Underground water infiltration replenishment evaluation method and equipment based on digital twinning

Abstract

The invention discloses an underground water infiltration replenishment evaluation method and equipment based on digital twinning, and relates to the technical field of underground water digital twinning evaluation, and the method comprises the steps: traversing a target area to carry out multi-source sensing collection; performing underground water infiltration simulation to generate an infiltration full-process data set, and obtaining an infiltration coupling model; geologic structure parameters of the target area are extracted, and a three-dimensional geologic structure model is constructed; performing association mapping on the infiltration coupling model and the three-dimensional geological structure model to obtain a dynamic simulation result; deviation analysis is carried out, automatic correction optimization is carried out, and an underground water infiltration supply evaluation report is generated. According to the method, the technical problems of insufficient multi-source data fusion, low space-time simulation precision and weak model dynamic correction capability in underground water infiltration supply evaluation in the prior art are solved, and underground water infiltration supply dynamic simulation and digital twinborn automatic correction of multi-source data coupling are realized; and the technical effect of improving the space-time precision of groundwater infiltration supply evaluation is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of groundwater digital twin assessment, and in particular to a groundwater infiltration and recharge assessment method and equipment based on digital twins. Background Art

[0002] In the field of groundwater infiltration and recharge assessment, existing technologies usually face the problems of low fusion efficiency of multi-source monitoring data (such as water level, soil moisture content, geological parameters, etc.) and insufficient simulation accuracy in time and space scales. Traditional models find it difficult to effectively couple the dynamic interaction between hydrological processes and geological structures, and lack an automatic model correction mechanism based on real-time monitoring data. As a result, the assessment results cannot accurately reflect the infiltration and recharge process under complex geological conditions, and it is difficult to meet the needs of refined water resources management for high-precision and real-time assessment.

[0003] The existing technologies for groundwater infiltration and recharge assessment have technical problems such as insufficient multi-source data fusion, low spatiotemporal simulation accuracy, and weak dynamic correction capability of the model. Summary of the Invention

[0004] The present application provides a groundwater infiltration and recharge assessment method and equipment based on digital twins, which is used to solve the technical problems in the existing technology of groundwater infiltration and recharge assessment, such as insufficient multi-source data fusion, low spatiotemporal simulation accuracy, and weak model dynamic correction capability.

[0005] In view of the above problems, this application provides a groundwater infiltration and recharge assessment method and equipment based on digital twins.

[0006] In a first aspect, the present application provides a groundwater infiltration and recharge assessment method based on digital twins, the method comprising:

[0007] The target area is traversed to perform multi-source sensing acquisition to obtain a multi-source dynamic monitoring data set; groundwater infiltration simulation is performed based on the multi-source dynamic monitoring data set to generate a full-process infiltration data set, and the full-process infiltration data set is data-coupled to obtain an infiltration coupling model; geological structure parameters of the target area are extracted based on the multi-source dynamic monitoring data set to construct a three-dimensional geological structure model; the infiltration coupling model is correlated and mapped with the three-dimensional geological structure model to construct a digital twin of the groundwater system, and simulation and deduction calculations are performed based on the digital twin to obtain dynamic simulation results; deviation analysis is performed based on the dynamic simulation results and real-time monitoring data, and the digital twin is automatically corrected and optimized based on the deviation results to generate a groundwater infiltration recharge assessment report.

[0008] The second aspect of the present application provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing a groundwater infiltration and recharge assessment method based on digital twins when executing the executable instructions stored in the memory.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The system traverses the target area to collect multi-source sensing data and obtain a multi-source dynamic monitoring dataset. It then simulates groundwater infiltration to generate a full-process infiltration dataset, which is then data-coupled to obtain an infiltration coupling model. It then extracts geological structural parameters from the target area and constructs a three-dimensional geological structural model. It then correlates and maps the infiltration coupling model with the three-dimensional geological structural model to construct a digital twin of the groundwater system. Simulation and calculations are then performed based on the digital twin to obtain dynamic simulation results. It then performs deviation analysis, automatically corrects and optimizes the digital twin based on the deviation results, and generates a groundwater infiltration recharge assessment report. This system achieves the technical effect of implementing multi-source data-coupled dynamic simulation of groundwater infiltration recharge and automatic correction of the digital twin, improving the spatiotemporal accuracy of groundwater infiltration recharge assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of a process for groundwater infiltration and recharge assessment based on digital twins provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0014] Description of the reference numerals: input device 201 , processor 202 , memory 203 , output device 204 . DETAILED DESCRIPTION

[0015] This application provides a groundwater infiltration and recharge assessment method and equipment based on digital twins, which is used to solve the technical problems in the existing technology of groundwater infiltration and recharge assessment, such as insufficient multi-source data fusion, low spatiotemporal simulation accuracy, and weak model dynamic correction capability.

[0016] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0017] Example 1, as Figure 1 As shown, the present application provides a groundwater infiltration recharge assessment method based on digital twins, the method comprising:

[0018] Step S100: traverse the target area to perform multi-source sensing acquisition to obtain a multi-source dynamic monitoring data set.

[0019] Specifically, when traversing the target area for multi-source sensing collection, the hydrogeological zoning map of the target area is first retrieved, and remote sensing collection is carried out on the target area through remote sensing satellites or drones to obtain a remote sensing image set containing information such as surface water distribution and vegetation coverage; according to the hydrogeological zoning map, the changing characteristics of the stratum lithology, structural zoning, etc. are analyzed, and the key boundary lines of spatial division such as topography, soil type, etc. are determined, and the target area is divided into multiple monitoring grid units according to the boundary lines; the remote sensing image set is mapped to each monitoring grid unit, and the surface features are matched through image recognition technology to activate multiple sensor node groups deployed in the grid, such as rain sensors, soil moisture sensors, and groundwater monitoring wells. Among them, the rain sensor is used to collect meteorological parameters such as precipitation intensity and temperature, and the soil moisture sensor is used to obtain soil physical parameters such as soil moisture content and porosity. Groundwater monitoring wells are used to collect groundwater dynamic monitoring data such as water level and water quality, and surface hydrological sensors are used to collect surface hydrological parameters such as river flow and water level. A monitoring connectivity graph is constructed with the center of each monitoring grid unit as a node. The connectivity graph is traversed to calculate the minimum path between all nodes. The collection order of the sensor node group is planned based on the path to generate the equipment movement trajectory. The acquisition clocks of various types of sensors are aligned with the geographic coordinates in time and space to build a unified time and space benchmark. The movement trajectory is executed according to the benchmark. When arriving at the grid center, the sensor node group is triggered to synchronously collect surface hydrological parameters, meteorological parameters, soil physical parameters and groundwater dynamic monitoring data to form an initial monitoring data set. The initial data set is then space-time aligned, and the missing data are interpolated using algorithms such as the Kriging interpolation method to ultimately generate a multi-source dynamic monitoring data set containing multi-dimensional parameters.

[0020] Step S200: performing groundwater infiltration simulation based on the multi-source dynamic monitoring data set to generate a full-process infiltration data set, and performing data coupling on the full-process infiltration data set to obtain an infiltration coupling model.

