River pollutant tracing system and method based on digital twinning

Abstract

The application relates to the technical field of water pollution tracing, and particularly discloses a river pollutant tracing system and method based on digital twinning, which comprises the following modules: a water body sampling module, which is used for acquiring current water quality data of a preset area of a target river; a model construction module, which is used for constructing a digital twinning model according to river terrain data and the current water quality data, and fusing historical hydrological data, real-time meteorological data and a distribution topology map of sewage outlets; a data analysis module, which is used for extracting the space-time characteristics of pollutant diffusion paths in the digital twinning model by using a graph convolutional neural network, combining a Bayesian inference, applying dynamic correction to a pollution source position probability distribution, and generating a tracing path heat map; and a pollution tracing module, which is used for obtaining a pollutant tracing result according to a confidence threshold of the tracing path heat map. The application can significantly improve the efficiency and accuracy of river pollutant tracing under a complex dynamic environment, and provides technical support for watershed ecological safety and precise management.

Description

Technical Field

[0001] This invention relates to the field of water pollution source tracing technology, and in particular to a river pollutant source tracing system and method based on digital twins. Background Technology

[0002] With rapid industrialization and urbanization, river water pollution has become increasingly severe, with frequent sudden pollutant discharge incidents posing a significant threat to the ecological security of river basins and the health of residents. How to quickly and accurately identify pollution sources and implement targeted remediation measures has become one of the core challenges of environmental monitoring and management. However, traditional river pollutant source tracing technologies still have many limitations and are insufficient to meet the needs of efficient remediation in complex and dynamic environments.

[0003] Current mainstream technologies mainly include chemical analysis based on manual sampling, numerical simulation prediction, and fixed sensor monitoring. Chemical analysis relies on on-site sampling and laboratory testing, which is time-consuming and has limited spatial coverage, making it difficult to achieve real-time response to pollution events. Although numerical simulation prediction can simulate pollutant diffusion paths, it relies on static parameter inputs (such as fixed hydrological and meteorological data), making it difficult to dynamically couple real-time monitoring data, resulting in model accuracy being limited by initial conditions and boundary assumptions. In addition, fixed sensor monitoring methods often adopt an isolated deployment mode, resulting in strong data heterogeneity, insufficient spatiotemporal resolution, and a lack of deep fusion mechanisms for multi-dimensional data, which easily leads to uncertainty in the source tracing results.

[0004] Therefore, there is an urgent need to provide a technical solution to address the above problems. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a river pollutant source tracing system and method based on digital twins.

[0006] In a first aspect, the present invention provides a river pollutant source tracing system based on digital twins, the technical solution of which is as follows:

[0007] The water sampling module is used to acquire current water quality data for a preset area of ​​the target river;

[0008] The model building module is used to construct a digital twin model of the target river based on the riverbed topography data and the current water quality data, and by integrating historical hydrological data, real-time meteorological data and the topology map of sewage outlet distribution.

[0009] The data analysis module is used to extract spatiotemporal features of pollutant diffusion paths in the digital twin model using graph convolutional neural networks, and to dynamically correct the probability distribution of pollution source locations by combining Bayesian inference to generate a heat map of the source tracing path.

[0010] The pollution source tracing module is used to obtain the pollutant source tracing results of the target river based on the confidence threshold of the source tracing path heat map.

[0011] Furthermore, the preset area includes: abnormal pollution areas and key nodes in the river channel; the current water quality data includes: pollutant concentration, pH value and dissolved oxygen data.

[0012] Furthermore, it also includes: a UAV remote sensing module; the UAV remote sensing module is used for:

[0013] The spectral characteristics of pollutants were determined by using a hyperspectral imager based on differences in spectral reflectance, and the characteristics of the river flow field and river topography data were captured simultaneously by a multispectral camera.

[0014] Based on the spatial superposition analysis of the spectral characteristics of the pollutants and the flow field characteristics of the river, the latitude and longitude coordinates that characterize the pollution anomaly are marked in real time to obtain the pollution anomaly area.

