Sky-ground integrated geological environment monitoring and evaluating method and system

Abstract

The invention relates to the technical field of data processing, and discloses a sky-ground integrated geological environment monitoring and evaluation method and system. The method comprises the following steps: fusing sky remote sensing, surface monitoring and underground detection data into a monitoring matrix, and processing to generate an original database; constructing a space-time standard field based on the database, and fusing to generate an associated pedigree; decomposing the associated pedigree to obtain an element feature chain; constructing a coupling dynamic field based on the feature chain, and analyzing to obtain an evolution parameter set; establishing a risk assessment matrix according to the parameter set, and analyzing and generating an early warning index system; and combining an early warning system and historical cases to design a treatment scheme. According to the method, the unified space-time standard field, the multilevel feature transfer network and the dynamic coupling model are constructed, deep fusion of the space-based remote sensing data, the surface monitoring data and the underground detection data is realized, and the accuracy and reliability of geological environment monitoring and evaluation are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a method and system for integrated sky-ground geological environment monitoring and assessment. Background Art

[0002] Geological environment monitoring and assessment is an important part of geological disaster prevention and control. Traditional geological environment monitoring methods mainly rely on a single data source, such as ground monitoring stations, satellite remote sensing, etc. In recent years, with the development of multi-source remote sensing technology, Internet of Things technology, and artificial intelligence technology, geological environment monitoring has gradually developed in the direction of multi-source data fusion. At present, a variety of monitoring technologies have been developed, including InSAR deformation monitoring, GNSS continuous monitoring, and groundwater dynamic monitoring, and have been widely used in geological disaster monitoring and early warning. At the same time, data analysis methods based on deep learning, numerical simulation methods based on physical mechanisms, and expert systems based on knowledge graphs are also constantly developing, providing new technical means for geological environment monitoring and assessment.

[0003] However, the existing geological environment monitoring and assessment methods have problems such as insufficient data integration, incomplete monitoring levels, and single assessment methods. Specifically, space-based remote sensing data, surface monitoring data, and underground detection data are often processed independently, lacking an effective collaborative analysis mechanism; the spatiotemporal resolution of monitoring data is inconsistent, making it difficult to achieve accurate docking of multi-source data; risk assessment methods rely too much on empirical judgments and lack systematic and quantitative assessment standards; the early warning indicator system is not perfect enough to accurately reflect the evolutionary characteristics and development trends of the geological environment; the formulation of governance plans lacks data support, making it difficult to achieve precise governance. Summary of the invention

[0004] The present application provides a method and system for geological environment monitoring and assessment that integrates space, ground and space, which is used to achieve deep integration of space-based remote sensing data, surface monitoring data and underground detection data by constructing a unified space-time standard field, a multi-level feature transfer network and a dynamic coupling model, thereby improving the accuracy and reliability of geological environment monitoring and assessment.

[0005] In the first aspect, the present application provides a sky-ground integrated geological environment monitoring and assessment method, which includes: integrating pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into a sky-ground integrated monitoring matrix, and generating a geological environment original database after layered outlier processing; constructing a sky-ground integrated space-time standard field based on the geological environment original database, and generating a geological environment correlation spectrum through space-time alignment and data fusion; performing multi-dimensional feature decomposition on the geological environment correlation spectrum, and generating a geological element feature chain through sky-ground collaborative analysis; constructing a sky-ground coupled dynamic field based on the geological element feature chain, and obtaining a geological environment evolution parameter set through multi-field coupling analysis; establishing a sky-ground integrated risk assessment matrix based on the geological environment evolution parameter set, and generating a risk warning indicator system through quantitative hierarchical analysis; taking the risk warning indicator system as a benchmark, combining the historical case library to design a sky-ground collaborative plan to generate a geological environment governance plan.

[0006] In a second aspect, the present application provides a sky-ground integrated geological environment monitoring and assessment system, the sky-ground integrated geological environment monitoring and assessment system comprising:

[0007] The acquisition module is used to integrate the pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into the sky-ground integrated monitoring matrix, and generate the original geological environment database after layered outlier processing;

[0008] A generation module is used to construct a sky-ground integrated space-time standard field based on the original geological environment database, and generate a geological environment correlation spectrum through space-time registration and data fusion;

[0009] The decomposition module is used to perform multi-dimensional feature decomposition of geological environment association spectrum and generate geological element feature chains through sky-ground collaborative analysis;

[0010] The coupling module is used to construct the sky-ground coupling dynamic field based on the characteristic chain of geological elements, and obtain the geological environment evolution parameter set through multi-field coupling analysis;

[0011] The classification module is used to establish a sky-ground integrated risk assessment matrix based on the geological environment evolution parameter set and generate a risk warning indicator system through quantitative classification analysis;

[0012] The design module is used to design sky-ground collaborative plans based on the risk warning indicator system and the historical case library to generate geological environment governance plans.

[0013] In the technical solution provided by the present application, by integrating the pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into the sky-ground integrated monitoring matrix, the coordinated collection of multi-source data is realized, the comprehensiveness and systematicness of data collection are ensured, and the original geological environment database generated after layered outlier processing has high data quality; based on the original geological environment database, a sky-ground integrated spatiotemporal standard field is constructed, and a geological environment correlation spectrum is generated through spatiotemporal registration and data fusion, realizing the deep fusion and spatiotemporal alignment of multi-source heterogeneous data; the geological environment correlation spectrum is decomposed into multiple dimensions, and the sky-ground collaborative analysis is carried out. The characteristic chain of geological elements is generated, the key characteristics of geological elements are extracted and the correlation between elements is established; the sky-ground coupling dynamic field is constructed based on the characteristic chain of geological elements, and the geological environment evolution parameter set is obtained through multi-field coupling analysis, realizing the accurate characterization of the dynamic evolution characteristics of the geological environment; the sky-ground integrated risk assessment matrix is ​​established according to the geological environment evolution parameter set, and the risk warning indicator system generated through quantitative hierarchical analysis has strong scientificity and operability; based on the risk warning indicator system, the sky-ground collaborative plan is designed in combination with the historical case library, and the generated geological environment governance plan has strong pertinence and practicality. This method organically integrates the monitoring data of the three levels of sky, surface and underground, establishes a complete data processing, analysis, evaluation and governance process, and significantly improves the accuracy and reliability of geological environment monitoring and evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0015] Figure 1 A schematic diagram of an embodiment of the sky-ground integrated geological environment monitoring and assessment method in the embodiment of the present application;

[0016] Figure 2 A schematic diagram of rock mass stress in an embodiment of the present application;

[0017] Figure 3 A schematic diagram of stratum displacement in an embodiment of the present application;

[0018] Figure 4 It is a schematic diagram of an embodiment of the sky-ground integrated geological environment monitoring and evaluation system in the embodiment of the present application. DETAILED DESCRIPTION

[0019] The embodiment of the present application provides a method and system for monitoring and evaluating geological environment in an integrated manner between sky and ground. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the sky-ground integrated geological environment monitoring and assessment method in the embodiment of the present application includes:

[0021] Step S101, integrating the pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into the sky-ground integrated monitoring matrix, and generating a geological environment original database after layered outlier processing;

[0022] Step S102: construct a sky-ground integrated space-time standard field based on the original geological environment database, and generate a geological environment correlation spectrum through space-time registration and data fusion;

[0023] Step S103, performing multi-dimensional feature decomposition on the geological environment association spectrum, and generating a geological element feature chain through sky-ground collaborative analysis;

[0024] Step S104: constructing a sky-ground coupled dynamic field based on the geological element feature chain, and obtaining a geological environment evolution parameter set through multi-field coupling analysis;

[0025] Step S105: establishing a sky-ground integrated risk assessment matrix according to the geological environment evolution parameter set, and generating a risk warning indicator system through quantitative hierarchical analysis;

[0026] Step S106: Based on the risk warning indicator system and combined with the historical case library, a sky-ground collaborative plan is designed to generate a geological environment management plan.

[0027] It is understandable that the execution subject of the present application can be the sky-ground integrated geological environment monitoring and assessment system, or a terminal or a server, which is not limited here. The present application embodiment is described by taking the server as the execution subject as an example.