[0021] Specifically, when simulating groundwater infiltration based on a multi-source dynamic monitoring data set, the soil inversion algorithm is first used to combine soil physical parameters with surface hydrological parameters to invert the soil moisture time series data of the target area; meteorological parameters such as precipitation intensity and temperature are introduced, and the soil moisture time series data are analyzed based on the Richards equation to construct soil moisture movement parameters such as soil moisture diffusivity and permeability coefficient; based on the soil moisture movement parameters, the soil hydraulic parameter field that characterizes the spatial distribution of soil hydraulic characteristics is obtained through spatial interpolation calculation; the surface infiltration boundary conditions are set based on the soil hydraulic parameter field, and the groundwater infiltration from the surface to the ground is simulated with the help of the HYDRUS numerical model. The entire process of the water layer is simulated to generate an infiltration full-process dataset containing information such as changes in soil moisture content and water migration paths in different periods. Based on the infiltration full-process dataset, the soil infiltration process is further analyzed to obtain the spatiotemporal distribution parameters of soil moisture content, and the groundwater infiltration process is analyzed to obtain the infiltration flux parameters. The groundwater recharge rate is calculated by combining the spatiotemporal distribution parameters of soil moisture content with the infiltration flux parameters, and the infiltration flux parameters are matched with the groundwater recharge rate in spatiotemporal order to construct a two-way feedback coupling mechanism in which surface water infiltration affects soil water distribution and soil water infiltration recharges groundwater. By iteratively correcting the coupling mechanism, an infiltration coupling model that couples the physical processes of surface water, soil water, and groundwater is finally obtained.

[0022] Step S300: extracting geological structural parameters of the target area based on the multi-source dynamic monitoring data set and constructing a three-dimensional geological structural model.

[0023] Specifically, when extracting the geological structure parameters of the target area based on the multi-source dynamic monitoring data set and constructing a three-dimensional geological structure model, the physical exploration data (such as seismic wave velocity and resistivity sounding data) in the multi-source dynamic monitoring data are first geologically analyzed to obtain basic information such as rock interface and fault distribution; by constructing a multi-level constrained geological inversion framework, the drill core data, logging curves, etc. are used as hard constraints, combined with regional geological data to form soft constraints, and the geological analysis data are inverted and constrained; according to the inversion framework, multi-source data are fused to construct a three-dimensional cube containing geological structure parameters such as lithologic parameters, porosity, and permeability; with the geological structure parameter cube as input, the GOCAD geological modeling software is used to divide the geological strata by the sequence stratigraphic method, and the structural geological characteristics are combined to construct a three-dimensional geological structure model reflecting the real geological structure of the target area, so as to achieve accurate characterization of characteristics such as the spatial distribution of strata and lithologic changes.

[0024] Step S400: Correlation mapping is performed between the infiltration coupling model and the three-dimensional geological structure model to construct a digital twin of the groundwater system, and simulation and deduction calculation are performed based on the digital twin to obtain dynamic simulation results.

[0025] Specifically, when the infiltration coupling model is associated with the three-dimensional geological structure model, the infiltration coupling model is first regularized to construct a finite difference network based on grid units. At the same time, the three-dimensional geological structure model is unstructured to construct a tetrahedron network that adapts to complex geological interfaces. The finite difference network is traversed and identified in combination with the tetrahedron network to form multiple identification sets containing node coordinates and attribute parameters. By calculating the Euclidean distance from the vertex of the tetrahedron network to the finite difference network, a distance weight matrix reflecting the degree of spatial position correlation is constructed. Based on the distance weight matrix and the identification set, the finite difference network and the tetrahedron network are mapped and calculated to establish a hybrid spatial index mapping relationship to realize the spatiotemporal association binding of hydrological processes and geological structures, thereby constructing a digital twin of the groundwater system. Based on this digital twin, the infiltration coupling model is driven to perform water cycle simulation and deduction to obtain the vertical water flux. The total regional recharge amount is obtained by spatial integration of the vertical water flux, and the cumulative recharge amount per period is obtained by time integration. At the same time, the three-dimensional geological structure model is driven to synchronize the total regional recharge amount and the cumulative recharge amount per period into the geological model for auxiliary simulation. Finally, the groundwater infiltration recharge amount covering different time and space scales is obtained and added to the dynamic simulation results to realize the multi-dimensional quantitative characterization of the groundwater infiltration recharge process.

[0026] Step S500: performing deviation analysis based on the dynamic simulation results and the real-time monitoring data, automatically correcting and optimizing the digital twin based on the deviation results, and generating a groundwater infiltration and recharge assessment report.

[0027] Specifically, when performing deviation analysis based on the dynamic simulation results and real-time monitoring data, the real-time monitoring data of the target area, such as surface hydrology and soil physics, are captured in real time through the edge computing node, and the deviation analysis of the spatiotemporal dimension is performed on the dynamic simulation results output by the digital twin. A spatiotemporal deviation tensor containing the deviation values ​​of longitude, latitude, and time dimensions is generated. The spatiotemporal deviation tensor is arranged in descending order according to the absolute value of the deviation, a simulation deviation sequence is constructed, and the deviation index is set according to the geological and hydrological professional standards. When the deviation index exceeds the preset threshold (such as the recharge error exceeds 15%), the hierarchical correction strategy is triggered, and the limited high-deviation area is first corrected. The weights of the differential network nodes are adjusted, and then the geological parameters of the tetrahedron network are iteratively inverted. After executing the correction strategy, a digital twin optimization body is generated, which drives it to re-simulate the coupling of water cycle and geological structure, forming a closed-loop feedback of data acquisition-simulation-correction. Finally, based on the optimized digital twin body, the spatial distribution characteristics of groundwater infiltration recharge (such as the geographical distribution of high-recharge areas and low-recharge areas) and temporal change trends (such as the recharge fluctuation curves in the rainy season and the dry season) are extracted. Combined with hydrogeological analysis, a groundwater infiltration recharge assessment report containing visual charts and data reports is generated to provide a decision-making basis for water resources management.

[0028] In one possible implementation, step S100 further includes:

[0029] Step S110: Retrieve the hydrogeological zoning map of the target area, perform remote sensing acquisition on the target area, and obtain a remote sensing image set.

[0030] Step S120: performing change analysis based on the hydrogeological zoning map to determine key boundary lines for spatial division.

[0031] Step S130: Divide the target area into a plurality of monitoring grid units according to the key spatial division boundary lines.

[0032] Step S140: mapping the remote sensing image set to the plurality of monitoring grid units for traversal matching, and activating a plurality of sensor node groups according to the matching results.

[0033] Step S150: performing multi-source sensing acquisition according to a unified spatiotemporal reference through the plurality of sensor node groups to generate an initial monitoring data set.

[0034] Step S160: performing spatiotemporal alignment on the initial monitoring dataset, performing missing data interpolation processing based on the aligned dataset, and generating the multi-source dynamic monitoring dataset.

[0035] Specifically, the hydrogeological zoning map of the target area is retrieved from the geographic information database. The map details the distribution of stratigraphic lithology, geological structural characteristics, and hydrogeological unit division in the area. At the same time, remote sensing operations are carried out in the target area using remote sensing satellites or drones equipped with multispectral imaging equipment to collect remote sensing image data covering visible light, near-infrared and other bands. After pre-processing such as radiation correction and geometric correction, a remote sensing image set containing spatial features such as surface vegetation coverage, water body distribution, and topography is formed, providing basic geographic information support for subsequent regional division and monitoring node deployment.