[0015] Furthermore, the model building module is specifically used for:

[0016] The river topography data and the sewage outlet distribution topology map are spatially gridded to generate a three-dimensional spatial grid structure for the river.

[0017] Based on the historical hydrological data, the cross-sectional flow and pollutant diffusion coefficient of the three-dimensional spatial grid structure are initialized, and the hydrodynamic equation and pollutant transport equation are coupled to construct a pollutant diffusion model.

[0018] The real-time meteorological data and the current water quality data are injected into the pollutant diffusion model through a spatiotemporal data synchronization engine. The river cross-sectional flow, pollutant diffusion coefficient and instantaneous discharge of sewage outlet in the pollutant diffusion model are dynamically corrected to obtain the digital twin model and dynamically generate the pollutant diffusion path.

[0019] Furthermore, the pollutant source tracing results include: candidate pollution source locations and predicted pollution diffusion trends; the pollution source tracing module is specifically used for:

[0020] The regions exceeding the confidence threshold in the heat map of the source tracing path are used as candidate pollution source locations, and the pollution diffusion prediction trend, which includes the spatiotemporal distribution map of pollutant concentration and the evolution curve of the impact range, is generated based on the time evolution parameters of the pollutant transport equation.

[0021] Furthermore, it also includes: a visualization module; the visualization module is used for:

[0022] The pollutant source tracing results are output to the target terminal for display.

[0023] Secondly, this invention provides a method for tracing the source of river pollutants based on digital twins. The technical solution of this method is as follows:

[0024] Obtain current water quality data for a predetermined area of ​​the target river;

[0025] Based on the riverbed topography data and current water quality data of the target river, and by integrating historical hydrological data, real-time meteorological data, and a topological map of sewage outlet distribution, a digital twin model of the target river is constructed.

[0026] The spatiotemporal features of the pollutant diffusion path in the digital twin model are extracted using a graph convolutional neural network. Combined with Bayesian inference, the probability distribution of the pollution source location is dynamically corrected to generate a heat map of the source tracing path.

[0027] Based on the confidence threshold of the heatmap of the source tracing path, the pollutant source tracing results of the target river are obtained.

[0028] Furthermore, the preset area includes: abnormal pollution areas and key nodes in the river channel; the current water quality data includes: pollutant concentration, pH value and dissolved oxygen data.

[0029] Furthermore, it also includes:

[0030] The spectral characteristics of pollutants were determined by using a hyperspectral imager based on differences in spectral reflectance, and the characteristics of the river flow field and river topography data were captured simultaneously by a multispectral camera.

[0031] Based on the spatial superposition analysis of the boundary of the abnormal region and the characteristics of the river flow field, the latitude and longitude coordinates that characterize the pollution anomaly are marked in real time to obtain the pollution anomaly region.

[0032] Thirdly, the technical solution of an electronic device according to the present invention is as follows:

[0033] It includes a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps of the digital twin-based river pollutant tracing method of the present invention.

[0034] Fourthly, the technical solution of a computer-readable storage medium provided by the present invention is as follows:

[0035] The computer-readable storage medium stores instructions that, when read, cause the computer-readable storage medium to perform the steps of the digital twin-based river pollutant tracing method of the present invention.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0037] The technical solution of this invention enables real-time response, dynamic correction, and visual source tracing of pollution sources, significantly improving the efficiency and accuracy of pollution source identification in complex dynamic environments, and providing technical support for watershed ecological security and precise governance.

[0038] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0040] Figure 1 This is a schematic diagram of an embodiment of a river pollutant tracing system based on digital twins according to the present invention;

[0041] Figure 2 This is a flowchart illustrating an embodiment of a river pollutant source tracing method based on digital twins according to the present invention.