[0028] Specifically, three types of basic data are collected: sky remote sensing parameters include surface deformation, geological structure information, and surface coverage data; surface monitoring parameters include surface crack width, surface displacement, rainfall, and groundwater level; underground detection data include rock stress, stratum displacement, and groundwater pressure. Figure 2 As shown, it is a schematic diagram of rock mass stress in the embodiment of the present application, such as Figure 3 As shown, it is a schematic diagram of stratum displacement in the embodiment of the present application. After being standardized, these data constitute the initial sky-ground integrated monitoring matrix. The data in the monitoring matrix are subjected to layered outlier processing. By calculating the mean and standard deviation of each layer of data, 3 times the standard deviation is set as the outlier judgment threshold, abnormal data points are screened out, and the processed data are stored in the original database of the geological environment. When constructing the sky-ground integrated space-time standard field based on the original database of the geological environment, the timestamp and spatial coordinate information of the data are extracted to establish a unified space-time reference grid. The data in each time window is standardized, and the correlation coefficients between different monitoring points are calculated to form a space-time correlation matrix. The data differences caused by different sampling frequencies are eliminated through space-time registration, and the data vacancy areas are supplemented. The registered data are grouped according to the attributes of the geological elements, the correlation strength between the elements in the group is calculated, and the correlation strength matrix is ​​constructed. The correlation strength matrix is ​​hierarchically clustered and spectrally analyzed to generate a geological environment correlation spectrum.

[0029] In the process of multidimensional feature decomposition of geological environment correlation spectrum, the correlation spectrum data is subspaced according to the time series to form a time-varying feature subspace. The time-varying feature subspace is decomposed by singular value, the main feature vector is extracted, and the feature basis matrix is ​​generated. The feature basis matrix is ​​reorganized according to the spatial position information to construct the spatial feature field. The spatial feature field and the time feature vector are tensor decomposed to extract the spatiotemporal coupling characteristics. The spatiotemporal coupling characteristics are classified and aggregated according to the type of geological elements to establish the element correlation matrix. The geological element feature chain is formed through hierarchical decomposition and feature reconstruction. When constructing the sky-ground coupling dynamic field based on the geological element feature chain, the feature chain is partitioned according to the spatial distribution characteristics, and the feature data of each region is analyzed in time series to form a regional dynamic feature matrix. The regional dynamic feature matrix is ​​spatially interpolated and time series decomposed to extract the periodic change and trend change components. The change feature field is classified according to the type of geological elements, and the coupling coefficient between different elements is calculated to form the sky-ground coupling dynamic field. The components of the coupling dynamic field are decomposed in time and space, the interaction relationship between the fields is extracted, and the coupling intensity matrix is ​​established. The dominant coupling modes are extracted through eigenvalue decomposition, the evolution feature space is constructed, and the geological environment evolution parameter set is generated.

[0030] In the process of establishing the integrated risk assessment matrix of sky and ground based on the geological environment evolution parameter set, the evolution parameter set is divided into multiple assessment units according to the spatial distribution characteristics, and the parameters of each assessment unit are normalized to form a standardized parameter matrix. The weight coefficients between the parameters are calculated to construct the parameter weight vector. The parameter weight vector and the standardized parameter matrix are combined to generate the risk assessment matrix. The risk assessment matrix is ​​decomposed by eigenvalue, the main risk factors are extracted, and the risk measurement space is established. The risk measurement space is divided into multiple levels, the threshold range of each interval is calculated, and a risk warning indicator system is formed. When designing the sky-ground collaborative plan based on the risk warning indicator system, the indicator system is classified according to the risk level, and the indicator characteristics under each level are extracted. The governance plan data in the historical case library are sorted by attributes to construct a plan feature matrix. The risk feature sequence and the plan feature matrix are matched by similarity calculation to generate an initial plan set. The parameters of the initial plan set are optimized to form a sky-ground collaborative governance strategy. The collaborative governance strategy is partitioned according to the spatial distribution, the governance parameters of each partition are adjusted, and a partition governance matrix is ​​established. The geological environment governance plan is generated through multi-level analysis and parameter combination.

[0031] For example, when conducting geological environmental monitoring in a certain area, sky remote sensing InSAR data is collected to obtain surface deformation information, displacement sensors and crack monitors are deployed on the surface, and stress and strain monitoring equipment is installed underground. These data are processed through spatiotemporal registration and outlier processing to form a unified monitoring data set. The data is decomposed into multi-dimensional features, the key geological element features are extracted, and a coupled dynamic field is established. By analyzing the data correlation between different monitoring points and calculating the coupling coefficient between various parameters, potential risk areas are identified. Based on risk warning indicators and historical governance experience, targeted prevention and control plans are formulated, including surface reinforcement, underground support and other measures.

[0032] In the embodiment of the present application, by integrating the pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into the sky-ground integrated monitoring matrix, the collaborative collection of multi-source data is achieved, the comprehensiveness and systematicness of data collection are ensured, and the original geological environment database generated after layered outlier processing has high data quality; based on the original geological environment database, a sky-ground integrated spatiotemporal standard field is constructed, and a geological environment association spectrum is generated through spatiotemporal registration and data fusion, realizing the deep fusion and spatiotemporal alignment of multi-source heterogeneous data; the geological environment association spectrum is multi-dimensionally decomposed, and a geological element feature chain is generated through sky-ground collaborative analysis, the key features of the geological elements are extracted and the correlation relationship between the elements is established; based on the geological element feature chain, a sky-ground coupled dynamic field is constructed, and a geological environment evolution parameter set is obtained through multi-field coupling analysis, realizing the accurate characterization of the dynamic evolution characteristics of the geological environment; according to the geological environment evolution parameter set, a sky-ground integrated risk assessment matrix is ​​established, and the risk warning indicator system generated through quantitative hierarchical analysis has strong scientificity and operability; based on the risk warning indicator system, a sky-ground collaborative plan is designed in combination with a historical case library, and the generated geological environment governance plan has strong pertinence and practicality. This method organically integrates monitoring data from three levels: sky, surface, and underground, establishes a complete data processing, analysis, evaluation, and governance process, and significantly improves the accuracy and reliability of geological environment monitoring and evaluation.

[0033] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0034] (1) The sky remote sensing parameters are divided into three data subsets: surface shape variable, surface cover variable, and geological structure variable. Each data subset is standardized to form a sky layer data matrix;

[0035] (2) Classify the surface monitoring parameters according to point and surface elements, perform spatial interpolation on the point element data, and perform grid resampling on the surface element data to generate a surface layer data matrix;

[0036] (3) The underground detection data are layered according to depth, and the parameters of the data at different depth layers are normalized and spatially registered to construct the underground layer data matrix;

[0037] (4) Time series alignment of the sky layer data matrix, the surface layer data matrix, and the underground layer data matrix is ​​performed, and a sky-ground integrated monitoring matrix is ​​generated through three-dimensional tensor operations;

[0038] (5) Perform hierarchical statistical analysis on each monitoring parameter in the integrated sky-ground monitoring matrix, set an outlier discrimination threshold, and remove abnormal data points;

[0039] (6) After removing abnormal data points, the integrated sky-ground monitoring matrix is ​​processed through data interpolation and smoothing to generate the original geological environment database.

[0040] Specifically, the data is divided into three basic subsets: surface shape variables include quantitative indicators such as surface settlement, uplift, and displacement; surface cover includes surface feature data such as vegetation coverage, exposed surface ratio, and water area; geological structure includes structural element information such as fault strike, dip, and joint density. The three types of data are standardized separately. The standardization process uses the maximum and minimum value standardization method to uniformly transform data of different dimensions into the [0,1] interval. The processed data is organized into a sky layer data matrix. The processing of surface monitoring parameters distinguishes the characteristics of point and surface elements. Point element data mainly includes discrete monitoring data such as GPS monitoring points, tilt measurement points, and ground fissure monitoring points. These point element data are processed using the Kriging spatial interpolation method. By calculating the spatial autocorrelation and variation function, the attribute values ​​of unknown points are estimated to achieve the conversion of point data to continuous surfaces. Surface element data include InSAR deformation data, surface deformation monitoring belts and other continuously distributed data. These data are grid-resampled to unify data of different resolutions to the same spatial resolution to form regular grid data, which are integrated into a surface layer data matrix.

