whether the ground settlement is accelerating or decelerating, and generating a first conclusion according to the judgment result; analyzing the ground settlement by using the fluctuation condition of recent data, judging whether the ground settlement is in a stable state or there is instability, and generating a second conclusion according to the judgment result; analyzing the ground settlement by using the periodic change of recent data, judging whether there is a periodic feature in the ground settlement, and generating a third conclusion according to the judgment result; generating a short-term analysis conclusion of the ground settlement according to the first conclusion, the second conclusion, and the third conclusion.

[0108] Among them, generating a long-term analysis conclusion of the ground settlement according to the long-term development trend of the ground settlement includes: analyzing the ground settlement by using the change rate of historical data, judging the long-term change direction of the ground settlement, and generating a fourth conclusion according to the judgment result; analyzing the ground settlement by using the fluctuation condition of historical data, judging the long-term stability of the ground settlement, and generating a fifth conclusion according to the judgment result; analyzing the ground settlement by using the periodic change of historical data, judging the long-term periodic feature of the ground settlement, and generating a sixth conclusion according to the judgment result; generating a long-term analysis conclusion of the ground settlement according to the fourth conclusion, the fifth conclusion, and the sixth conclusion.

[0109] The analysis conclusion of ground settlement refers to the conclusion obtained through comprehensive analysis of the short-term and long-term development trends of ground settlement, which is used to describe the current state of ground settlement and its future change trend. The short-term development trend includes the change rate, fluctuation situation and periodic change of recent data, which are used to evaluate the specific changes of ground settlement in the short term. The long-term development trend includes the change rate, fluctuation situation and periodic change of historical data, which are used to evaluate the overall change direction of ground settlement over a long time span. The change rate refers to the change speed of ground settlement per unit time, the fluctuation situation refers to the fluctuation degree of ground settlement in the time series, and the periodic change refers to the regular change that appears repeatedly within a specific time period of ground settlement.

[0110] First, according to the short-term development trend of ground settlement, generate a short-term analysis conclusion. The specific steps include: using the change rate of recent data to judge whether the ground settlement is accelerating or decelerating, and generating the first conclusion; using the fluctuation situation of recent data to judge whether the ground settlement is in a stable state or there is instability, and generating the second conclusion; using the periodic change of recent data to judge whether there is a periodic characteristic in the ground settlement, and generating the third conclusion. Then, synthesize the first, second and third conclusions to generate the short-term analysis conclusion of ground settlement. Secondly, according to the long-term development trend of ground settlement, generate a long-term analysis conclusion. The specific steps include: using the change rate of historical data to judge the long-term change direction of ground settlement, and generating the fourth conclusion; using the fluctuation situation of historical data to judge the long-term stability of ground settlement, and generating the fifth conclusion; using the periodic change of historical data to judge the long-term periodic characteristic of ground settlement, and generating the sixth conclusion. Then, synthesize the fourth, fifth and sixth conclusions to generate the long-term analysis conclusion of ground settlement. Finally, according to the short-term analysis conclusion and the long-term analysis conclusion, generate the final analysis conclusion of ground settlement, which comprehensively describes the current state of ground settlement and its future change trend.

[0111] In the embodiment of the present application, it is assumed that a certain city has experienced significant ground settlement problems in the past few years. In order to better understand this phenomenon and predict its future trend, the relevant department decides to adopt the above scheme for analysis. First, they collected the ground settlement data of the recent year, including the settlement rate, fluctuation situation and periodic change of each month. By analyzing these data, they found that:

[0112] The first conclusion of the short-term analysis: The change rate of recent data shows that the ground settlement accelerates in summer and slows down in winter. The second conclusion: The fluctuation situation of recent data shows that there are large fluctuations in the ground settlement in some months, especially during the rainy season. The third conclusion: The periodic change of recent data shows that there are obvious seasonal changes in the ground settlement, with the settlement accelerating in summer and alleviating in winter.

[0113] Combining the above three conclusions, the short-term analysis conclusion of ground settlement is generated: Ground settlement shows obvious seasonal variations in the short term, accelerating in summer, slowing down in winter, and having large fluctuations during the rainy season.