[0036] Based on the retrieved hydrogeological zoning map, terrain slope data, soil type distribution data, and surface cover type data were superimposed to conduct a change analysis. Areas with terrain slopes greater than 5° were identified as topographic and geomorphological abrupt boundaries. Soil type boundaries were delineated based on the boundaries where soil permeability differences between clay and sand were significant. Furthermore, vegetation cover abrupt zones with a Normalized Difference Vegetation Index (NDVI) difference exceeding 0.2 were identified. By combining these slope change thresholds, soil permeability differences, and vegetation cover abrupt characteristics, key spatial demarcation boundaries that reflect the spatial differentiation patterns of hydrogeological parameters were determined.

[0037] Based on the identified key spatial demarcation boundaries, the target area was divided into multiple monitoring grid cells with hydrogeological homogeneity using the spatial analysis capabilities of a geographic information system (GIS). During the demarcation process, constraints were set such as terrain slope mutation lines greater than 5°, soil permeability difference boundaries (such as the interface between clay and sand), and vegetation cover mutation zones (NDVI difference > 0.2). This ensured that the topography, soil type, and surface cover characteristics within each grid cell were relatively consistent, while also balancing the regularity of the grid shape and monitoring efficiency. Ultimately, a monitoring grid cell system covering the entire target area was formed.

[0038] With the help of the spatial overlay analysis function of the geographic information system (GIS), the pre-processed remote sensing image set is spatially mapped to multiple divided monitoring grid units, and the surface features (such as topography, vegetation cover type, water body distribution, etc.) in each grid unit are traversed and matched through image recognition algorithms. The normalized difference vegetation index (NDVI) in the remote sensing image is used to identify vegetation coverage areas, the spectral characteristics are used to distinguish the boundaries between water bodies and land, and different landform units are divided based on terrain slope data. Based on the matched surface feature information, the sensor node group in the corresponding grid unit is automatically activated. For example, the soil moisture sensor group is activated in the vegetation area with an NDVI value higher than 0.5, the water level monitoring sensor group is activated near the water body boundary, and the slope runoff monitoring sensor group is activated in the area with a terrain slope greater than 5°, realizing on-demand activation and precise deployment of the sensor node group.

[0039] A monitoring connectivity graph for the target area is constructed using the center of each monitoring grid cell as a node. Graph theory algorithms are used to calculate the minimum values ​​of all nodes, resulting in a minimum path set consisting of multiple optimal collection paths. This path set is then used to analyze the collection sequence of each sensor node group and generate the device's movement trajectory within the target area. The clock systems of multiple sensor node groups are synchronized and calibrated with the Global Positioning System (GPS), and a unified spatiotemporal reference is constructed based on geographic coordinates to ensure the temporal accuracy and spatial positioning accuracy of data collection. Multiple sensor node groups execute the device's movement trajectory according to the unified spatiotemporal reference. Upon reaching the center of each monitoring grid cell, the sensor node group is triggered to synchronously collect surface hydrological parameters (such as river flow and water level), meteorological parameters (such as precipitation intensity and temperature), soil physical parameters (such as water content and porosity), and groundwater dynamic monitoring data (such as water level and water quality). The collected multi-source data are preliminarily organized according to time series and spatial location to generate an initial monitoring dataset containing the original monitoring data.

[0040] When performing spatiotemporal alignment on the initial monitoring dataset, the surface hydrological, meteorological, soil physical and groundwater dynamic data collected by different sensor node groups are first spatially calibrated and time series synchronized based on the global positioning system coordinates and a unified timestamp to eliminate the spatiotemporal misalignment caused by equipment clock bias and positioning errors. For missing values ​​in the aligned data, the Kriging interpolation method is used in combination with the spatiotemporal correlation of the data to interpolate. The spatial weight matrix of the valid data around the missing points is first calculated, and then the missing values ​​in the time dimension are filled through time series trend prediction. Abnormal data points are smoothed using the Kalman filter algorithm. Finally, the interpolated and corrected multi-dimensional monitoring data are reorganized according to a unified spatiotemporal grid to generate a multi-source dynamic monitoring dataset covering the complete spatiotemporal sequence, providing high-precision data support for subsequent groundwater infiltration simulation and digital twin modeling.

[0041] In one possible implementation, step S150 further includes:

[0042] Step S151: constructing a monitoring connectivity graph of the target area with the center positions of the plurality of monitoring grid units as nodes.

[0043] Step S152: traverse the monitoring connectivity graph and perform minimum value calculations on all nodes to obtain multiple minimum value paths.

[0044] Step S153: performing collection sequence analysis on the multiple sensor node groups based on the multiple minimum value paths to generate a device movement trajectory.

[0045] Step S154: aligning the multiple sensor node groups in time and space to build a unified time and space benchmark.

[0046] Step S155: executing the device movement trajectory for the multiple sensor node groups according to the unified spatiotemporal basis, and triggering the multiple sensor node groups to perform fixed-point sensing collection when arriving at the center position of each monitoring grid unit to obtain the initial monitoring data set.

[0047] Specifically, the center locations of the multiple monitoring grid cells are used as nodes. The geographic coordinates of each node are extracted through a geographic information system. The Euclidean distance between nodes, or the actual travel distance that takes into account the influence of topography, is calculated to construct a monitoring connectivity graph for the target area. This connectivity graph represents the spatial relationship between the monitoring grid cells in the form of a graph theory model. The nodes in the graph correspond to the grid center locations, and the edge weights reflect the distance between nodes or the difficulty of travel. This provides a topological structure foundation for the subsequent collection path planning of the sensor node group, ensuring efficient path optimization calculations based on the graph model.

[0048] The constructed monitoring connectivity graph is traversed using a path optimization algorithm from graph theory. The minimum path of all nodes is calculated by solving the shortest Hamiltonian path problem. Based on the node weights of the monitoring connectivity graph (i.e., the spatial distance between the center positions of each monitoring grid unit or the terrain resistance parameter), the Dijkstra algorithm is used to find the shortest closed path that passes through each node only once. In the process, multiple minimum paths that meet different constraints (such as giving priority to flat terrain areas and equipment energy consumption thresholds) are generated to ensure that the sensing equipment can cover all monitoring grid units with the minimum movement cost, providing the optimal path set for subsequent acquisition sequence planning and trajectory generation.

[0049] Based on multiple acquired minimum paths and combined with real-time obstacle monitoring data (such as the distribution of surface obstacles acquired through remote sensing imagery or IoT sensors), the acquisition sequence of multiple sensor node groups is dynamically analyzed. The acquisition time efficiency and energy consumption cost under different paths are calculated based on the node traversal order and path length of each minimum path. Secondly, real-time obstacle information is introduced, and a path planning algorithm (such as the A* algorithm) is used to optimize the initial minimum path for obstacle avoidance. When a real-time obstacle (such as a sudden flood or a construction area) is detected in a certain section of the path, the system automatically switches to an alternative minimum path or generates a local detour. Finally, considering the mobility characteristics of the device types (such as drones and ground monitoring vehicles) of the sensor node group and the data acquisition timing requirements, the optimized path sequence is integrated into a device movement trajectory that includes real-time obstacle avoidance logic. This trajectory not only meets the shortest path principle but also dynamically avoids obstacles that appear during the monitoring process, ensuring the continuity and security of multi-source sensor data acquisition.