[0041] The underground detection data processing is layered according to the depth, and the underground space is usually divided into shallow layer (0-50m), middle layer (50-200m) and deep layer (>200m). The monitoring data of each layer, including parameters such as borehole stress, rock displacement, and groundwater level, are normalized. The normalization adopts the Z-score standardization method to convert the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. At the same time, spatial registration is performed to unify the monitoring data of different depths and different locations into the same spatial reference system to construct the underground layer data matrix. The time series of the three-level data matrices are aligned. The timestamps of all data are unified to the same time reference, and the data with different sampling frequencies are resampled, the high-frequency data is downsampled or the low-frequency data is interpolated so that all data have the same time interval. Then the three-level data matrices after time alignment are combined through three-dimensional tensor operations to form a sky-ground integrated monitoring matrix. The tensor operation process includes tensor decomposition and reconstruction to retain the spatiotemporal correlation characteristics between data.

[0042] The formed sky-ground integrated monitoring matrix is ​​subjected to hierarchical statistical analysis, and the statistical characteristics of each layer of data, such as the mean, standard deviation, skewness, and kurtosis, are calculated. Based on these statistical characteristics, the threshold for distinguishing outliers is set. The mean ± 3 times the standard deviation is usually used as the standard for distinguishing, and the data points that exceed the threshold range are marked and removed. Finally, the data matrix after removing the outliers is interpolated and smoothed. The data interpolation adopts the spatiotemporal interpolation method, comprehensively considering the temporal continuity and spatial correlation of the data, and reasonably estimating the missing values. The sliding average method is used for data smoothing to eliminate random fluctuations in the data and form the original database of the geological environment.

[0043] For example, in areas with geological disaster risks, surface deformation data is obtained through satellite remote sensing, displacement data is obtained by setting up monitoring points on the ground, and stress data is obtained by deep drilling. The deformation data obtained by remote sensing is first classified, and information such as surface settlement and surface crack distribution is extracted, and a matrix is ​​formed after standardization. The displacement data of the ground monitoring points is used to generate a continuous distribution field through spatial interpolation. The stress data of deep drilling is normalized after being layered by depth. These three types of data are aligned in time series, such as unifying monitoring data of different frequencies to a daily sampling frequency to form a unified monitoring matrix. Outliers are identified through statistical analysis, such as abnormally large displacement values ​​that suddenly appear at a certain monitoring point, and they are eliminated. Finally, the data is smoothed to obtain a monitoring data set.

[0044] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0045] (1) Extracting timestamp information and spatial location information from the original geological environment database, establishing a spatiotemporal reference grid, and mapping discrete data points to a unified spatiotemporal coordinate system;

[0046] (2) The monitoring data in the spatiotemporal reference grid is segmented according to time windows, and the data in each time window is standardized to form a time series data set;

[0047] (3) Based on the time series data set, a spatiotemporal correlation matrix is ​​constructed, the correlation coefficients between different monitoring points are calculated, and a sky-ground integrated spatiotemporal standard field is generated;

[0048] (4) Performing space-time registration of the integrated space-time standard field of the sky and the ground, aligning data items with different sampling frequencies, and supplementing data vacancy areas;

[0049] (5) Grouping the registered data according to the attributes of geological elements, calculating the correlation strength between the elements in the group, and constructing the correlation strength matrix;

[0050] (6) The correlation intensity matrix is ​​divided into multiple characteristic sub-matrices according to the hierarchical relationship. Each characteristic sub-matrix is ​​subjected to spectral decomposition and frequency domain analysis. The decomposition results are hierarchically clustered and then merged. Based on the clustering results, a correlation spectrum is constructed and spectrum characteristics are extracted to form a geological environment correlation spectrum.

[0051] Specifically, the timestamp information (accurate to seconds) and spatial location information (including longitude, latitude and elevation) recorded at each monitoring point are extracted to establish a three-dimensional spatiotemporal reference grid. The spatiotemporal reference grid uses a longitude and latitude projection coordinate system with a horizontal resolution of 0.001 degrees, a vertical resolution of 1 meter, and a time resolution of 1 hour. The discrete monitoring point data are mapped to a unified grid node through spatial interpolation methods (including inverse distance weighting and kriging interpolation). The monitoring data in the spatiotemporal reference grid are segmented according to a fixed time window (such as 24 hours), and the data in each time window are standardized. The standardization process uses the Z-score method to convert monitoring data of different dimensions into a unified standard normal distribution interval. The standardized data forms a time series data set, which contains standardized time series of multiple monitoring indicators such as surface deformation, groundwater level, and rainfall.

[0052] When constructing the spatiotemporal correlation matrix based on the time series data set, the Pearson correlation coefficient between different monitoring points is calculated. For time series data, the dynamic correlation coefficient is calculated using the sliding window method, with a window length of 30 days and a step length of 1 day. The calculated correlation coefficient matrix reflects the degree of association between different monitoring points, thereby generating a space-time standard field for the integration of sky and ground.

[0053] For space-time registration, the following space-time registration model is adopted:

[0054]

[0055] Where: C align (t) represents the space-time data after registration; X i (t) represents the space-based monitoring data sequence; Y j (t) represents the surface monitoring data sequence; Z k (t) represents the underground monitoring data sequence; α i , β j , γ k They represent the weight coefficients of different data sources respectively; n, m, and p represent the number of three types of data sources respectively.

[0056] The registered data are grouped according to the attributes of geological elements (such as topography, geological structure, hydrogeology, etc.), and the correlation strength between the elements in the group is calculated. The correlation strength calculation adopts the gray correlation analysis method, and the correlation relationship between the elements is quantified by calculating the gray correlation between different time series. Each element in the correlation strength matrix represents the degree of correlation between two geological elements, and the value range is between [0,1]. The correlation strength matrix is ​​divided into multiple characteristic sub-matrices according to the hierarchical relationship, and each sub-matrix corresponds to a geological element category. The characteristic sub-matrix is ​​spectrally decomposed, the main eigenvalues ​​and eigenvectors are extracted, and analyzed in the frequency domain. The frequency domain analysis adopts the wavelet transform method, selects Morlet wavelet as the basis function, and performs multi-scale decomposition on the time series. The decomposition results are classified by the hierarchical clustering method, and the Ward minimum variance method is used as the clustering algorithm. The elements are divided into different categories according to the similarity of the spectral features. Finally, the correlation spectrum is constructed according to the clustering results, the spectrum characteristics are extracted, and the geological environment correlation spectrum is formed.

[0057] In the data processing example, monitoring data are extracted from the original database, including satellite InSAR deformation data (sampling interval of 12 days), ground GPS deformation monitoring data (sampling interval of 1 hour) and underground microseismic monitoring data (sampling interval of 10 minutes). These data with different temporal and spatial resolutions are unified into the same coordinate system through the temporal and spatial reference grid. For InSAR data, the 100-meter resolution deformation data are resampled to the standard grid using the spatial interpolation method; for GPS data, the point observation data are extended to the entire monitoring area through Kriging interpolation; for microseismic data, the spatial position is determined according to the earthquake source location results, and the temporal resolution is unified to 1 hour.

[0058] In the process of spatiotemporal registration, the registration model is used to align the data for sampling data of different frequencies. The correlation matrix between monitoring points is obtained by calculating the Pearson correlation coefficient. The calculation of the correlation coefficient is based on the sliding time window to obtain the dynamic correlation change characteristics. In the process of constructing the association spectrum, the monitoring data is first grouped according to the attributes of geological elements, such as classifying deformation data, hydrological data, and structural data separately. The correlation strength between the elements in the group is calculated to form an association strength matrix. The association strength matrix is ​​spectrally decomposed and analyzed in the frequency domain to extract the main characteristic modes, and the features are classified and integrated through the hierarchical clustering method. The obtained association spectrum reflects the correlation relationship and evolution characteristics between different geological elements.