[0042] Figure 3 This is a schematic diagram of an embodiment of an electronic device according to the present invention. Detailed Implementation

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0044] Figure 1 A schematic diagram of an embodiment of a river pollutant tracing system based on digital twins provided by the present invention is shown. Figure 1 As shown, the system includes 100 components:

[0045] The water sampling module 110 is used to acquire the current water quality data of a preset area of ​​the target river.

[0046] The target river is the river for which pollutant source tracing is required in this embodiment. The preset areas include: areas of abnormal pollution and key river nodes. Key river nodes refer to sensitive areas predicted based on historical pollution event statistics and pollutant diffusion models, specifically including river inflow points, tributary confluences, and downstream sections of sewage outlets. Current water quality data includes: pollutant concentration, pH value, and dissolved oxygen data. Water quality data differ for different areas (nodes) of the target river.

[0047] It should be noted that the water sampling module 110 is equipped with an autonomous navigation unit and a water quality sensor. The autonomous navigation unit generates a dynamic sampling path based on the coordinates of the preset area and the river topography data, controlling the movement of the sampling device (water quality sensor). Each time the water quality sensor reaches a preset area, it triggers fixed-point water sampling to acquire the current water quality data.

[0048] The model building module 120 is used to build a digital twin model of the target river based on the riverbed topography data and the current water quality data, and by integrating historical hydrological data, real-time meteorological data and the topology map of sewage outlet distribution.

[0049] Historical hydrological data can be obtained from hydrological databases or through satellite remote sensing inversion. The sewage outlet distribution topology map includes: the geographical location of the sewage outlets, discharge type (industrial / domestic wastewater), discharge volume statistics, and discharge time patterns. The sewage outlet distribution topology map is generated by using drones equipped with visible light cameras to take aerial photographs of the river channel, combined with deep learning algorithms (such as YOLO) to identify the locations of sewage outlets.

[0050] In an alternative embodiment, the model building module 120 is specifically used for:

[0051] The river topography data and the sewage outlet distribution topology map are spatially gridded to generate a three-dimensional spatial grid structure for the river.

[0052] Among them, the three-dimensional spatial grid structure refers to the geometric coordinates (x, y, z) of each grid cell, the topological connection relationship, and the sewage outlet marking information.

[0053] Specifically, the Delaunay triangulation algorithm or finite element mesh generation tool (such as Gmsh) is used to divide the river channel into irregular triangular / tetrahedral mesh units based on the river channel topography data to ensure accurate fitting of complex terrain; the location of each sewage outlet in the sewage outlet distribution topology map is mapped to the nearest mesh node, and an initial discharge parameter (based on historical data or default value) is assigned to it, finally obtaining the three-dimensional spatial mesh structure of the river channel.

[0054] Based on the historical hydrological data, the cross-sectional flow and pollutant diffusion coefficient of the three-dimensional spatial grid structure are initialized, and the hydrodynamic equation and pollutant transport equation are coupled to construct a pollutant diffusion model.

[0055] Specifically, based on the average flow velocity recorded in historical hydrological data, it is allocated to each grid cell of the three-dimensional spatial grid structure using spatial interpolation to initialize the river cross-section flow. Based on historical pollutant concentration monitoring data, the diffusion coefficient is calculated using empirical formulas and assigned values ​​according to the river's depth gradient distribution to initialize the pollutant diffusion coefficient. The hydrodynamic equations use the Saint-Venant equations to describe river flow motion, while the pollutant transport equations use the convection-diffusion equations to describe pollutant migration. The pollutant diffusion model is used to dynamically simulate the migration, diffusion, and transformation processes of pollutants in the river channel by coupling physical mechanisms with real-time data; that is, the pollutant diffusion model is generated by coupling the hydrodynamic equations and the pollutant transport equations.