[0114] Fourth conclusion of the long-term analysis: The change rate of historical data shows that ground settlement has generally shown a downward trend in the past decade, but the rate of decline has slowed down in recent years. Fifth conclusion: The fluctuation of historical data shows that ground settlement has large fluctuations in some years, especially in years with large groundwater extraction. Sixth conclusion: The periodic changes of historical data indicate that ground settlement has certain periodic characteristics, especially the periodic changes related to groundwater extraction and seasonal rainfall.

[0115] Combining the above three conclusions, the long-term analysis conclusion of ground settlement is generated: Ground settlement shows a downward trend in the long term, but the rate of decline gradually slows down, and there are large fluctuations in years with large groundwater extraction, showing periodic characteristics related to groundwater extraction and seasonal rainfall.

[0116] Combining the short-term analysis conclusion and the long-term analysis conclusion, the final analysis conclusion of ground settlement is generated: Ground settlement shows obvious seasonal variations in the short term, accelerating in summer, slowing down in winter, and having large fluctuations during the rainy season. In the long term, ground settlement shows a downward trend, but the rate of decline gradually slows down, and there are large fluctuations in years with large groundwater extraction, showing periodic characteristics related to groundwater extraction and seasonal rainfall.

[0117] This application takes into account that with the acceleration of the urbanization process, the development and utilization of underground space are becoming increasingly frequent, and ground settlement has become a problem that cannot be ignored. Ground settlement not only affects the safety of buildings but may also trigger a series of environmental problems. Therefore, accurately predicting ground settlement is of great significance for urban planning and environmental protection. As a time series analysis method, the autoregressive integrated moving average model (ARIMA) has a good performance in dealing with non-stationary time series data and is widely used in many fields such as economy, meteorology, and engineering. This case applies the ARIMA model to the prediction of ground settlement to improve the prediction accuracy.

[0118] Optionally, constructing the autoregressive integrated moving average model using the key feature data includes:

[0119] Constructing the autoregressive integrated moving average model using the key feature data, where the key feature data includes the location of the settlement center , the maximum settlement , the settlement rate and the settlement range , The autoregressive integrated moving average model refers to a model that can reflect the characteristics of the surface settlement time series. The model formula of the autoregressive integrated moving average model is defined as:

[0120]

[0121] Among them, The observed value of surface settlement at time ; The constant term of the model, representing the average level of surface settlement The order of the autoregressive term, representing the lag order of the autoregressive part in the model The autoregressive coefficient, representing the relationship between surface settlement at time and ; The order of the moving average term, representing the lag order of the moving average part in the model The moving average coefficient, representing the error relationship between surface settlement at time and ; The white noise error term at time , representing random disturbance The coefficient of the settlement center position ; The coefficient of the maximum settlement ; The coefficient of the settlement rate ; The coefficient of the settlement range ;

[0122] The above formula is constructed based on the ARIMA model and is specifically extended for the surface settlement problem. The traditional ARIMA model is mainly used to process one-dimensional time series data, while surface settlement is affected by various factors, such as the settlement center position ( ), the maximum settlement ( ), the settlement rate ( ), and the settlement range ( ), etc. These key feature data directly reflect the physical characteristics of surface settlement. Incorporating them into the model can more accurately capture the characteristics of the surface settlement time series, thereby improving the accuracy of prediction.

[0123] The following briefly introduces the design reasons for each item of this formula:

[0124]

[0125] The autoregressive term : Ground settlement is a time-dependent process, that is, the current settlement amount is affected by past settlement amounts. By introducing autoregressive terms, this temporal dependence can be captured, enabling the model to better predict future change trends. The order of the autoregressive terms is usually determined by analyzing the autocorrelation function (ACF) and partial autocorrelation function (PACF) of the data to find the optimal lag order.

[0126] Constant term : Represents the long-term average level of ground settlement, which reflects the overall trend of ground settlement. Introducing the constant term ensures that the model can still reflect the basic level of ground settlement when there are no other external influences. This is very important for the stability and interpretability of the model.