[0059] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0060] (1) The geological environment correlation spectrum is segmented according to the time series, and the correlation spectrum data in each time period is divided into subspaces to form a time-varying characteristic subspace;

[0061] (2) Perform singular value decomposition on the data in the time-varying feature subspace, extract the main eigenvectors, and generate the feature basis matrix;

[0062] (3) Reorganize the feature basis matrix according to the spatial position information, construct the spatial feature field, and extract the spatial feature components;

[0063] (4) Perform tensor decomposition on spatial feature components and temporal feature vectors to extract spatiotemporal coupling features;

[0064] (5) Classify and aggregate the spatiotemporal coupling characteristics according to the geological element types and establish an element association matrix;

[0065] (6) Perform hierarchical decomposition and feature reconstruction on the element association matrix, organize the reconstructed features in a chain according to the sky-ground coordination relationship, perform multi-level feature mapping and correlation analysis, and form a geological element feature chain through feature transfer and feature fusion.

[0066] Specifically, the correlation spectrum data is segmented according to fixed time intervals (such as 30 days), and subspace partitioning is performed for each segment of data. Subspace partitioning uses the principal component analysis method to project high-dimensional data into a low-dimensional feature space to form a time-varying feature subspace. The time-varying feature subspace contains the changing characteristics of different monitoring elements (such as surface deformation, groundwater level, rock mass stress, etc.) in different time periods.

[0067] The singular value decomposition of the data in the time-varying feature subspace is performed, and its mathematical expression is:

[0068]

[0069] Where: D(t) represents the time-varying feature subspace data matrix; U(t) represents the left singular matrix, including the time eigenvector; Λ(t) represents the singular value diagonal matrix; V(t) represents the right singular matrix, including the space eigenvector; μ i represents the weight coefficient of the i-th eigenmode; ω i (t) represents the i-th time characteristic function; represents the i-th spatial characteristic function; r represents the number of selected characteristic modes.

[0070] The characteristic basis matrix obtained after singular value decomposition contains the main spatiotemporal variation characteristics, and the important eigenvectors are selected by the size of the eigenvalues. The characteristic basis matrix is ​​reorganized according to the spatial location information of the monitoring points to construct the spatial characteristic field. The spatial characteristic field reflects the correlation characteristics of different monitoring elements in spatial distribution.

[0071] The tensor decomposition of spatial feature components and temporal feature vectors is expressed as follows:

[0072]

[0073] Where: T(x,y,z,t) represents the four-dimensional space-time tensor; ψ p (x) represents the horizontal spatial basis function; θ q (y,z) represents the spatial basis function in the vertical direction; η k (t) represents the time basis function; ρ pqk Represents the tensor decomposition coefficient; P, Q, and K represent the number of basis functions in three directions respectively.

[0074] The spatiotemporal coupling features extracted by tensor decomposition are classified and aggregated according to the type of geological elements (such as structure, hydrology, lithology, etc.) to establish an element association matrix. Each element in the element association matrix represents the degree of association between different geological elements. The element association matrix is ​​hierarchically decomposed, and the geological elements are organized into three levels: sky, surface, and underground using a multi-level network analysis method. In the process of feature reconstruction, the association weights between elements at different levels are determined in combination with expert experience and knowledge, so as to realize the chain transmission and fusion of features and form a geological element feature chain.

[0075] For example, the monitoring data includes multi-source data such as surface deformation monitored by satellite InSAR, ground tilt monitoring, and underground displacement monitoring. The monitoring data for one year is segmented into 30-day time windows to form data blocks of 12 time periods. Subspace partitioning is performed on each data block to extract the main change characteristics. The time eigenvector and space eigenvector are obtained by singular value decomposition. Analysis shows that the first three eigenmodes occupy the main part of the total variance. The eigenvectors are reorganized to construct the spatial feature field, which reflects the distribution law of deformation in space. Subsequently, the four-dimensional space-time data is tensor decomposed to obtain the basis functions in the horizontal, vertical and time directions. Based on the decomposition results, the monitoring elements are organized into three levels: space-based InSAR monitoring, ground GPS monitoring, and underground displacement monitoring, and a multi-level feature transfer network is constructed. By calculating the inter-layer correlation strength and determining the feature transfer path, a complete geological element feature chain is formed, which fully reflects the deformation characteristics and evolution process of the landslide body from deep to shallow.

[0076] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0077] (1) Divide the geological element feature chain into different regions according to the spatial distribution characteristics, conduct time series analysis on the feature data of each region, and form a regional dynamic feature matrix;

[0078] (2) Perform spatial interpolation and time series decomposition on the regional dynamic feature matrix, extract periodic change and trend change components, and construct a change feature field;

[0079] (3) Classify the variation characteristic field according to the type of geological elements, calculate the coupling coefficients between different elements, and generate the sky-ground coupling dynamic field;

[0080] (4) Perform spatiotemporal decomposition of the components of the sky-ground coupled dynamic field, extract the interaction relationship between the fields, and establish a coupling strength matrix;

[0081] (5) Perform eigenvalue decomposition on the coupling intensity matrix, extract the dominant coupling mode, and construct the evolution feature space;

[0082] (6) Perform multi-level decomposition and reorganization of the evolutionary feature space, extract key evolutionary features and combine them in time and space, and parameterize the feature combination according to the sky-ground coupling relationship through coupling relationship transmission and feature correlation analysis to generate a set of geological environment evolution parameters.

[0083] Specifically, based on the characteristic chain of geological elements, combined with the spatial distribution characteristics of topography, geological structure, etc., the monitoring area is divided into several sub-areas using a spatial clustering algorithm. Spatial clustering uses the density-based DBSCAN algorithm to divide the areas with similar spatial proximity and similar characteristics into one category by calculating the Euclidean distance between monitoring points and setting the density threshold. Time series analysis is performed on the characteristic data of each sub-area, and the time series features are extracted based on the sliding time window method to form a regional dynamic feature matrix. For the regional dynamic feature matrix, the Kriging interpolation method is used to grid the spatial discrete point data to obtain continuous spatial distribution characteristics. Time series decomposition is performed on the gridded data, and the wavelet analysis method is used to decompose the time series data into periodic change components and trend change components. The periodic change component reflects the periodic change laws such as seasonality and diurnality, while the trend change component reflects the long-term evolution trend. Based on the decomposition results, a change feature field is constructed, which contains the change characteristics at different time scales.

[0084] The change characteristic field is classified according to the type of geological elements (such as topographic changes, hydrological changes, structural changes, etc.), and the coupling coefficient between different types of elements is calculated using the canonical correlation analysis method. The coupling coefficient quantifies the interaction intensity between different elements, and by constructing a coupling relationship network, a sky-ground coupling dynamic field is generated. This dynamic field integrates space-based remote sensing, surface monitoring and underground detection data, reflecting the synergistic characteristics of multi-source data.

[0085] The space-time decomposition of the sky-ground coupled dynamic field is expressed as follows:

[0086]

[0087] Where: F(x,y,z,t) represents the four-dimensional coupled dynamic field; χ i (x, y) represents the horizontal plane characteristic function; ζj (z) represents the vertical characteristic function; ν k (t) represents the time characteristic function; ξ ijk represents the coupling strength coefficient; m, n, and l represent the number of characteristic functions in three directions respectively.

[0088] By decomposing and extracting the interaction relationship between fields, the coupling strength between different monitoring levels is quantified, and a coupling strength matrix is ​​established. The coupling strength matrix is ​​subjected to eigenvalue decomposition to extract the dominant coupling mode. The dominant coupling mode reflects the most significant coupling mode, and the evolution feature space is constructed based on these modes. The evolution feature space is decomposed at multiple levels, and the feature space is divided into different scale levels using a multi-scale analysis method. Key evolution features are extracted at each scale level, and the correlation between features is determined through spatiotemporal combination analysis. Information transmission and fusion between features at different levels are achieved through coupling relationship transmission. The feature combination is parameterized based on the sky-ground synergy relationship to generate a set of geological environment evolution parameters.