[0050] The acquisition clocks of multiple sensor node groups are synchronized with the standard time source of global navigation satellite systems (such as GPS and BeiDou) to ensure that the timestamp error of each device does not exceed 10 milliseconds. At the same time, the positioning module of each sensor node group is calibrated based on the WGS84 coordinate system or the target area's dedicated geographic coordinate system, and the spatial coordinate accuracy is improved to sub-meter level through differential positioning technology. On this basis, a unified spatiotemporal reference framework containing time and spatial dimensions (longitude / latitude / elevation) is established to provide a standardized spatiotemporal reference system for subsequent multi-source data such as surface hydrology and soil physics, eliminating the spatiotemporal misalignment of data caused by clock bias and positioning errors, and laying the foundation for the fusion analysis and digital twin modeling of multi-source data.

[0051] Under a unified spatiotemporal reference, devices equipped with multiple sensor node groups (such as unmanned vehicles and drones) strictly follow the generated mobile trajectory and calibrate the deviation between the current position and the trajectory node through a real-time positioning system. When the device arrives at the center of each monitoring grid unit, the sensor node group is triggered according to the unified time reference to synchronously collect surface hydrological parameters (such as river flow, water level), meteorological parameters (such as precipitation intensity, temperature, wind speed), soil physical parameters (such as water content, porosity, permeability) and groundwater dynamic monitoring data (such as water level, water quality, and water temperature). During the collection process, all sensor data are marked with timestamps accurate to seconds and sub-meter spatial coordinates, and are initially packaged and stored by the edge computing unit to form an initial monitoring data set containing multi-dimensional raw monitoring data, providing basic input for subsequent spatiotemporal alignment and data interpolation.

[0052] In one possible implementation, step S200 further includes:

[0053] Step S210: performing soil inversion on the target area based on the multi-source dynamic monitoring data set to obtain soil moisture time series data.

[0054] Step S220: introducing precipitation intensity data, performing water movement analysis on the soil moisture time series data according to the precipitation intensity data, and constructing soil moisture movement parameters.

[0055] Step S230: performing spatial distribution calculation based on the soil water movement parameters to obtain a soil hydraulic parameter field.

[0056] Step S240: setting surface infiltration boundary conditions according to the soil hydraulic parameter field, performing full-process simulation of groundwater infiltration based on the surface infiltration boundary conditions, and generating a full-process infiltration data set.

[0057] Specifically, based on soil bulk density, porosity, surface temperature, precipitation and other parameters in the multi-source dynamic monitoring data set, a random forest regression model is used to perform soil inversion in the target area. First, the multi-source data is standardized and preprocessed to eliminate the dimensionality effect. Then, the random forest model is constructed using the training set data. By integrating the prediction results of multiple decision trees, the variance is reduced and the inversion accuracy is improved. During the model training process, parameters such as the node splitting criterion and the number of trees are optimized to minimize the mean square error between the predicted and measured soil moisture values. After evaluating the model using the validation set, the optimized random forest model is applied to the entire target area. Combined with the spatiotemporal interpolation algorithm, soil moisture time series data with a time resolution of 1 hour and a spatial resolution of 10 meters are obtained. This data can accurately reflect the dynamic change characteristics of soil moisture in different periods and provide reliable data support for subsequent soil moisture movement analysis.

[0058] The precipitation intensity data of the target area (including information such as precipitation rate and precipitation duration in different periods) are introduced and temporally and spatially matched with the soil moisture time series data. Based on the Richards equation, the water movement analysis of the changes in soil moisture content with the precipitation process is carried out. By calculating parameters such as the infiltration rate of water in the soil and the matrix potential gradient, soil water movement parameters such as soil water diffusivity and permeability coefficient that change with soil water content are constructed, thereby quantitatively characterizing the migration law and physical properties of soil water during precipitation infiltration.

[0059] The spatial distribution of soil water movement parameters (such as permeability and soil water diffusivity) was calculated using the Kriging interpolation method. Semivariogram analysis was first performed on discrete parameter points, and nugget values, ranges, and sill values ​​were fitted to characterize spatial variation. This was then used as a basis for unbiased optimal estimation of unsampled points in the target area, generating a continuous two-dimensional soil hydraulic parameter field. This was then validated using the inverse distance weighted interpolation method. By setting a distance decay exponent and a search neighborhood range, the parameters of soil layers at different depths were interpolated layer by layer. Ultimately, a three-dimensional soil hydraulic parameter field with both horizontal and vertical variation was constructed, visually demonstrating the spatially heterogeneous distribution of soil permeability and water retention capacity.

[0060] Based on the generated soil hydraulic parameter field, surface infiltration boundary conditions, including initial soil moisture content, surface water depth, and infiltration rate, are set. These parameters are then imported as boundary inputs into the HYDRUS hydrological model to dynamically simulate the entire process of groundwater infiltration from the surface into the aquifer. The simulation fully considers the coupling of multiple physical processes, including precipitation infiltration, surface runoff, soil moisture redistribution, and groundwater recharge. Physical quantities such as soil moisture distribution, water migration pathways, and infiltration flux at different times are calculated in real time. Ultimately, a full-process infiltration dataset, encompassing both time series and spatial distribution, is generated, providing complete physical process data support for the subsequent construction of the infiltration coupling model.

[0061] In one possible implementation, step S200 further includes:

[0062] Step S250: performing soil infiltration analysis based on the full-process infiltration data set to obtain spatiotemporal distribution parameters of soil moisture content.

[0063] Step S260: performing groundwater infiltration analysis based on the full-process infiltration data set to obtain infiltration flux parameters.

[0064] Step S270: performing infiltration recharge calculation according to the spatiotemporal distribution parameter of the soil moisture content and the infiltration flux parameter to generate a groundwater recharge rate.

[0065] Step S280: performing spatiotemporal matching of the infiltration flux parameter and the groundwater recharge rate to construct a bidirectional feedback coupling mechanism.

[0066] Step S290: performing iterative correction according to the bidirectional feedback coupling mechanism to construct the infiltration coupling model.

[0067] Specifically, a multi-dimensional analysis of the soil moisture data in the full-process infiltration dataset was performed. By extracting the moisture content monitoring values ​​of soil layers at different time nodes and different depths, a dynamic distribution model was constructed using a spatiotemporal interpolation algorithm to transform the discrete moisture content data into a continuous spatiotemporal distribution field. The spatiotemporal distribution parameters of soil moisture were obtained, which can characterize the changing trend of soil moisture content in the time series (such as moisture fluctuations before and after precipitation) and the vertical stratification and horizontal differentiation characteristics at the spatial level. This provides a quantitative basis for in-depth analysis of the water migration law during soil infiltration.

[0068] Relevant data of the groundwater infiltration stage were extracted from the full-process infiltration data set. The water migration process in soil pores was quantitatively analyzed using hydromechanical theories such as Darcy's law. By calculating the water content of soil passing through unit cross-sectional area per unit time, the infiltration flux parameter that can characterize the groundwater infiltration intensity was obtained. This parameter comprehensively reflects the influence of factors such as soil permeability and hydraulic gradient on the infiltration process, providing key data support for evaluating groundwater recharge capacity.