[0056] It should be noted that the hydrodynamic equation is: Q represents the river cross-sectional discharge, h represents the water level, A represents the cross-sectional area of ​​the water passage, and S represents the cross-sectional area of ​​the water passage. f Let g represent the friction gradient and g represent the acceleration due to gravity. The hydrodynamic equations are used to calculate the velocity field of the water flow, providing a carrier for pollutant transport. The pollutant transport equation is: u represents the flow velocity, D represents the pollutant diffusion coefficient, and S represents the instantaneous discharge from the sewage outlet. The pollutant transport equation is used to simulate the combined effects of pollutant migration with water flow (convection), natural diffusion, and external input.

[0057] The real-time meteorological data and the current water quality data are injected into the pollutant diffusion model through a spatiotemporal data synchronization engine. The river cross-sectional flow, pollutant diffusion coefficient and instantaneous discharge of sewage outlet in the pollutant diffusion model are dynamically corrected to obtain the digital twin model and dynamically generate the pollutant diffusion path.

[0058] Specifically: ① Real-time meteorological data, including wind speed v and rainfall R, is obtained through an API interface and mapped to a three-dimensional river grid using spatial interpolation; current water quality data consists of pollutant concentrations C collected by mobile devices at key nodes. obs ② The water surface friction coefficient S is adjusted based on the wind speed v. f The flow distribution is updated iteratively through hydrodynamic equations to correct the cross-sectional flow rate Q; with C obs Concentration C predicted by the model sim The objective is to minimize the residual, and the gradient descent method is used to optimize the value of D and correct the pollutant diffusion coefficient D; if a downstream node of a certain discharge outlet satisfies C obs >C sim+3σ (σ is the historical concentration standard deviation), then update the instantaneous discharge S of the sewage outlet according to the Bayesian formula. ③ Only for the local grid affected by the correction parameters (such as the area within a 50-meter radius around the sewage outlet), resolve the hydrodynamic equation and pollutant transport equation to generate the updated pollutant concentration field C. new Extract C new The spatiotemporal distribution of pollutants is analyzed, and dynamically updated pollutant diffusion paths are output.

[0059] The data analysis module 130 is used to extract the spatiotemporal features of the pollutant diffusion path in the digital twin model using a graph convolutional neural network, and to dynamically correct the probability distribution of the pollution source location by combining Bayesian inference to generate a heat map of the source tracing path.

[0060] Specifically: ① The pollutant diffusion path is mapped as a graph structure, where each node represents a river channel grid cell. Node characteristics include pollutant concentration, flow velocity, diffusion coefficient, and timestamp. Edge weights are calculated based on the flow direction and distance between grid cells, for example: w ij d represents the edge weight between the i-th channel grid cell and the j-th channel grid cell. ij ① Represents the Euclidean distance between the i-th and j-th channel grid cells. ② Use a gated graph convolutional network for multi-layer message passing, outputting the spatiotemporal feature vector of each node (channel grid cell). ③ Based on the spatiotemporal feature vector output by the gated graph convolutional network, generate the initial pollution source probability distribution P through a fully connected layer. prior (x); Assuming pollutant concentration C obs N(C) follows a Gaussian distribution sim ,σ 2 Markov chain Monte Carlo (MCMC) sampling is used to iteratively update the posterior probability: P posterior (x)∝P(C obs |x)·P prior (x). ④ Normalize the posterior probability to the 0-1 interval, and render it to the 3D river grid through color mapping (e.g., red → high probability, blue → low probability) to generate a heat map of the source tracing path.

[0061] It should be noted that the above process updates the posterior distribution of pollution source locations through Bayesian inference, which falls under the category of probabilistic modeling and parameter estimation, rather than aiming to optimize the objective function. The above technical solution preserves the spatial topology and temporal evolution correlation through graph structures, overcoming the limitations of traditional convolutional neural networks in modeling irregular river channels; the Bayesian framework integrates physical model predictions with real-time data, reducing the misjudgment rate caused by multi-source interference.

[0062] The pollution source tracing module 140 is used to obtain the pollutant source tracing results of the target river based on the confidence threshold of the source tracing path heat map.

[0063] The pollutant source tracing results include: candidate locations of pollution sources and predicted trends of pollution diffusion. The confidence threshold can be set according to actual conditions, such as 80%, and is not limited here.