[0089] For example, in the geological environment monitoring of mining areas, based on InSAR deformation data, surface GPS monitoring data and underground microseismic monitoring data, the monitoring area is divided into three sub-areas: goaf area, surrounding impact area and stable area. Time series analysis is performed on each sub-area to extract the time series of characteristic parameters such as surface settlement, groundwater level and microseismic frequency. The discrete monitoring data is extended to the entire area through Kriging interpolation, and the annual seasonal changes and long-term trend changes are separated using wavelet analysis methods. Typical correlation coefficients are calculated for different types of monitoring data to establish a sky-ground coupled dynamic field. The main coupling modes are extracted through spatiotemporal decomposition, and it is found that there is a significant interaction relationship between surface settlement, groundwater level changes and microseismic activity. Based on these coupling relationships, a multi-level evolution feature space is constructed to form an evolution parameter set containing parameters such as geological environment evolution rate, trend and interaction intensity.

[0090] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0091] (1) Divide the geological environment evolution parameter set into multiple evaluation units according to the spatial distribution characteristics, and normalize the parameters of each evaluation unit to form a standardized parameter matrix;

[0092] (2) Perform correlation analysis on the standardized parameter matrix, calculate the weight coefficients between parameters, and construct the parameter weight vector;

[0093] (3) Combine the parameter weight vector and the standardized parameter matrix to generate a sky-ground integrated risk assessment matrix;

[0094] (4) Perform eigenvalue decomposition on the integrated air-ground risk assessment matrix, extract the main risk factors, and establish a risk measurement space;

[0095] (5) Divide the risk measurement space into multiple risk level intervals, calculate the threshold range of each interval, and form a grading standard system;

[0096] (6) Conduct a multi-level combined analysis of the grading standard system, determine the risk transmission relationship through risk factor correlation analysis, establish warning level classification criteria, divide risk zones into risk zones based on spatial distribution characteristics, determine the risk level and set warning thresholds for each zone, and generate a risk warning indicator system.

[0097] Specifically, the geological environment evolution parameter set includes multiple evolution parameters such as surface deformation rate, groundwater level change, rock mass stress change, etc. According to the spatial distribution characteristics (such as topographic and geomorphic units, geological structural divisions, hydrogeological divisions, etc.), the geographical unit method is used to divide the monitoring area into multiple evaluation units. The parameters in each evaluation unit are normalized. The normalization method uses the maximum and minimum value standardization to unify the parameters of different dimensions into the [0,1] interval to form a standardized parameter matrix. The standardized parameter matrix is ​​subjected to correlation analysis, and the correlation between parameters is calculated using the Pearson correlation coefficient method. Based on the correlation analysis results, the parameter weights are calculated using the analytic hierarchy process (AHP). The AHP method establishes a judgment matrix, determines the importance ratio between parameters through expert scoring, and then calculates the characteristic roots and characteristic vectors to obtain the weight coefficients of each parameter and construct a parameter weight vector.

[0098] The parameter weight vector is combined with the standardized parameter matrix, and the weighted summation method is used to calculate the comprehensive risk value of each assessment unit to generate the integrated sky-ground risk assessment matrix. The risk assessment matrix reflects the degree of geological environmental risk at different locations in the monitoring area. The risk assessment matrix is ​​subjected to eigenvalue decomposition, and the main risk factors are extracted using the principal component analysis method. During the principal component analysis process, the main eigenvectors are selected according to the cumulative contribution rate, and these eigenvectors constitute the basis of the risk measurement space. The risk measurement space is a multidimensional feature space, and its dimension is determined by the number of selected principal components.

[0099] Based on historical monitoring data and expert experience, the risk measurement space is divided into multiple risk level intervals. Cluster analysis methods (such as K-means clustering) are used to group risk values ​​and determine the threshold range of each level interval. The grading standard system contains quantitative boundaries of different risk levels. A multi-level combined analysis is conducted on the grading standard system to construct a risk indicator system, including multiple levels such as surface deformation indicators, groundwater hydrological indicators, and geological structure indicators. The correlation between indicators at different levels is determined through correlation analysis, and a risk transmission network is established. Based on the risk transmission network, the warning level division criteria are set, and the risk level is divided into four levels: red (dangerous), orange (warning), yellow (caution) and green (normal). Combined with the spatial distribution characteristics, the regional zoning method is used to divide the monitoring area into different risk zones, and the corresponding warning threshold is set for each zone.

[0100] For example, in an open-pit mine, the area is divided into assessment units according to the side slopes, accumulation bodies and surrounding impact areas of the mine. The monitoring data of each unit (including surface displacement monitored by InSAR, deformation rate monitored by GPS, groundwater level observations, etc.) are normalized. The weights of each parameter are determined by the hierarchical analysis method, such as the weight of surface displacement is 0.4, the weight of deformation rate is 0.3, and the weight of groundwater level is 0.3. The calculated risk assessment matrix is ​​subjected to principal component analysis, and three main risk factors are extracted: deformation accumulation, water level fluctuation and tectonic activity. Based on these risk factors, a risk measurement space is constructed, and the risk value is divided into different level intervals through cluster analysis. In the risk transfer analysis, it is found that there is a significant correlation between surface deformation and groundwater level changes, and tectonic activities have an impact on both. Based on this, a hierarchical early warning indicator system is established: when the annual cumulative deformation of the surface exceeds the set threshold and the groundwater level fluctuates abnormally, an orange early warning is triggered; when tectonic activities are frequent and accelerated deformation occurs on the surface, it is upgraded to a red early warning. This early warning system realizes accurate identification and timely early warning of different risk levels.

[0101] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0102] (1) Classify the risk warning indicator system according to risk levels, extract features of indicators under each risk level, and form a risk feature sequence;

[0103] (2) Organize the attributes of the governance plan data in the historical case library, extract key governance parameters, and construct a plan feature matrix;

[0104] (3) Calculate the similarity between the risk feature sequence and the solution feature matrix, select historical cases with high matching degree, and generate the initial solution set;

[0105] (4) Optimize the parameters of the initial solution set, combine solutions for different governance objectives, and form a sky-ground collaborative governance strategy;

[0106] (5) Divide the sky-ground collaborative governance strategy into zones according to spatial distribution, adjust the governance parameters of each zone, and establish a zone governance matrix;

[0107] (6) Conduct multi-level analysis and parameter combination on the zoning governance matrix, optimize the multi-dimensional governance parameters of the sky and the ground, combine the risk warning level and governance effect evaluation, dynamically adjust and optimize the governance parameters, build a governance process sequence, and generate a geological environment governance plan.

[0108] Specifically, according to the warning level (red, orange, yellow, green), the indicators under each level (including surface deformation rate, groundwater level change rate, tectonic activity intensity, etc.) are feature extracted. Feature extraction uses statistical analysis methods to calculate the statistical characteristics of each indicator, such as the mean, standard deviation, and coefficient of variation, and combines time series analysis methods to extract trend characteristics and periodic characteristics to form a risk feature sequence. The governance plan data in the historical case library is systematically organized to establish a data structure with multi-dimensional attributes such as governance means, engineering parameters, and implementation conditions. Key governance parameters are extracted, including quantitative indicators such as project scale, construction technology, and material parameters, as well as qualitative indicators such as geological conditions and environmental constraints. Through data standardization and encoding conversion, these parameters are organized into a structured scheme feature matrix.

[0109] The similarity calculation method is used to match and analyze the risk feature sequence and the solution feature matrix. The similarity calculation adopts a method that combines cosine similarity and Euclidean distance, while considering the matching degree of quantitative indicators and qualitative indicators. By setting the similarity threshold, historical cases with high matching degree are screened out to form an initial solution set. The parameters of the initial solution set are optimized, and a multi-objective optimization method is used to take the governance effect, engineering cost, environmental impact, etc. as optimization targets. For different governance targets (such as slope stability, groundwater governance, surface subsidence control, etc.), the solution parameters are combined and optimized. The combined optimization process uses a genetic algorithm to generate new solution combinations through operations such as crossover and mutation, gradually optimize the solution parameters, and form a sky-ground collaborative governance strategy.