[0127] Settlement characteristic variables and their coefficients : Ground settlement is not only a function of time but also affected by various geographical and physical factors. The location of the settlement center , the maximum settlement amount , the settlement rate and the settlement range are specific manifestations of these factors. By introducing these variables and their coefficients, the complexity of ground settlement can be more comprehensively described, improving the prediction accuracy of the model. The coefficients are determined through data analysis and fitting, reflecting the degree of influence of these characteristic variables on ground settlement.

[0128] Moving average terms : Moving average terms are used to capture the temporal dependence of the random error terms in the model. There may be some random disturbances during the ground settlement process, and these disturbances may be correlated over time. By introducing moving average terms, the impact of these random fluctuations on the prediction results can be reduced, making the model more robust. The order of the moving average terms is also determined by analyzing the ACF and PACF of the data.

[0129] White noise error terms : Represent the random disturbances that the model cannot explain. In any practical application, there is always a certain degree of uncertainty, and these uncertainties can be modeled through white noise error terms. Introducing white noise error terms can make the model more in line with the actual situation and improve the reliability of the prediction.

[0130] The following briefly introduces the acquisition methods of the parameters in this formula:

[0131] Location of the settlement center , the maximum settlement amount , the settlement rate and settlement range : These data can usually be obtained through geological surveys, remote sensing monitoring, or ground measurements. For example, high-precision surface settlement data can be obtained through satellite radar interferometry (InSAR).

[0132] Autoregressive coefficient , Moving average coefficient , Settlement characteristic variable coefficient and constant term : These parameters need to be obtained by fitting historical surface settlement data, and common methods include the least squares method, maximum likelihood estimation, etc.

[0133] In the embodiment of the present application, assume that there is a set of surface settlement data, which includes monthly observations for the past 5 years. To simplify the calculation, a simplified example is set:

[0134] Model parameter setting: (i.e., first-order autoregression and first-order moving average)

[0135] Assume known parameters:

[0136]

[0137] Key feature data:

[0138] Previous observation value:

[0139] Previous error term:

[0140] According to the above settings, the predicted value of the surface settlement in the t-th period can be calculated as follows:

[0141]

[0142] The calculation results show that according to the given key feature data and model parameters, the predicted surface settlement in the next period (the t-th period) is about 2.405 units. This result indicates that considering the historical trend of surface settlement and the influence of key features, it is expected that the surface settlement will continue to develop at a certain rate. This prediction can help urban planners and decision-makers take preventive measures to mitigate the negative impacts brought by surface settlement. However, it should be noted that in practical applications, more real-time data and environmental conditions need to be combined for adjustment to ensure the accuracy of the prediction.

[0143] Figure 2 The following is a schematic structural diagram of a surface settlement monitoring system that integrates Beidou and InSAR data provided by the embodiment of the present application, as Figure 2 shown, the device includes:

[0144] A receiving module 21, configured to receive positioning data from the Beidou satellite system and surface deformation data obtained by an InSAR (Interferometric Synthetic Aperture Radar) system;

[0145] A constructing module 22, configured to construct a spatio-temporal fusion model based on the positioning data and the surface deformation data, so as to correct the surface deformation data according to environmental factors through the spatio-temporal fusion model to obtain corrected surface deformation data, where the environmental factors at least include atmospheric delay and terrain undulation;

[0146] A generating module 23, configured to use the corrected surface deformation data, adopt a multi-period analysis technique to determine the development trend of surface subsidence, and generate a surface subsidence distribution map, where the surface subsidence distribution map is used to display the spatial distribution characteristics of surface subsidence; according to the surface subsidence distribution map, use the spatio-temporal fusion model to monitor future surface subsidence conditions and generate a surface subsidence monitoring report, and the surface subsidence monitoring report can provide a scientific basis for the early warning and prevention of geological disasters.