[0064] In one alternative embodiment, the pollution tracing module 140 is specifically used for:

[0065] The regions exceeding the confidence threshold in the heat map of the source tracing path are used as candidate pollution source locations, and the pollution diffusion prediction trend, which includes the spatiotemporal distribution map of pollutant concentration and the evolution curve of the impact range, is generated based on the time evolution parameters of the pollutant transport equation.

[0066] Specifically: ① Based on the confidence threshold, extract all grid cells exceeding the confidence threshold from the source tracing path heatmap. ② Use the DBSCAN algorithm to cluster continuous high-probability areas (grid cells), with the cluster centers being candidate pollution source locations. ③ Based on the pollutant transport equation, set a prediction time window, inject real-time meteorological forecast data (wind speed, rainfall) as boundary conditions, run the digital twin model, and output the concentration field at each time step. ④ Extract areas where the concentration exceeds the safety standard and generate a spatiotemporal distribution map. ⑤ Statistically calculate the pollution area and maximum impact distance at each time step, plot the curves of pollution area and maximum impact distance at each time step, mark inflection points (such as pollution peak time), and obtain the pollution diffusion prediction trend.

[0067] In one alternative embodiment, the system further includes: an unmanned aerial vehicle (UAV) remote sensing module. The UAV remote sensing module is equipped with a hyperspectral imager and a multispectral camera for cruising along the target river; the UAV remote sensing module is used for:

[0068] The spectral characteristics of pollutants were determined by using a hyperspectral imager based on differences in spectral reflectance, and the characteristics of the river flow field and river topography data were captured simultaneously by a multispectral camera.

[0069] The specific steps for determining the spectral characteristics of pollutants based on differences in spectral reflectance using a hyperspectral imager include: ① The hyperspectral imager continuously scans the river surface at nanometer-level spectral resolution (e.g., 5 nm) to acquire hyperspectral cubic data (spatial × spectral dimension) in the 400-2500 nm band. ② Calculate the difference in spectral reflectance: ΔR(λ) = R target (λ)-R background (λ); ΔR(λ) represents the difference in spectral reflectance at wavelength λ, characterizing the difference in reflectance between the target area and the background area in a specific wavelength band, and is used to identify abnormal reflectance features caused by pollutants. R target (λ) represents the spectral reflectance of the target area (suspected contaminated area) at wavelength λ. background(λ) represents the spectral reflectance of the background area (clean water body or unpolluted area) at wavelength λ. ③ Match the spectral library (such as the characteristic absorption peaks of heavy metals and petroleum pollutants) based on the difference in spectral reflectance to determine the pollutant type and obtain the spectral characteristics of the pollutant.

[0070] Based on the spatial superposition analysis of the spectral characteristics of the pollutants and the flow field characteristics of the river, the latitude and longitude coordinates that characterize the pollution anomaly are marked in real time to obtain the pollution anomaly area.

[0071] Specifically: ① Convert the spectral characteristics of pollutants and the river flow field characteristics to the same geographic coordinate system, and ensure that the timestamp deviation between the spectral and flow field data is less than 1 second through GPS synchronization. ② Starting from the boundary vertex of the abnormal area corresponding to the spectral characteristics of pollutants, trace the possible source path of pollutants along the flow field vector in the reverse direction, simulating the reverse motion trajectory of particles. ③ Assign weights to the grid cells traversed by the tracing path according to the following rules: the larger the absolute value of ΔR(λ), the higher the weight; if the flow direction is consistent with the source tracing path direction, the weight increases. ④ Perform spatial clustering on the weight values ​​(such as the Getis-Ord Gi* algorithm for hotspot analysis), identify significantly high-weight areas, and extract the latitude and longitude of the geometric center point of the hotspot area as the coordinates of the pollution anomaly area; if the hotspot area consists of multiple discrete points, take the top N points with the highest weights (e.g., N=5) to finally obtain the pollution anomaly area.