[0110] The sky-ground collaborative governance strategy is divided into zones according to spatial distribution characteristics, and the governance area is divided into multiple sub-areas considering factors such as topography, engineering geological conditions, and hydrogeological conditions. Targeted adjustments are made to the governance parameters of each zone, including engineering layout, construction parameters, monitoring points, etc., to establish a zone governance matrix. Multi-level analysis is performed on the zone governance matrix, and the analytic hierarchy process is used to evaluate the importance and priority of different governance measures. The governance parameters are dynamically adjusted in combination with the risk warning level. The parameter optimization process adopts a rolling optimization strategy, and dynamically adjusts the optimization parameter combination based on the real-time evaluation results of the governance effect. Construct a governance process sequence that includes construction steps, parameter configuration, monitoring plan, etc. to form a complete geological environment governance plan.

[0111] For example, in landslide control, risk warning indicators (including surface displacement rate, groundwater level, degree of crack development, etc.) are classified according to the warning level, and the spatiotemporal variation characteristics of each indicator are extracted. The historical case library is queried to extract the key parameters of control solutions such as anti-slide piles, drainage projects, and anchoring projects. Through similarity calculation, historical cases with similar geological conditions and deformation characteristics are found. The initial scheme is optimized and combined, such as combining anti-slide piles with drainage projects, and optimizing the pile position layout and drainage network layout. According to the site conditions, the control area is divided into the main sliding area, the secondary sliding area and the impact area, and control measures are formulated separately. Arrange an array of anti-slide piles in the main sliding area and set up deep well drainage, implement anchor frame beam reinforcement in the secondary sliding area, and set up a monitoring network in the impact area. Through continuous monitoring and evaluation of the control effect, dynamically adjust the construction parameters.

[0112] In a specific embodiment, the process of performing parameter optimization on the initial solution set may specifically include the following steps:

[0113] (1) Group the initial solution set according to the type of governance objectives, and standardize the parameters of each group of solutions to form a standard parameter set;

[0114] (2) Perform correlation analysis on the parameters in the standard parameter set, calculate the correlation strength between the parameters, and construct a parameter correlation network;

[0115] (3) The parameter association network is layered according to the governance objectives, key parameter combinations of each layer are extracted, and a multi-objective parameter space is generated;

[0116] (4) Set constraints on the multi-objective parameter space, determine the feasible domain through parameter boundary analysis, and form the parameter optimization interval;

[0117] (5) Combine and match the parameters within the parameter optimization range, screen them according to the target priority, and establish a scheme combination sequence;

[0118] (6) Conduct a multi-dimensional evaluation of the scheme combination sequence, dynamically adjust the parameter combination through parameter sensitivity analysis and scheme effect evaluation, optimize and integrate the schemes in combination with the sky-ground coordination relationship, and form a sky-ground coordinated governance strategy.

[0119] Specifically, the schemes are grouped according to the type of governance target (such as surface deformation control, groundwater governance, geological structure reinforcement, etc.), and the maximum and minimum values ​​of the engineering parameters in each group of schemes (such as support structure size, grouting pressure, anchor length, etc.) are standardized, and the parameters of different dimensions are unified into the [0,1] interval to form a standard parameter set. Correlation analysis is performed on the parameters in the standard parameter set, and the Pearson correlation coefficient method is used to calculate the correlation strength between the parameters. By setting the correlation coefficient threshold, parameter pairs with significant correlation are screened out to construct a parameter association network. The parameter association network is represented by a graph structure, with nodes representing parameters, edges representing the association relationship between parameters, and edge weights representing the association strength.

[0120] The parameter association network is hierarchically processed according to the governance objectives, and the community discovery algorithm is used to identify the parameter communities in the network. Each community corresponds to a governance objective level. Key parameter combinations are extracted in each level. The selection of key parameters is based on centrality analysis, including degree centrality, betweenness centrality, and eigenvector centrality. By combining these key parameters, a multi-objective parameter space is generated. Constraints are set for the multi-objective parameter space. The constraints include engineering technical constraints (such as construction process restrictions and equipment capacity restrictions), resource constraints (such as material supply and construction period), and environmental constraints (such as terrain conditions and climate conditions). Through parameter boundary analysis, the value range of each parameter is determined to form a parameter optimization interval.

[0121] Parameter combinations are matched within the parameter optimization range, and a multi-objective optimization algorithm (such as NSGA-II algorithm) is used to generate a non-dominated solution set. According to the priority of the governance goal (such as safety first, economy second), the schemes are screened and sorted to establish a scheme combination sequence. The scheme combination sequence is evaluated in multiple dimensions, including technical feasibility evaluation, economic rationality evaluation and environmental impact assessment. The parameter sensitivity analysis method is used to identify the key parameters that have a significant impact on the governance effect. Through orthogonal experimental design, the impact of different parameter combinations on the governance effect is analyzed. Combined with multi-source monitoring data from the sky and the ground, the parameter combination is dynamically optimized and adjusted to form a sky-ground collaborative governance strategy.

[0122] For example, in the treatment of karst collapse, schemes including filling grouting, pile foundation reinforcement, drainage engineering, etc. are grouped according to the treatment objectives. Grouting parameters (such as slurry ratio, grouting pressure, grouting volume), pile foundation parameters (such as pile length, pile diameter, pile spacing) and drainage parameters (such as pipe network layout, water collection well depth) are standardized. Through correlation analysis, it is found that there is a significant correlation between grouting pressure and slurry diffusion radius, pile foundation spacing and foundation bearing capacity. The parameter association network is divided into three levels: surface reinforcement layer, underground filling layer and base reinforcement layer, and key parameter combinations are extracted. Considering constraints such as stratum bearing capacity and construction equipment capacity, the feasible value range of the parameters is determined. A multi-objective optimization method is used to generate a series of parameter combination schemes, and the optimal parameter configuration is determined through sensitivity analysis to form a comprehensive treatment strategy.

[0123] In a specific embodiment, the process of partitioning the sky-ground collaborative governance strategy according to the spatial distribution may specifically include the following steps:

[0124] (1) Gridding the parameter data in the sky-ground collaborative governance strategy according to spatial coordinates to generate a parameter spatial distribution map;

[0125] (2) Perform spatial autocorrelation analysis on the parameter spatial distribution map, calibrate the parameter variation characteristics, and form a spatial variation field;

[0126] (3) The spatial variation field is divided into regions according to parameter similarity, and the parameters in the region are classified and counted to generate a partition parameter sequence;

[0127] (4) Optimize the boundaries of the partition parameter sequence to eliminate parameter mutations between regions and construct a smooth transition zone;

[0128] (5) Analyze the parameters of the smooth transition zone and the internal parameters of the region together, calculate the regional characteristic values, and generate the regional characteristic spectrum;

[0129] (6) Perform spatial superposition and correlation analysis on the regional characteristic spectra, and dynamically correct the partition boundaries and internal parameters through parameter partition optimization and regional parameter adjustment combined with spatial continuity analysis to form a partition governance matrix.

[0130] Specifically, the construction of the zoning governance matrix performs spatial processing on the parameter data in the sky-ground collaborative governance strategy. The monitoring area is divided into grid cells using the regular grid method, and the grid size is determined according to the monitoring accuracy. The governance parameters (including engineering parameters, monitoring parameters, control parameters, etc.) in each grid cell are interpolated, and the Kriging interpolation method is used to expand the discrete parameter data to the entire spatial domain to generate a parameter spatial distribution map. Spatial autocorrelation analysis is performed on the parameter spatial distribution map, and the Moran index method is used to calculate the spatial correlation of the parameters. By constructing a spatial weight matrix, the degree of correlation between the parameters of each grid cell and the adjacent cells is calculated. Based on the variation function theory, the spatial variation law of the parameters is analyzed, including the variation directionality, variation scale and spatial structure characteristics, to form a spatial variation field. The spatial variation field reflects the changing characteristics of the parameters in spatial distribution.

[0131] The spatial variation field is divided into regions according to parameter similarity, and the fuzzy C-means clustering algorithm is used to classify the parameters. By setting the cluster center and fuzziness coefficient, grid cells with similar parameter characteristics are divided into the same region. The parameters in each region are statistically analyzed, and the mean, standard deviation and other statistics are calculated to form a partition parameter sequence. The parameter sequence reflects the parameter characteristics of different regions. The boundary optimization is performed on the partition parameter sequence, and the boundary smoothing algorithm is used to handle the parameter mutation between regions. A transition zone is set between adjacent regions, and the width of the transition zone is determined according to the parameter gradient. The weighted average method is used to interpolate the parameters in the transition zone to achieve a smooth transition of the parameters. The setting of the transition zone avoids the discontinuity of the governance parameters in space.