[0147] Figure 2 The described surface subsidence monitoring system integrating Beidou and InSAR data can execute Figure 1 The described surface subsidence monitoring method integrating Beidou and InSAR data in the illustrated embodiment, its implementation principle and technical effects will not be elaborated. For the surface subsidence monitoring system integrating Beidou and InSAR data in the above embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0148] In a possible design, Figure 2 The surface subsidence monitoring system integrating Beidou and InSAR data in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, and this computing device may include a storage component 31 and a processing component 32;

[0149] The storage component 31 stores one or more computer instructions, where the one or more computer instructions are called and executed by the processing component 32.

[0150] The processing component 32 is configured to: receive positioning data from the Beidou satellite system and surface deformation data obtained by the synthetic aperture radar interferometry system; based on the positioning data and the surface deformation data, correct the surface deformation data according to environmental factors through a spatio-temporal fusion model to obtain the corrected surface deformation data; use the corrected surface deformation data, adopt a multi-period analysis technique to determine the development trend of surface subsidence, and generate a surface subsidence distribution map, which is used to display the spatial distribution characteristics of surface subsidence; according to the surface subsidence distribution map, use the spatio-temporal fusion model to monitor the future surface subsidence situation, and the surface subsidence monitoring report can provide a scientific basis for the early warning and prevention of geological disasters.

[0151] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0152] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0153] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0154] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0155] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0156] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources leased or purchased from the cloud computing platform.

[0157] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the aboveFigure 1 A method for monitoring land subsidence by integrating Beidou and InSAR data in the illustrated embodiment.

[0158] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0159] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0160] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A surface subsidence monitoring method integrating Beidou and InSAR data, characterized in that: include: Receive positioning data from the BeiDou satellite system and surface deformation data obtained by the synthetic aperture radar interferometry system; Based on the positioning data and the surface deformation data, a spatiotemporal fusion model is constructed to correct the surface deformation data according to environmental factors through the spatiotemporal fusion model to obtain corrected surface deformation data, wherein the environmental factors at least include atmospheric delay and terrain undulation; Using the corrected surface deformation data and adopting multi-period analysis technology, the development trend of surface subsidence is determined, and a surface subsidence distribution map is generated, which is used to show the spatial distribution characteristics of surface subsidence; According to the surface subsidence distribution map, the future surface subsidence is monitored using the spatiotemporal fusion model to generate a surface subsidence monitoring report; The modified surface deformation data is used to determine the development trend of surface subsidence by adopting multi-period analysis technology, and generate a surface subsidence distribution map, including: The corrected surface deformation data are organized into multiple-period surface deformation data sets according to the time series, and the Kalman filter algorithm is used to perform noise suppression on the surface deformation data sets of each period to obtain the optimized surface deformation data set. Based on the optimized surface deformation data set, the spatial analysis tools of the geographic information system are used to extract the key characteristic data of each period of surface settlement, which include the settlement center position, maximum settlement amount, settlement rate and settlement range; Using the key characteristic data, the autoregressive integrated moving average model is used to comprehensively analyze the surface deformation data sets of multiple periods, and the settlement patterns under different frequencies are analyzed in combination with the wavelet transform technology to determine the development trend of surface settlement and generate a development trend report of surface settlement; The development trend of the surface subsidence includes a long-term development trend and a short-term development trend; The key characteristic data is used to comprehensively analyze the multi-period surface deformation data set using an autoregressive integrated moving average model, and the settlement patterns at different frequencies are analyzed in combination with wavelet transform technology to determine the development trend of surface settlement, and generate a surface settlement development trend report, including: Using the key characteristic data, an autoregressive integrated moving average model is constructed, wherein the autoregressive integrated moving average model refers to a model that can reflect the time series characteristics of surface settlement; Based on the autoregressive integrated moving average model, a comprehensive analysis of multiple periods of surface deformation data sets is performed to obtain the long-term development trend and periodic changes of surface subsidence; Using wavelet transform technology, multi-resolution analysis of multi-period surface deformation data sets was performed to obtain settlement patterns at different time scales. Determine the short-term development trend of surface subsidence by combining the long-term development trend, the periodic changes and the subsidence pattern; Generating an analysis conclusion of the surface subsidence according to the long-term development trend and short-term development trend of the surface subsidence; Based on the analysis conclusions, a development trend report of surface subsidence is generated.