[0069] Infiltration recharge is calculated using a mass conservation algorithm based on the finite-difference method. The target area is divided into regular grid cells along the spatial dimension. A calculation step size is set along the temporal dimension, and a water balance equation is established for each grid cell: groundwater recharge rate = (soil moisture content at the end of the time period - soil moisture content at the beginning of the time period) × grid volume / time step size + infiltration flux × grid cross-sectional area. The spatiotemporal distribution parameters of soil moisture content are used to calculate the moisture variation within the grid cell, while the infiltration flux parameter serves as the vertical moisture input. The recharge rate for each grid cell at different time steps is iteratively calculated, ultimately generating a groundwater recharge rate distribution field for the entire target area. This algorithm balances computational accuracy and efficiency, accurately reflecting groundwater recharge dynamics under spatiotemporal heterogeneity.

[0070] The infiltration flux parameters and groundwater recharge rate were matched by using spatiotemporal grid indexing technology. The target area was divided into three-dimensional grids with uniform spatiotemporal resolution. The time step was set to 1 hour and the spatial grid accuracy was set to 10 m × 10 m × 5 m. By establishing a spatiotemporal correlation matrix, the infiltration flux parameters of each grid cell were calculated. The unit is m 3 / (m 2h) and the groundwater recharge rate (unit: m / h) during the corresponding time period, and a correlation mapping is performed. Based on this, a feedback control algorithm is introduced. When the infiltration flux of a grid cell increases by 10%, Darcy's law is used to inversely calculate the impact of this change on the groundwater level. This in turn adjusts the infiltration boundary conditions for subsequent time periods, forming a bidirectional feedback loop between infiltration flux, recharge rate, soil moisture content, and infiltration flux. Ultimately, a bidirectional feedback coupling mechanism with dynamic equilibrium characteristics is constructed, achieving the coordinated evolution and mutual constraint of the two across spatiotemporal scales.

[0071] Using an iterative optimization framework based on a genetic algorithm, a bidirectional feedback coupling mechanism is embedded in the model parameter correction process. First, a 12-dimensional parameter vector, including soil permeability coefficient and water retention curve parameters, is defined. The feedback mechanism is used to calculate the deviation between infiltration flux and recharge rate under the current parameters. Using the Nash efficiency coefficient and root mean square error as the objective function, a new generation of parameter populations is generated through selection, crossover, and mutation operations. In each iteration, the feedback mechanism adjusts the infiltration boundary conditions based on the latest parameters, resimulating and evaluating the deviation. The iteration is terminated when the parameter optimization margin for five consecutive generations is less than 1% or the NSE is greater than 0.95. Ultimately, through this adaptive iterative correction, an infiltration coupling model is constructed that accurately reflects the soil-groundwater interaction process and enables dynamic simulation of groundwater infiltration and recharge under different precipitation conditions.

[0072] In one possible implementation, step S300 further includes:

[0073] Step S310: Perform geological analysis based on the multi-source dynamic monitoring dataset to obtain a physical exploration dataset.

[0074] Step S320: performing inversion constraints based on the physical exploration data set to construct a multi-level constrained geological inversion framework.

[0075] Step S330: performing data fusion according to the multi-level constrained geological inversion framework to construct a geological structure parameter cube, wherein the geological structure parameter cube includes geological structure parameters.

[0076] Step S340: using the geological structure parameters as input to perform geological modeling and construct the three-dimensional geological structure model.

[0077] Specifically, the geological sensor data such as seismic waves, resistivity, and geomagnetism in the multi-source dynamic monitoring data set are preprocessed, and the environmental noise is removed through band-pass filtering. The feature extraction algorithm is used to identify effective geological signals, and the data is calibrated with the drilling core data. After removing outliers, a standardized physical exploration data set is generated. This data set contains parameters such as seismic wave velocity, resistivity distribution, and geomagnetic intensity at different depths, which can accurately reflect the geological interface and lithology distribution characteristics of the target area.

[0078] Based on physical exploration datasets, a multi-level geological inversion framework was constructed using a hierarchical constraint strategy. First, the dielectric constant distribution of shallow strata (0-50 m) was inverted using ground-penetrating radar (GPR) profile data. A high-resolution dielectric model of the shallow strata was established by analyzing the relationship between radar wave reflection characteristics and dielectric constant. Second, the shear wave velocity (Vs) field of the mid-to-deep depth (50-300 m) was inverted based on microseismic monitoring data. The shear wave velocity structure of the subsurface medium was inverted using surface wave dispersion characteristics, obtaining velocity stratification information for the mid-to-deep strata. Finally, the resistivity characteristics of deep lithologies (>300 m) were calibrated using borehole resistivity logging data. A correspondence between deep lithology and resistivity was established by combining prior geological knowledge. By coupling the shallow dielectric constant, the mid-to-deep shear wave velocity field, and the deep lithologic resistivity characteristics with multi-level constraints, a multi-level constrained geological inversion framework from shallow to deep was constructed, providing multi-scale constraints for the subsequent inversion of geological structural parameters.

[0079] According to the multi-level constrained geological inversion framework, a weighted fusion algorithm is used to fuse physical exploration data of different depths and types (such as the dielectric constant of shallow formations, the shear wave velocity field of medium and deep layers, and the resistivity of deep lithology). By setting depth weights and data credibility weights, the multi-source data are mapped to a unified three-dimensional spatial grid, forming a geological structure parameter cube with a resolution of 1m×1m×1m. This cube contains geological structure parameters such as lithology type, porosity, permeability, and shear wave velocity, realizing the three-dimensional spatial discretization and quantitative expression of geological parameters, providing accurate parameter support for subsequent three-dimensional geological modeling.

[0080] Taking the lithology, porosity, permeability and other parameters in the geological structure parameter cube as input, GOCAD geological modeling software is used to perform three-dimensional spatial interpolation of the parameters through the Kriging interpolation algorithm to generate a continuous geological attribute body. Combined with the interpretation results of the seismic reflection phase axis of the geological interface, the triangulated mesh subdivision technology is used to construct the stratum interface, and finally a three-dimensional geological structure model including faults, strata, lithology distribution and physical property parameters is formed. This model can intuitively display the geological spatial distribution characteristics and physical property distribution laws of the target area.

[0081] In one possible implementation, step S400 further includes:

[0082] Step S410: performing regularization processing based on the infiltration coupling model to construct a finite difference network.

[0083] Step S420: performing unstructured processing based on the three-dimensional geological structure model to construct a tetrahedron network.

[0084] Step S430: traverse the finite difference network and combine it with the tetrahedron network to perform identification, and obtain multiple identification sets.

[0085] Step S440: Calculate the distance weights from the vertices of the tetrahedron network to the finite difference network, and construct a distance weight matrix.

[0086] Step S450: performing mapping calculation on the finite difference network and the tetrahedron network according to the distance weight matrix in combination with the multiple identification sets to construct a hybrid space index mapping relationship.

[0087] Step S460: Based on the hybrid spatial index mapping relationship, the infiltration coupling model and the three-dimensional geological structure model are temporally and spatially associated to construct the digital twin of the groundwater system.