[0072] In an alternative embodiment, it further includes: a visualization module; the visualization module is used for:

[0073] The pollutant source tracing results are output to the target terminal for display.

[0074] The target terminal can be a visual device such as a mobile phone, computer, tablet, or smart bracelet, and there are no restrictions on this.

[0075] This embodiment addresses the limitations of traditional river pollutant source tracing technologies by proposing a river pollutant source tracing system based on digital twins. The technical solution of this embodiment constructs a digital twin model by fusing multi-source data, extracts spatiotemporal features using graph convolutional neural networks, and combines Bayesian inference to dynamically correct the probability distribution of pollution source locations, generating a high-precision source tracing path heatmap. This system overcomes the problems of long processing times, limited accuracy, and strong data heterogeneity inherent in traditional methods, achieving real-time response, dynamic correction, and visualized source tracing of pollution sources. It significantly improves the efficiency and accuracy of pollution source identification in complex and dynamic environments, providing technical support for watershed ecological security and precise governance.

[0076] Figure 2 The diagram illustrates a flowchart of an embodiment of a river pollutant source tracing method based on digital twins provided by the present invention. Figure 2 As shown, the method includes the following steps:

[0077] S1. Obtain the current water quality data of the target river in a preset area;

[0078] S2. Based on the riverbed topography data of the target river and the current water quality data, and by integrating historical hydrological data, real-time meteorological data and the topology map of sewage outlet distribution, construct a digital twin model of the target river;

[0079] S3. Using a graph convolutional neural network, the spatiotemporal features of the pollutant diffusion path in the digital twin model are extracted, and Bayesian inference is combined to dynamically correct the probability distribution of the pollution source location and generate a heat map of the source tracing path.

[0080] S4. Based on the confidence threshold of the heat map of the source tracing path, obtain the source tracing results of the target river.

[0081] In one alternative approach, the preset area includes: an abnormal pollution area and key nodes in the river channel; the current water quality data includes: pollutant concentration, pH value, and dissolved oxygen data.

[0082] In one alternative approach, it also includes:

[0083] The spectral characteristics of pollutants were determined by using a hyperspectral imager based on differences in spectral reflectance, and the characteristics of the river flow field and river topography data were captured simultaneously by a multispectral camera.

[0084] Based on the spatial superposition analysis of the spectral characteristics of the pollutants and the flow field characteristics of the river, the latitude and longitude coordinates that characterize the pollution anomaly are marked in real time to obtain the pollution anomaly area.

[0085] In one optional approach, the step of constructing a digital twin model of the target river based on the riverbed topography data and the current water quality data, and by integrating historical hydrological data, real-time meteorological data, and a topological map of sewage outlet distribution, includes:

[0086] The river topography data and the sewage outlet distribution topology map are spatially gridded to generate a three-dimensional spatial grid structure for the river.

[0087] Based on the historical hydrological data, the cross-sectional flow and pollutant diffusion coefficient of the three-dimensional spatial grid structure are initialized, and the hydrodynamic equation and pollutant transport equation are coupled to construct a pollutant diffusion model.

[0088] The real-time meteorological data and the current water quality data are injected into the pollutant diffusion model through a spatiotemporal data synchronization engine. The river cross-sectional flow, pollutant diffusion coefficient and instantaneous discharge of sewage outlet in the pollutant diffusion model are dynamically corrected to obtain the digital twin model and dynamically generate the pollutant diffusion path.

[0089] In one optional approach, the pollutant source tracing results include: candidate pollution source locations and predicted pollution diffusion trends; the step of obtaining the pollutant source tracing results of the target river based on the confidence threshold of the source tracing path heatmap includes:

[0090] The regions exceeding the confidence threshold in the heat map of the source tracing path are used as candidate pollution source locations, and the pollution diffusion prediction trend, which includes the spatiotemporal distribution map of pollutant concentration and the evolution curve of the impact range, is generated based on the time evolution parameters of the pollutant transport equation.