2. The method according to claim 1, characterized in that The method of determining the short-term development trend of surface subsidence by integrating the long-term development trend, the periodic change and the subsidence pattern includes: utilizing the long-term trends, the cyclical changes, and the sedimentation patterns to form a comprehensive data set; Selecting a time series analysis model suitable for short-term prediction based on the comprehensive data set, and training the selected time series analysis model to ensure that the time series analysis model can capture the short-term variation characteristics of surface subsidence; Based on the trained time series analysis model, the short-term prediction of the most recent surface deformation data set is carried out to obtain the short-term development trend of surface subsidence.

3. The method according to claim 1, characterized in that The analysis conclusion of the surface subsidence is generated according to the long-term development trend and short-term development trend of the surface subsidence, including: Generating a short-term analysis conclusion of the surface subsidence according to the short-term development trend of the surface subsidence, wherein the short-term development trend includes the rate of change of recent data, the fluctuation of recent data and the periodic change of recent data; Generate a long-term analysis conclusion of the surface subsidence according to the long-term development trend of the surface subsidence, wherein the long-term development trend includes the change rate of historical data, the fluctuation of historical data and the periodic change of historical data; generating an analysis conclusion of the surface subsidence according to the long-term analysis conclusion of the surface subsidence and the short-term analysis conclusion of the surface subsidence; Wherein, generating a short-term analysis conclusion of the surface subsidence according to the short-term development trend of the surface subsidence includes: analyzing the surface subsidence by using the change rate of recent data to determine whether the surface subsidence is accelerating or decelerating, and generating a first conclusion according to the determination result; analyzing the surface subsidence by using the fluctuation of recent data to determine whether the surface subsidence is in a stable state or unstable, and generating a second conclusion according to the determination result; analyzing the surface subsidence by using the periodic changes of recent data to determine whether the surface subsidence has periodic characteristics, and generating a third conclusion according to the determination result; generating a short-term analysis conclusion of the surface subsidence according to the first conclusion, the second conclusion and the third conclusion; Among them, generating a long-term analysis conclusion of surface subsidence based on the long-term development trend of the surface subsidence includes: using the change rate of historical data to analyze the surface subsidence, judging the long-term change direction of the surface subsidence, and generating a fourth conclusion based on the judgment result; using the fluctuation of historical data to analyze the surface subsidence, judging the long-term stability of the surface subsidence, and generating a fifth conclusion based on the judgment result; using the periodic changes of historical data to analyze the surface subsidence, judging the long-term periodic characteristics of the surface subsidence, and generating a sixth conclusion based on the judgment result; generating a long-term analysis conclusion of surface subsidence based on the fourth conclusion, the fifth conclusion and the sixth conclusion.

4. The method according to claim 1, characterized in that: The method of monitoring future surface subsidence conditions based on the surface subsidence distribution map and using the spatiotemporal fusion model to generate a surface subsidence monitoring report includes: Extracting the spatial distribution characteristics and the degree of surface subsidence from the surface subsidence distribution map; Based on the extracted spatial distribution characteristics and extent of surface subsidence, the spatiotemporal fusion model is used to continuously monitor and predict future surface subsidence in combination with historical surface deformation data and real-time surface deformation data, so as to obtain the latest short-term development trend and the latest long-term development trend; The process of using the spatiotemporal fusion model, in combination with historical surface deformation data and real-time surface deformation data, to continuously monitor and predict future surface subsidence to obtain the latest short-term development trend and the latest long-term development trend includes: using historical surface deformation data and real-time surface deformation data to prepare data and form a comprehensive data set; based on the comprehensive data set, updating the spatiotemporal fusion model to ensure that the spatiotemporal fusion model can capture the latest temporal and spatial variation characteristics of surface subsidence; using the updated spatiotemporal fusion model to perform short-term prediction on the most recent period of surface deformation data set to obtain the latest short-term development trend of surface subsidence; using the updated spatiotemporal fusion model to perform long-term prediction on multiple periods of surface deformation data to obtain the latest long-term development trend of surface subsidence; Based on the latest short-term development trend and long-term development trend of surface subsidence, a surface subsidence monitoring report is generated, and the surface subsidence monitoring report records in detail the current status of surface subsidence, the latest short-term development trend and the latest long-term development trend.