[0132] The parameters of the smooth transition zone are jointly analyzed with the internal parameters of the region, and the principal component analysis method is used to extract regional characteristics. The main parameter characteristics of the region are determined by calculating the eigenvalues ​​and eigenvectors. A characteristic spectrum is generated for each region, which contains the parameter distribution characteristics and change laws of the region. The regional characteristic spectrum is spatially superimposed and the characteristic spectra of different regions are combined using the spatial superposition operation method. The parameter relationship between regions is identified through association analysis, and the consistency of parameter distribution is evaluated using the spatial continuity analysis method. According to the analysis results, the partition boundaries and internal parameters are dynamically corrected, the parameter configuration is optimized, and the partition governance matrix is ​​formed.

[0133] For example, in the governance of goaf areas in mining areas, the governance strategy including filling parameters, support parameters and monitoring parameters is gridded, and the grid size is set to 10 meters × 10 meters. The parameter spatial distribution map is generated by Kriging interpolation, reflecting the distribution of governance parameters at different locations. Spatial autocorrelation analysis shows that the parameters have obvious directional characteristics, showing different variation patterns along the strike and dip. Based on parameter similarity, the area is divided into three zones: goaf area, transition zone and stable zone. The goaf area is mainly filled, the transition zone adopts composite support, and the stable zone is mainly monitored and warned. A 20-meter-wide transition zone is set at the boundary of the zone, and a weight-decreasing method is used to achieve smooth parameter transition. The characteristic spectrum of each zone is extracted by principal component analysis, reflecting the governance characteristics of different regions. Finally, combined with spatial continuity analysis, the zone parameter configuration is optimized to form a complete zone governance matrix.

[0134] The above describes the sky-ground integrated geological environment monitoring and evaluation method in the embodiment of the present application. The following describes the sky-ground integrated geological environment monitoring and evaluation system in the embodiment of the present application. Figure 4 In the embodiment of the present application, an embodiment of the sky-ground integrated geological environment monitoring and assessment system includes:

[0135] The acquisition module 201 is used to integrate the pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into the sky-ground integrated monitoring matrix, and generate the original geological environment database after layered outlier processing;

[0136] A generation module 202 is used to construct a space-sky integrated space-time standard field based on the original geological environment database, and generate a geological environment correlation spectrum through space-time registration and data fusion;

[0137] Decomposition module 203, used for multi-dimensional feature decomposition of geological environment correlation spectrum, and generating geological element feature chain through sky-ground collaborative analysis;

[0138] The coupling module 204 is used to construct a sky-ground coupling dynamic field based on the geological element feature chain, and obtain a geological environment evolution parameter set through multi-field coupling analysis;

[0139] The classification module 205 is used to establish a sky-ground integrated risk assessment matrix according to the geological environment evolution parameter set, and generate a risk warning indicator system through quantitative classification analysis;

[0140] Design module 206 is used to design a sky-ground coordination plan based on the risk warning indicator system and in combination with the historical case library to generate a geological environment management plan.

[0141] Through the coordinated cooperation of the above-mentioned components, by integrating the pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into the sky-ground integrated monitoring matrix, the coordinated collection of multi-source data is realized, ensuring the comprehensiveness and systematicness of data collection. The original geological environment database generated after layered outlier processing has high data quality; based on the original geological environment database, a sky-ground integrated spatiotemporal standard field is constructed, and a geological environment correlation spectrum is generated through spatiotemporal registration and data fusion, realizing the deep fusion and spatiotemporal alignment of multi-source heterogeneous data; the geological environment correlation spectrum is decomposed into multi-dimensional features, and the sky-ground collaborative The characteristic chain of geological elements was generated by analysis, the key characteristics of geological elements were extracted and the correlation between elements was established; the sky-ground coupled dynamic field was constructed based on the characteristic chain of geological elements, and the geological environment evolution parameter set was obtained through multi-field coupling analysis, realizing the accurate characterization of the dynamic evolution characteristics of the geological environment; the sky-ground integrated risk assessment matrix was established based on the geological environment evolution parameter set, and the risk warning indicator system generated through quantitative hierarchical analysis has strong scientificity and operability; based on the risk warning indicator system, the sky-ground collaborative plan was designed in combination with the historical case library, and the generated geological environment governance plan has strong pertinence and practicality. This method organically integrates the monitoring data of the three levels of sky, surface and underground, establishes a complete data processing, analysis, evaluation and governance process, and significantly improves the accuracy and reliability of geological environment monitoring and evaluation.

[0142] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A sky-ground integrated geological environment monitoring and assessment method, characterized in that: The sky-ground integrated geological environment monitoring and assessment method comprises: Integrate the pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into the sky-ground integrated monitoring matrix, and generate the original geological environment database after layered outlier processing; Based on the original geological environment database, a sky-ground integrated space-time standard field is constructed, and a geological environment correlation spectrum is generated through space-time registration and data fusion; Decompose the geological environment correlation spectrum in multiple dimensions, and generate geological element characteristic chains through sky-ground collaborative analysis; Based on the characteristic chain of geological elements, the sky-ground coupled dynamic field is constructed, and the geological environment evolution parameter set is obtained through multi-field coupling analysis; An integrated sky-ground risk assessment matrix is ​​established based on the geological environment evolution parameter set, and a risk warning indicator system is generated through quantitative hierarchical analysis; Based on the risk warning indicator system and combined with the historical case library, a sky-ground collaborative plan is designed to generate a geological environment governance plan.

2. The sky-ground integrated geological environment monitoring and assessment method according to claim 1 is characterized in that: The previously collected sky remote sensing parameters, surface monitoring parameters and underground detection data are integrated into the sky-ground integrated monitoring matrix, and the original geological environment database is generated after layered outlier processing, including: Dividing the sky remote sensing parameters into three data subsets: surface shape variable, surface cover variable and geological structure variable, and performing standardization processing on each data subset to form a sky layer data matrix; Classifying the surface monitoring parameters according to point and surface elements, performing spatial interpolation on the point element data, and performing grid resampling on the surface element data to generate a surface layer data matrix; The underground detection data is layered according to depth, and parameter normalization and spatial registration are performed on the data of different depth layers to construct an underground layer data matrix; Performing time series alignment on the sky layer data matrix, the surface layer data matrix and the underground layer data matrix, and generating the sky-ground integrated monitoring matrix through three-dimensional tensor calculation; Performing hierarchical statistical analysis on each monitoring parameter in the integrated sky-ground monitoring matrix, setting an abnormal value discrimination threshold, and eliminating abnormal data points; The sky-ground integrated monitoring matrix after removing abnormal data points is subjected to data interpolation and smoothing to generate the original geological environment database.

3. The sky-ground integrated geological environment monitoring and assessment method according to claim 1 is characterized in that: The method of constructing a sky-ground integrated space-time standard field based on the original geological environment database and generating a geological environment correlation spectrum through space-time registration and data fusion includes: Extracting time stamp information and spatial location information from the original geological environment database, establishing a spatiotemporal reference grid, and mapping discrete data points to a unified spatiotemporal coordinate system; The monitoring data in the spatiotemporal reference grid is segmented according to time windows, and the data in each time window is standardized to form a time series data set; Building a spatiotemporal correlation matrix based on the time series data set, calculating the correlation coefficients between different monitoring points, and generating the sky-ground integrated spatiotemporal standard field; Performing space-time registration on the sky-ground integrated space-time standard field, aligning data items with different sampling frequencies, and supplementing data missing areas; The registered data are grouped according to the attributes of geological elements, the correlation strength between the elements in the group is calculated, and the correlation strength matrix is ​​constructed; The association intensity matrix is ​​divided into multiple characteristic sub-matrices according to the hierarchical relationship, and each characteristic sub-matrix is ​​subjected to spectral decomposition and frequency domain analysis. The decomposition results are hierarchically clustered and then merged. According to the clustering results, an association spectrum is constructed and spectrum characteristics are extracted to form the geological environment association spectrum.