[0091] In one alternative approach, it also includes:

[0092] The pollutant source tracing results are output to the target terminal for display.

[0093] It should be noted that the beneficial effects of the river pollutant source tracing method based on digital twins provided in the above embodiments are the same as those of the river pollutant source tracing system 100 based on digital twins described above, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0094] The river pollutant tracing system based on digital twins of the present invention can be a computer program (including program code) running on a computer device. For example, the river pollutant tracing system based on digital twins of the present invention is an application software that can be used to execute the corresponding steps in the river pollutant tracing method based on digital twins of the present invention.

[0095] In some embodiments, the river pollutant tracing system based on digital twins of the present invention can be implemented using a combination of hardware and software. As an example, the river pollutant tracing system based on digital twins of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the river pollutant tracing method based on digital twins of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0096] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0097] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned methods for tracing the source of river pollutants based on digital twins. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the method for tracing the source of river pollutants based on digital twins according to any embodiment of the present invention by calling the computer program.

[0098] In one alternative embodiment, an electronic device is provided, such as Figure 2 As shown, Figure 2 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0099] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0100] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 2 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0101] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0102] The memory 4003 stores the application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0103] Among them, electronic devices can also be terminal devices. A terminal device can be any terminal device that can install applications and access web pages through applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0104] It should be noted that, Figure 2 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0105] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-described methods for tracing the source of river pollutants based on digital twins.

[0106] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0107] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned digital twin-based river pollutant source tracing method.

[0108] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0109] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0110] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0111] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0112] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0113] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0114] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A river pollutant tracing system based on digital twinning, characterized in that, Comprise: a water body sampling module for obtaining current water quality data of a preset area of a target river; a model construction module for constructing a digital twin model of the target river according to river channel topographic data and the current water quality data of the target river, and fusing historical hydrological data, real-time meteorological data and a distribution topology of pollution outlets; a data analysis module for extracting space-time features of a pollutant diffusion path in the digital twin model by using a graph convolutional neural network, combining a Bayesian inference to apply dynamic correction of a pollution source location probability distribution, and generating a traceability path heat map; a pollution traceability module for obtaining a pollutant traceability result of the target river according to a confidence threshold of the traceability path heat map; the model construction module is specifically used for: spatially gridding the river channel topographic data and the distribution topology of pollution outlets to generate a river channel three-dimensional spatial grid structure; initializing river channel cross-section flow and pollutant diffusion coefficient of the three-dimensional spatial grid structure based on the historical hydrological data, and coupling a water dynamic equation and a pollutant transport equation to construct a pollutant diffusion model; injecting the real-time meteorological data and the current water quality data into the pollutant diffusion model through a space-time data synchronization engine to dynamically correct the river channel cross-section flow, the pollutant diffusion coefficient and the pollution outlet instantaneous discharge in the pollutant diffusion model, obtain the digital twin model and dynamically generate the pollutant diffusion path; the specific steps of generating the traceability path heat map are as follows: ① mapping the pollutant diffusion path into a graph structure, wherein each node represents a river channel grid unit, and node features include pollutant concentration, flow rate, diffusion coefficient and time stamp; ② using a gated graph convolutional network for multi-layer message passing to output a space-time feature vector of each node; ③Based on the spatiotemporal feature vector output by the gated graph convolution network, an initial pollution source probability distribution is generated through a fully connected layer ; assuming that the pollutant concentration obeys a Gaussian distribution ; Markov chain Monte Carlo sampling is used to iteratively update the posterior probability: ; ④ normalizing the posterior probability to the interval of 0-1, and rendering to a three-dimensional river channel grid through color mapping to generate a traceability path heat map.

2. The digital twin based river pollution source tracing system of claim 1, wherein, The preset area includes a pollution anomaly area and a river channel key node, and the current water quality data includes pollutant concentration, pH value and dissolved oxygen data.