5. The method according to claim 1, characterized in that The surface deformation data is corrected according to environmental factors by the spatiotemporal fusion model to obtain the corrected surface deformation data, including: Using the spatiotemporal fusion model, combined with preset meteorological data and atmospheric models, the atmospheric delay effect in the surface deformation data is corrected to reduce the influence of the atmospheric delay on the surface deformation data, and obtain preliminary corrected surface deformation data; The spatiotemporal fusion model is used in combination with preset elevation data and terrain models to correct the terrain undulation effect in the initially corrected surface deformation data, reduce the impact of terrain undulation on the surface deformation data, and obtain the final corrected surface deformation data.

6. A surface subsidence monitoring system integrating Beidou and InSAR data, characterized in that: include: A receiving module is used to receive positioning data from the Beidou satellite system and surface deformation data obtained by the synthetic aperture radar interferometry system; A construction module, configured to construct a spatiotemporal fusion model based on the positioning data and the surface deformation data, so as to correct the surface deformation data according to environmental factors through the spatiotemporal fusion model to obtain corrected surface deformation data, wherein the environmental factors at least include atmospheric delay and terrain undulation; A generation module is used to use the corrected surface deformation data and multi-period analysis technology to determine the development trend of surface subsidence and generate a surface subsidence distribution map, which is used to show the spatial distribution characteristics of surface subsidence; based on the surface subsidence distribution map, the spatiotemporal fusion model is used to monitor future surface subsidence and generate a surface subsidence monitoring report; The modified surface deformation data is used to determine the development trend of surface subsidence by adopting multi-period analysis technology, and generate a surface subsidence distribution map, including: The corrected surface deformation data are organized into multiple-period surface deformation data sets according to the time series, and the Kalman filter algorithm is used to perform noise suppression on the surface deformation data sets of each period to obtain the optimized surface deformation data set. Based on the optimized surface deformation data set, the spatial analysis tools of the geographic information system are used to extract the key characteristic data of each period of surface settlement, which include the settlement center position, maximum settlement amount, settlement rate and settlement range; Using the key characteristic data, the autoregressive integrated moving average model is used to comprehensively analyze the surface deformation data sets of multiple periods, and the settlement patterns under different frequencies are analyzed in combination with the wavelet transform technology to determine the development trend of surface settlement and generate a development trend report of surface settlement; The development trend of the surface subsidence includes a long-term development trend and a short-term development trend; The key characteristic data is used to comprehensively analyze the multi-period surface deformation data set using an autoregressive integrated moving average model, and the settlement patterns at different frequencies are analyzed in combination with wavelet transform technology to determine the development trend of surface settlement, and generate a surface settlement development trend report, including: Using the key characteristic data, an autoregressive integrated moving average model is constructed, wherein the autoregressive integrated moving average model refers to a model that can reflect the time series characteristics of surface settlement; Based on the autoregressive integrated moving average model, a comprehensive analysis of multiple periods of surface deformation data sets is performed to obtain the long-term development trend and periodic changes of surface subsidence; Using wavelet transform technology, multi-resolution analysis of multi-period surface deformation data sets was performed to obtain settlement patterns at different time scales. Determine the short-term development trend of surface subsidence by combining the long-term development trend, the periodic changes and the subsidence pattern; Generating an analysis conclusion of the surface subsidence according to the long-term development trend and short-term development trend of the surface subsidence; Based on the analysis conclusions, a development trend report of surface subsidence is generated.

7. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a surface subsidence monitoring method that integrates Beidou and InSAR data as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a surface subsidence monitoring method integrating Beidou and InSAR data as described in any one of claims 1 to 5 is implemented.

Images