4. The sky-ground integrated geological environment monitoring and assessment method according to claim 1 is characterized in that: The multi-dimensional feature decomposition of the geological environment association spectrum is performed to generate a geological element feature chain through sky-ground collaborative analysis, including: The geological environment correlation spectrum is segmented according to the time series, and the correlation spectrum data in each time period is divided into subspaces to form a time-varying characteristic subspace; Performing singular value decomposition on the data in the time-varying feature subspace, extracting main eigenvectors, and generating a feature basis matrix; Reorganize the feature basis matrix according to the spatial position information, construct a spatial feature field, and extract the spatial feature components; Performing tensor decomposition on the spatial feature components and the temporal feature vectors to extract spatiotemporal coupling features; Classify and aggregate the spatiotemporal coupling characteristics according to the types of geological elements to establish an element association matrix; The element association matrix is ​​hierarchically decomposed and feature reconstructed, the reconstructed features are chain-organized according to the sky-ground collaborative relationship, multi-level feature mapping and correlation analysis are performed, and the geological element feature chain is formed through feature transfer and feature fusion.

5. The sky-ground integrated geological environment monitoring and assessment method according to claim 1 is characterized in that: The sky-ground coupled dynamic field is constructed based on the characteristic chain of geological elements, and the geological environment evolution parameter set is obtained through multi-field coupling analysis, including: The geological element characteristic chain is divided into zones according to the spatial distribution characteristics, and the characteristic data of each zone is analyzed in time series to form a regional dynamic characteristic matrix; Performing spatial interpolation and time series decomposition on the regional dynamic feature matrix, extracting periodic change and trend change components, and constructing a change feature field; Classifying the change characteristic field according to the type of geological elements, calculating the coupling coefficients between different elements, and generating the sky-ground coupling dynamic field; Decomposing the components of the sky-ground coupled dynamic field in time and space, extracting the interaction relationship between the fields, and establishing a coupling strength matrix; Performing eigenvalue decomposition on the coupling strength matrix, extracting the dominant coupling mode, and constructing an evolution feature space; The evolution feature space is decomposed and reorganized at multiple levels, key evolution features are extracted and combined in time and space, and the feature combination is parameterized according to the sky-ground coupling relationship through coupling relationship transmission and feature association analysis to generate the geological environment evolution parameter set.

6. The sky-ground integrated geological environment monitoring and assessment method according to claim 1 is characterized in that: The above-mentioned sky-ground integrated risk assessment matrix is ​​established according to the geological environment evolution parameter set, and a risk warning indicator system is generated through quantitative hierarchical analysis, including: Dividing the geological environment evolution parameter set into a plurality of evaluation units according to spatial distribution characteristics, and normalizing the parameters of each evaluation unit to form a standardized parameter matrix; Performing correlation analysis on the standardized parameter matrix, calculating weight coefficients between parameters, and constructing a parameter weight vector; Combining the parameter weight vector with the standardized parameter matrix to generate the sky-ground integrated risk assessment matrix; Performing eigenvalue decomposition on the air-ground integrated risk assessment matrix, extracting main risk factors, and establishing a risk measurement space; Dividing the risk measurement space into multiple risk level intervals, calculating the threshold range of each interval, and forming a grading standard system; A multi-level combined analysis is performed on the grading standard system, the risk transmission relationship is determined through risk factor correlation analysis, warning level classification criteria are established, risk zoning is performed in combination with spatial distribution characteristics, risk level determination and warning threshold setting are performed for each zone, and the risk warning indicator system is generated.

7. The sky-ground integrated geological environment monitoring and assessment method according to claim 1 is characterized in that: The risk warning indicator system is used as a benchmark, and the sky-ground coordination plan is designed in combination with the historical case library to generate a geological environment governance plan, including: Classifying the risk warning indicator system according to risk levels, extracting features of indicators under each risk level, and forming a risk feature sequence; Arrange the attributes of the governance plan data in the historical case library, extract key governance parameters, and construct a plan feature matrix; Calculate the similarity between the risk feature sequence and the solution feature matrix, select historical cases with a high matching degree, and generate an initial solution set; Optimizing parameters of the initial solution set, combining solutions for different governance objectives, and forming a sky-ground collaborative governance strategy; The sky-ground collaborative governance strategy is divided into zones according to spatial distribution, the governance parameters of each zone are adjusted, and a zone governance matrix is ​​established; The zoning governance matrix is ​​subjected to multi-level analysis and parameter combination. Through multi-dimensional governance parameter optimization of the sky and the ground, combined with risk warning levels and governance effect evaluation, the governance parameters are dynamically adjusted and optimally combined to construct a governance process sequence and generate the geological environment governance plan.

8. The sky-ground integrated geological environment monitoring and assessment method according to claim 7 is characterized in that: The parameter optimization of the initial solution set and the combination of solutions for different governance objectives to form a sky-ground collaborative governance strategy include: The initial solution set is grouped according to the type of governance target, and the parameters of each group of solutions are numerically standardized to form a standard parameter set; Performing correlation analysis on the parameters in the standard parameter set, calculating the correlation strength between the parameters, and constructing a parameter correlation network; The parameter association network is layered according to the governance objectives, key parameter combinations of each layer are extracted, and a multi-objective parameter space is generated; Setting constraints on the multi-objective parameter space, determining a feasible region through parameter boundary analysis, and forming a parameter optimization interval; Combine and match the parameters within the parameter optimization interval, screen them according to target priorities, and establish a scheme combination sequence; A multi-dimensional evaluation is performed on the scheme combination sequence, and the parameter combination is dynamically adjusted through parameter sensitivity analysis and scheme effect evaluation. The schemes are optimized and integrated in combination with the sky-ground collaborative relationship to form the sky-ground collaborative governance strategy.

9. The sky-ground integrated geological environment monitoring and assessment method according to claim 7, characterized in that: The sky-ground collaborative governance strategy is partitioned according to spatial distribution, the governance parameters of each partition are adjusted, and a partition governance matrix is ​​established, including: Gridding the parameter data in the sky-ground collaborative governance strategy according to spatial coordinates to generate a parameter space distribution map; Performing spatial autocorrelation analysis on the parameter spatial distribution diagram, calibrating parameter variation characteristics, and forming a spatial variation field; The spatial variation field is divided into regions according to parameter similarity, and the parameters in the regions are classified and counted to generate a partition parameter sequence; Performing boundary optimization processing on the partition parameter sequence, eliminating parameter mutations between regions, and constructing a smooth transition zone; The parameters of the smooth transition zone are jointly analyzed with the internal parameters of the region, the regional characteristic values ​​are calculated, and the regional characteristic spectrum is generated; The regional characteristic spectra are spatially superimposed and correlated, and the partition boundaries and internal parameters are dynamically corrected by parameter partition optimization and regional parameter adjustment combined with spatial continuity analysis to form the partition governance matrix.

10. A sky-ground integrated geological environment monitoring and assessment system, used to implement the sky-ground integrated geological environment monitoring and assessment method as described in any one of claims 1 to 7, characterized in that: The sky-ground integrated geological environment monitoring and assessment system comprises: The acquisition module is used to integrate the pre-collected sky remote sensing parameters, surface monitoring parameters and underground detection data into the sky-ground integrated monitoring matrix, and generate the original geological environment database after layered outlier processing; A generation module is used to construct a sky-ground integrated space-time standard field based on the original geological environment database, and generate a geological environment correlation spectrum through space-time registration and data fusion; The decomposition module is used to perform multi-dimensional feature decomposition of geological environment association spectrum and generate geological element feature chains through sky-ground collaborative analysis; The coupling module is used to construct the sky-ground coupling dynamic field based on the characteristic chain of geological elements, and obtain the geological environment evolution parameter set through multi-field coupling analysis; The classification module is used to establish a sky-ground integrated risk assessment matrix based on the geological environment evolution parameter set and generate a risk warning indicator system through quantitative classification analysis; The design module is used to design sky-ground collaborative plans based on the risk warning indicator system and the historical case library to generate geological environment governance plans.

Images