3. The digital twin based river pollution source tracing system of claim 2, wherein, Further comprise: a UAV remote sensing module; the UAV remote sensing module is used for: using a hyperspectral imager to determine pollutant spectral characteristics according to spectral reflectance difference, and synchronously capturing river channel flow field characteristics and river channel topographic data through a multi-spectral camera; based on spatial superposition analysis of the pollutant spectral characteristics and the river channel flow field characteristics, real-time marking of latitude and longitude coordinates representing pollution anomalies is performed to obtain the pollution anomaly area.

4. The digital twin based river pollution source tracing system of claim 1, wherein, The pollutant traceability result includes a pollution source candidate location and a pollution diffusion prediction trend, and the pollution traceability module is specifically used for: regarding an area in the traceability path heat map exceeding a confidence threshold as a pollution source candidate location, and generating the pollution diffusion prediction trend including a pollutant concentration space-time distribution graph and an influence range evolution curve based on time evolution parameters of a pollutant transport equation.

5. The digital twin based river pollution source tracing system according to any one of claims 1 to 4, characterized in that, Further comprise: a visualization module; the visualization module is used for: outputting the pollutant traceability result to a target terminal for display.

6. A river pollutant tracing method based on digital twinning, characterized in that, Comprise: obtaining current water quality data of a preset area of a target river; According to the river channel topographic data and the current water quality data of the target river, and by fusing historical hydrological data, real-time meteorological data, and a topology map of a pollution outlet distribution, a digital twin model of the target river is constructed; A graph convolutional neural network is used to extract the spatiotemporal features of the pollutant diffusion path in the digital twin model, and a dynamic correction of the probability distribution of the pollution source position is applied by combining Bayesian inference to generate a tracing path heat map; The generation process of the pollutant diffusion path is as follows: The river channel topographic data and the topology map of the pollution outlet distribution are subjected to spatial gridding processing to generate a river channel three-dimensional spatial grid structure; Based on the historical hydrological data, the river channel cross-section flow and the pollutant diffusion coefficient of the three-dimensional spatial grid structure are initialized, and a water dynamic equation and a pollutant transport equation are coupled to construct a pollutant diffusion model; The real-time meteorological data and the current water quality data are injected into the pollutant diffusion model through a spatiotemporal data synchronization engine, the river channel cross-section flow, the pollutant diffusion coefficient, and the instantaneous discharge of the pollution outlet in the pollutant diffusion model are dynamically corrected, the digital twin model is obtained, and the pollutant diffusion path is dynamically generated; The specific steps of generating the tracing path heat map are as follows: ①The pollutant diffusion path is mapped into a graph structure, where each node represents a river channel grid element, and the node features include pollutant concentration, flow rate, diffusion coefficient, and time stamp; ②A gated graph convolutional network is used for multi-layer message passing to output the spatiotemporal feature vector of each node; ③Based on the spatiotemporal feature vector output by the gated graph convolution network, an initial pollution source probability distribution is generated through a fully connected layer ; assuming that the pollutant concentration obeys a Gaussian distribution ; Markov chain Monte Carlo sampling is used to iteratively update the posterior probability: ;​ ④The posterior probability is normalized to the 0-1 interval and rendered to the three-dimensional river channel grid through color mapping to generate the tracing path heat map; According to the confidence threshold of the tracing path heat map, the pollutant tracing result of the target river is obtained.

7. The digital twin based river pollution source tracing method of claim 6, wherein, The preset area includes a pollution anomaly area and a river channel key node; the current water quality data includes pollutant concentration, pH value, and dissolved oxygen data.

8. An electronic device, comprising: The electronic device includes a processor coupled with a memory, and the memory stores at least one computer program, which is loaded and executed by the processor to enable the electronic device to implement the river pollutant tracing method based on digital twin as claimed in claim 6 or 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one computer program, which is loaded and executed by the processor to enable the computer readable storage medium to implement the river pollutant tracing method based on digital twin as claimed in claim 6 or 7.

Images