[0088] Specifically, the calculation area of ​​the infiltration coupling model is discretized in a regular manner, and the three-dimensional space is divided into uniform cubic grid units according to a uniform spatial step size (such as 10 meters × 10 meters × 5 meters). Each grid has the same geometric size and topological structure in the X, Y, and Z axis directions, thereby constructing a regular finite difference network, providing a standardized spatial framework for the subsequent numerical calculation of the groundwater infiltration process, ensuring the consistency and repeatability of the calculation.

[0089] To address the complex geological interfaces and heterogeneous properties in 3D geological structural models, an unstructured mesh generation algorithm is used to discretize the geological volume into a series of tetrahedral units of varying shapes and sizes. During this process, the side lengths of the tetrahedrons are automatically adjusted based on the curvature of the geological interfaces and the lithologic gradient. Smaller tetrahedrons are used in areas with complex geological structures (such as fault zones and stratigraphic pinchouts) to improve modeling accuracy, while larger tetrahedrons are used in areas with simpler geological structures to reduce computational effort. Ultimately, a tetrahedral network is constructed that accurately fits the geological interface morphology and adapts to the spatial variation of geological parameters.

[0090] For each regular grid cell in the finite difference network, its spatial bounding box range is calculated, and then the tetrahedral network is traversed to retrieve all tetrahedral cells that are completely or partially located within the bounding box. The unique IDs (identification marks) of these tetrahedral cells are extracted and marked on the corresponding finite difference grid cells to form a mapping relationship between finite difference grid cells and tetrahedral cell IDs. This process is repeated until all finite difference grid cells are marked, and finally multiple identification sets containing spatial mapping relationships are obtained, which provide basic data for the subsequent spatial association of the two types of networks.

[0091] For each vertex in the tetrahedron network, the Euclidean distance to the center of each grid cell in the finite difference network is calculated, and the distance is converted into a weight coefficient (the closer the distance, the greater the weight) through the Gaussian kernel function. The weight formula is: Where w represents the weight coefficient, which is used to quantify the spatial correlation strength between the tetrahedral network vertices and the finite difference network grid cells. The closer the distance, the greater the weight. d represents the Euclidean distance from the tetrahedral network vertex to the center of the grid cell in the finite difference network, which is used to measure the spatial distance between the two types of network nodes. σ is a scale parameter, which is used to control the rate at which the weight decays with distance, affecting the distribution range and sensitivity of the distance weight. e is a natural constant, which is the base of the natural exponential function and is used in this formula to construct the exponential decay relationship between distance and weight. The weight coefficients of all tetrahedral vertices and finite difference grid cells are arranged in rows and columns to construct a distance weight matrix of dimension N×M (N is the number of tetrahedral vertices, M is the number of finite difference grid cells). This matrix quantifies the spatial correlation strength between the two types of network nodes and provides weight parameters for subsequent mapping calculations.

[0092] Utilizing a constructed distance weight matrix and multiple identification sets, a mapping calculation is performed between the finite-difference network and the tetrahedron network. For each finite-difference grid cell, the attribute transfer relationship between the grid cell and the tetrahedron cell is calculated using a weighted average method based on the tetrahedron cell ID contained in its identification set and the corresponding weight coefficient in the distance weight matrix. This establishes a hybrid spatial index mapping relationship that reflects both spatial location association and attribute similarity. This achieves a bidirectional mapping between the regularized finite-difference network and the unstructured tetrahedron network, providing an efficient data index structure for the spatiotemporal associations between the two types of models.

[0093] Through the hybrid spatial index mapping relationship, the time-space dual-dimensional association technology is used to realize the binding of the infiltration coupling model and the three-dimensional geological structure model. First, the finite difference grid unit of the infiltration coupling model and the tetrahedron unit of the three-dimensional geological structure model are established through index mapping. Then, based on the time step, the hydrological process parameters (such as infiltration flux and recharge rate) are mapped to the corresponding geological space position in a time series, forming a space-time-attribute trinity association network. Specifically, by developing a data interaction interface and setting the time-space synchronization threshold (spatial error ≤ 5 meters, time error ≤ 1 hour), when the model is running, the mapping relationship in the hybrid index is called in real time to drive the two-way transmission of hydrological parameters and geological attributes, and finally construct a digital twin that can dynamically reflect the groundwater infiltration and recharge process, and realize high-precision simulation of the physical process of the groundwater system.

[0094] In one possible implementation, step S400 further includes:

[0095] Step S470: Based on the digital twin, the infiltration coupling model is driven to perform water cycle simulation and deduction to obtain vertical water flux; based on the vertical water flux, spatial integration is performed to obtain the total regional recharge; based on the vertical water flux, time integration is performed to obtain the cumulative recharge for a period; based on the digital twin, the three-dimensional geological structure model is driven to synchronize the total regional recharge and the cumulative recharge for the period to the three-dimensional geological structure model for auxiliary simulation to obtain groundwater infiltration recharge with multiple time and space scales; the groundwater infiltration recharge with multiple time and space scales is added to the dynamic simulation result.

[0096] Specifically, based on the constructed digital twin, the lithologic parameters (such as permeability and porosity) of the three-dimensional geological structure model and the hydrological process parameters (such as precipitation intensity and evaporation) of the infiltration coupling model are temporally and spatially matched through a hybrid spatial index mapping relationship. The finite difference method is used to solve the Richards equation, and the vertical water migration of each grid cell per unit time is calculated to generate a high-precision vertical water flux field, thereby realizing the dynamic quantification of the groundwater infiltration process.

[0097] Based on the vertical water flux field and the spatial grid division of the three-dimensional geological structure model, the vertical water flux of all grid cells in the target area or the specified sub-area is spatially integrated. By traversing the mapping relationship between the finite difference network and the tetrahedron network, the flux value of each grid cell is converted into m 3 / (m 2 d) is multiplied by its corresponding three-dimensional spatial volume weight, and then accumulated and summed in the horizontal and vertical directions to finally obtain the total supply volume covering the entire area or the specified sub-area (unit: m 3 ), realizing the quantitative conversion from single-point flux to regional total.

[0098] Based on the time series data of the vertical water flux field, the vertical water flux in each time step is accumulated and integrated for specific periods such as day, month, and year. By traversing the time dimension data recorded in the digital twin, the flux values ​​of each time step in the corresponding period are superimposed in chronological order, and the area weight of the spatial grid is combined for calculation to finally obtain the cumulative recharge in a specific period (unit: m 3 ), realizing the quantification of the time dimension from instantaneous flux to the total amount over a period of time, and accurately reflecting the cumulative effect of groundwater infiltration and recharge at different time scales.

[0099] Through the hybrid spatial index mapping mechanism of the digital twin, the total regional recharge volume is allocated to a tetrahedral grid (e.g., 10m×10m×5m resolution) of a three-dimensional geological structure model based on the volume weights of the geological units. The cumulative recharge over a period of time is simultaneously mapped to the corresponding geological horizons in a time series (e.g., hourly / daily / monthly). Multiscale constraints are constructed by combining the permeability tensor field and porosity distribution. A parallel computing framework is used to enable bidirectional data transfer between hydrological parameters (e.g., recharge intensity) and geological attributes (e.g., permeability coefficient). A spatiotemporal synchronization algorithm (with a time step error of ≤0.1h and a spatial position error of ≤0.5m) drives the three-dimensional seepage field simulation. This generates groundwater infiltration recharge datasets covering different geological units (e.g., phreatic zone / confined layer) and at different time scales (e.g., rainstorm events / seasonal variations). This enables multidimensional quantification, from regional totals to local fluxes, and from long-term trends to transient responses.

[0100] Based on the digital twin-driven infiltration coupling model and the three-dimensional geological structure model, the vertical water flux of different geological layers is first calculated by the finite difference method (for example, the vertical water flux of the sand and gravel layer under heavy rain is 5.2~8.7m 3 / (m 2 d)), and then spatially integrate the vertical water flow to obtain the total regional recharge (e.g., the total regional recharge in a 24-hour rainstorm scenario is 15600m 3 ), and at the same time, perform time integration to obtain the cumulative supply volume during the period (e.g., the annual cumulative supply volume in the seasonal supply scenario is 35600m 3 Next, the lithologic parameters in the 3D geological structure model (e.g., the permeability coefficient of the silty clay layer is 0.85 m / d, and the permeability coefficient of the moderately weathered rock layer is 1.24 m / d) were temporally and spatially correlated with the aforementioned recharge data. At different spatial resolutions (10 m × 10 m to 100 m × 100 m) and time scales (hourly to annual), the vertical water flow, total regional recharge, and cumulative recharge over time were mapped to the grid nodes and tetrahedron vertices of the digital twin. Finally, these data were integrated into the dynamic simulation results in the form of 3D cloud maps and spatiotemporal distribution curves.

[0101] In one possible implementation, step S500 further includes:

[0102] Step S510: capturing the real-time monitoring data of the target area in real time, performing deviation analysis on the dynamic simulation result and the real-time monitoring data to obtain a deviation result, wherein the deviation result includes a spatiotemporal deviation tensor.

[0103] Step S520: performing descending analysis based on the spatiotemporal deviation tensor, constructing a simulated deviation sequence, and setting a deviation index according to the simulated deviation sequence.

[0104] Step S530: When the deviation indicator exceeds a preset deviation threshold, a hierarchical correction strategy is triggered.

[0105] Step S540: Execute the hierarchical correction strategy to automatically correct and optimize the digital twin to construct an optimized digital twin.

[0106] Step S550: re-simulating and deducing based on the digital twin optimization body to form a data closed loop, performing an assessment according to the data closed loop, and generating the groundwater infiltration and recharge assessment report.

[0107] Specifically, a sensor array (such as groundwater level sensors and soil water potential sensors) is deployed in the target area to collect monitoring data such as water level, moisture content, and seepage pressure in real time. The data is transmitted to the digital twin platform using the Internet of Things communication protocol, and the dynamic simulation results are spatially and temporally aligned with the real-time monitoring data. For each monitoring point, the deviation between the simulated value and the measured value in the X, Y, and Z spatial coordinates and time series is calculated, and then a spatiotemporal deviation tensor containing spatial position deviation components (ΔX, ΔY, ΔZ) and time series deviation components (Δt) is constructed. This tensor quantifies the error distribution of different dimensions in matrix form, providing a multi-dimensional data basis for subsequent deviation analysis.

[0108] The deviation values ​​for each dimension in the spatiotemporal deviation tensor (e.g., spatial position error, time series error, and attribute value error) are sorted in descending order and arranged from largest to smallest to form a simulated deviation sequence. This sequence visually displays the deviation distribution gradient and key error points. By statistically analyzing the cumulative distribution characteristics of the deviation values ​​in the sequence (e.g., the proportion of the top 10% deviation values ​​in the total error), and combining them with field standards for groundwater simulation, deviation metrics are established to characterize the overall simulation accuracy. These metrics, such as the root mean square error (RMSE) and mean absolute error (MAE), are used to quantify the degree of deviation between the simulation results and the actual monitoring data.

[0109] The set deviation indicators (such as root mean square error (RMSE) and mean absolute error (MAE)) are compared with preset deviation thresholds (for example, RMSE ≤ 3% and MAE ≤ 5%) in real time. When the deviation indicator exceeds the threshold, the degree of deviation is automatically identified and a graded correction strategy is triggered. This strategy is divided into multiple response mechanisms based on the size of the deviation (such as mild, moderate, and severe correction levels). Different levels correspond to different correction priorities and parameter adjustment ranges. For example, in the case of mild deviation, only local grid parameters are optimized, while in the case of severe deviation, the model structure reconstruction process is initiated. This ensures that the correction strategy matches the error scale and realizes dynamic control of simulation accuracy.

[0110] Based on the triggered hierarchical correction strategy, the corresponding correction process is initiated according to the degree of deviation: if it is a mild deviation, the local parameters of the infiltration coupling model in the digital twin (such as permeability and porosity) are fine-tuned through the particle swarm optimization algorithm; in the case of moderate deviation, the grid accuracy of the three-dimensional geological structure model is locally encrypted in combination with the Kriging interpolation method (such as refining the 10m×10m grid to 5m×5m), and the Kalman filter is used to update the boundary conditions; in the case of severe deviation, the model reconstruction mechanism is activated, and the tetrahedral network topology structure is regenerated based on the real-time monitoring data. The model parameter group is globally optimized through the genetic algorithm, and finally a digital twin optimization body with a higher degree of match with the actual monitoring data is constructed, realizing multi-level correction from parameter adjustment to structure optimization.

[0111] Based on the digital twin optimization body, the infiltration coupling model and the three-dimensional geological structure model are re-driven to carry out water cycle simulation, and the newly generated simulation results are analyzed again with the real-time monitoring data for spatiotemporal deviations to form a data closed loop of monitoring-deviation analysis-correction-resimulation. By evaluating the convergence trend of the deviation indicators in the closed loop (such as the RMSE is reduced to below the threshold after three consecutive corrections), parameter stability (such as the fluctuation range of the optimized parameters ≤ 2%) and model prediction accuracy (such as the spatial correlation coefficient with the measured data ≥ 0.9), a groundwater infiltration recharge assessment report is automatically generated, which includes the distribution of recharge at multiple spatiotemporal scales, visualization of the correction process, uncertainty quantification and future trend prediction, providing dynamic and reliable decision support for water resources management.

[0112] Example 2: Figure 2 1 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. Figure 2 The electronic device shown is merely an example and should not limit the functionality and scope of use of the embodiments of the present invention. The electronic device is implemented as a general-purpose computing device, and its components may include, but are not limited to, an input device 201, a processor 202, a memory 203, and an output device 204. The processor 202 may be one or more; the processor 202 executes the software programs, instructions, and modules stored in the memory 203 to perform various functional applications and data processing of the computer device, thereby implementing the aforementioned digital twin-based groundwater infiltration and recharge assessment method.

[0113] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0115] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, to the extent such modifications and variations fall within the scope of the present application and its equivalents, the present application is intended to include such modifications and variations.

Claims

1. A groundwater infiltration recharge assessment method based on digital twins, characterized by: The method comprises: Traverse the target area to perform multi-source sensing acquisition and obtain a multi-source dynamic monitoring data set; Performing groundwater infiltration simulation based on the multi-source dynamic monitoring data set to generate a full-process infiltration data set, and performing data coupling on the full-process infiltration data set to obtain an infiltration coupling model; Extracting geological structural parameters of the target area based on the multi-source dynamic monitoring data set and constructing a three-dimensional geological structural model; Correlating and mapping the infiltration coupling model with the three-dimensional geological structure model to construct a digital twin of the groundwater system, and performing simulation and deduction calculations based on the digital twin to obtain dynamic simulation results; Deviation analysis is performed based on the dynamic simulation results and real-time monitoring data, and the digital twin is automatically corrected and optimized based on the deviation results to generate a groundwater infiltration and recharge assessment report.

2. The groundwater infiltration and recharge assessment method based on digital twin according to claim 1, characterized in that: Traverse the target area to perform multi-source sensing acquisition and obtain a multi-source dynamic monitoring data set. The method includes: Retrieve the hydrogeological zoning map of the target area, conduct remote sensing acquisition of the target area, and obtain a remote sensing image set; Conduct change analysis based on the hydrogeological zoning map to determine key boundary lines for spatial division; Dividing the target area into a plurality of monitoring grid units according to the spatial division key boundary lines; Mapping the remote sensing image set to the plurality of monitoring grid units for traversal matching, and activating a plurality of sensor node groups according to the matching results; Performing multi-source sensing acquisition according to a unified spatiotemporal reference through the plurality of sensor node groups to generate an initial monitoring data set; The initial monitoring data set is temporally and spatially aligned, and missing data interpolation processing is performed based on the aligned data set to generate the multi-source dynamic monitoring data set.

3. The groundwater infiltration and recharge assessment method based on digital twin according to claim 2, characterized in that: Performing multi-source sensing acquisition by the plurality of sensor node groups according to a unified spatiotemporal reference to generate an initial monitoring data set, the method comprising: Constructing a monitoring connectivity graph of the target area with the center positions of the plurality of monitoring grid units as nodes; Traversing the monitoring connectivity graph, performing minimum value calculations on all nodes, and obtaining multiple minimum value paths; performing a collection sequence analysis on the plurality of sensor node groups based on the plurality of minimum value paths to generate a device movement trajectory; Aligning the multiple sensor node groups in time and space to build a unified time and space benchmark; The device movement trajectory is executed on the multiple sensor node groups according to the unified time-space basis. When the device arrives at the center position of each monitoring grid unit, the multiple sensor node groups are triggered to perform fixed-point sensing collection to obtain the initial monitoring data set.

4. The groundwater infiltration and recharge assessment method based on digital twin according to claim 1, characterized in that: Based on the multi-source dynamic monitoring data set, groundwater infiltration simulation is performed to generate an infiltration full-process data set, the method comprising: Perform soil inversion on the target area based on the multi-source dynamic monitoring data set to obtain soil moisture time series data; Introducing precipitation intensity data, performing water movement analysis on the soil moisture time series data according to the precipitation intensity data, and constructing soil moisture movement parameters; Perform spatial distribution calculation based on the soil water movement parameters to obtain a soil hydraulic parameter field; Surface infiltration boundary conditions are set according to the soil hydraulic parameter field, and groundwater infiltration is fully simulated based on the surface infiltration boundary conditions to generate a full-process infiltration data set.

5. The groundwater infiltration and recharge assessment method based on digital twin according to claim 4, characterized in that: The infiltration full process data set is coupled to obtain an infiltration coupling model, and the method includes: Perform soil infiltration analysis based on the full-process infiltration data set to obtain spatiotemporal distribution parameters of soil moisture content; Performing groundwater infiltration analysis based on the full-process infiltration data set to obtain infiltration flux parameters; performing an infiltration recharge calculation based on the spatiotemporal distribution parameter of the soil moisture content and the infiltration flux parameter to generate a groundwater recharge rate; Matching the infiltration flux parameter with the groundwater recharge rate in time and space to construct a two-way feedback coupling mechanism; Iterative correction is performed according to the bidirectional feedback coupling mechanism to construct the infiltration coupling model.

6. The groundwater infiltration and recharge assessment method based on digital twin according to claim 1, characterized in that: Extracting geological structural parameters of a target area based on the multi-source dynamic monitoring data set and constructing a three-dimensional geological structural model, the method includes: Performing geological analysis based on the multi-source dynamic monitoring data set to obtain a physical exploration data set; Performing inversion constraints based on the physical exploration data set to construct a multi-level constrained geological inversion framework; Performing data fusion according to the multi-level constrained geological inversion framework to construct a geological structure parameter cube, wherein the geological structure parameter cube includes geological structure parameters; The geological structure parameters are used as input to perform geological modeling and construct the three-dimensional geological structure model.

7. The groundwater infiltration and recharge assessment method based on digital twin according to claim 1, characterized in that: Correlating and mapping the infiltration coupling model with the three-dimensional geological structure model to construct a digital twin of the groundwater system, the method includes: Performing regularization based on the infiltration coupling model to construct a finite difference network; Performing unstructured processing based on the three-dimensional geological structure model to construct a tetrahedron network; Traversing the finite difference network and combining it with the tetrahedron network to perform identification, and obtaining a plurality of identification sets; Calculating the distance weights from the vertices of the tetrahedron network to the finite difference network, and constructing a distance weight matrix; Performing a mapping calculation on the finite difference network and the tetrahedron network according to a distance weight matrix combined with the multiple identification sets to construct a hybrid space index mapping relationship; Based on the hybrid spatial index mapping relationship, the infiltration coupling model and the three-dimensional geological structure model are temporally and spatially associated to construct the digital twin of the groundwater system.

8. The groundwater infiltration and recharge assessment method based on digital twin according to claim 1, characterized in that: Performing simulation and deduction calculations based on the digital twin to obtain dynamic simulation results includes: Based on the digital twin, the infiltration coupling model is driven to perform water cycle simulation to obtain vertical water flux; Perform spatial integration based on the vertical water flux to obtain the total regional recharge; Performing time integration based on the vertical water flow rate to obtain a cumulative recharge amount for a period of time; Based on the digital twin, the three-dimensional geological structure model is driven, and the total regional recharge amount and the cumulative recharge amount during the period are synchronized to the three-dimensional geological structure model for auxiliary simulation to obtain groundwater infiltration recharge at multiple temporal and spatial scales; The groundwater infiltration recharge at multiple time and space scales is added to the dynamic simulation results.

9. The groundwater infiltration and recharge assessment method based on digital twin according to claim 1, characterized in that: Deviation analysis is performed based on the dynamic simulation results and the real-time monitoring data, and the digital twin is automatically corrected and optimized based on the deviation results to generate a groundwater infiltration and recharge assessment report. The method includes: capturing the real-time monitoring data of the target area in real time, performing deviation analysis on the dynamic simulation result and the real-time monitoring data to obtain a deviation result, wherein the deviation result includes a spatiotemporal deviation tensor; Performing descending analysis based on the spatiotemporal deviation tensor to construct a simulated deviation sequence, and setting a deviation index according to the simulated deviation sequence; When the deviation index exceeds a preset deviation threshold, a hierarchical correction strategy is triggered; Executing the hierarchical correction strategy to automatically correct and optimize the digital twin to construct an optimized digital twin; Re-simulation and deduction are performed based on the digital twin optimization body to form a data closed loop, and evaluation is performed according to the data closed loop to generate the groundwater infiltration and recharge evaluation report.

10. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement the groundwater infiltration and recharge assessment method based on digital twins as described in any one of claims 1 to 9 when executing the executable instructions stored in the memory.

Images