29 results about "Groundwater contamination" patented technology

The invention relates to the technical field of soil monitoring, in particular to a soil-groundwater pollution risk threshold dynamic adjustment method and system based on an environment model, and the method comprises the steps: collecting soil and groundwater monitoring data, constructing an environment model containing the soil pollution concentration, the groundwater pollution concentration and the pollutant migration rate, obtaining comprehensive pollution characteristic data, extracting main characteristics, and determining the contribution degree of each characteristic to risk assessment; calculating the initial weight of each feature according to the contribution degree, and obtaining a weight distribution scheme; calculating pollution risk values of the soil and the underground water in combination with the pollution load data and the weight values, and preliminarily setting a risk threshold value; monitoring pollutant concentration fluctuation data in real time, predicting a pollutant migration trend through a time sequence analysis algorithm, and obtaining a risk change prediction result; and combining the risk change prediction result and the environmental capacity constraint optimization risk threshold to obtain a dynamically adjusted risk threshold. According to the invention, accurate extraction of pollution characteristics and dynamic adjustment of weights are realized.

The invention discloses a channel structure analysis method and system based on multi-modal data, and the method comprises the steps: obtaining the multi-source data of a target region, building a three-dimensional geological structure model of the target region based on the multi-source data, generating a point distribution scheme through a space optimization algorithm, generating a monitoring network based on the point distribution scheme, and carrying out the analysis of the three-dimensional geological structure model. Different types of tracers are injected into the injection points by adopting a graded injection strategy, monitoring data are collected, an underground structure model is generated based on the monitoring data, hydraulic parameters are calculated, the underground structure model is dynamically corrected based on the hydraulic parameters, and an underground pipeline three-dimensional model is obtained; and grading channel structures in the underground pipeline three-dimensional model by using a preset channel grading standard, and generating a channel three-dimensional map based on a grading result. According to the method, the three-dimensional model of the underground pipeline is generated through comprehensive analysis of the multi-modal data, and the structural analysis precision of the underground water pollution channel is improved.

The invention, which relates to the technical field of underground water pollution prevention and control, discloses a machine learning-based safety assessment method for a new reconstruction and extension land involving an underground pipeline, comprising the following steps: performing seepage and leakage risk assessment on the underground pipeline by using a constructed seepage and leakage risk assessment model based on machine learning; and according to a seepage leakage risk assessment result, performing groundwater pollution risk assessment on the pipeline with the seepage leakage risk by using the constructed groundwater pollution risk assessment model, and according to the assessment result, assessing the safety of the land for new reconstruction and extension of the underground pipeline. According to the method, the workload of traditional risk assessment based on numerical simulation is greatly reduced, the calculation process is simple and practical, the technology is reliable, engineering implementation is easy, reliable reference can be provided for scientific and accurate groundwater pollution prevention and control, and the method has important environmental protection and social significance.

The application discloses a groundwater cyanide pollution treatment system and relates to the technical field of groundwater pollution treatment. In the system, a sewage conditioning tank is used for water quality homogenization of underground sewage, and the underground sewage after water quality homogenization is input into a Fenton oxidation device; a multi-agent water inlet device is used for putting multiple agents into the Fenton oxidation device; the Fenton oxidation device is a cyanide pollution treatment site for underground sewage; a multifunctional water quality monitoring system is used for obtaining water quality parameters of water inlet of the Fenton oxidation device; an intelligent online control module is used for taking the water quality parameters of water inlet of the Fenton oxidation device as a feature vector, inputting into a machine learning prediction model, obtaining a predicted putting amount of the multiple agents, and controlling the multi-agent water inlet device based on the predicted putting amount of the multiple agents. The application realizes efficient and stable removal of cyanide by combining real-time monitoring with dynamic dosing and introducing a pollutant concentration-agent putting amount prediction mechanism, and guarantees that the effluent water quality continuously meets the standards.

The invention discloses a groundwater pollution risk detection device based on artificial intelligence, and relates to the technical field of optical detection, and the technical key points are that the groundwater pollution risk detection device comprises a detection module which comprises a base, a laser light source and a focusing lens are arranged on the base, a multispectral optical sensor is arranged on one side of the base, and an optical filter is arranged in a light receiving area and is used for receiving reflected light of different wave bands; the direction adjusting module comprises a mounting frame and is fixed with the base through a spherical holder movable part; the parameter processing module comprises a data acquisition unit, is in signal connection with the multispectral optical sensor, is then in signal connection with an intelligent processing unit embedded with an artificial intelligence algorithm model, and is used for matching the pollutant type and concentration and obtaining a warning signal when the concentration exceeds the standard; the online monitoring module comprises a wireless transmission unit, is in signal connection with the intelligent processing unit, is in wireless connection with a remote monitoring device, and is used for receiving and displaying related information; the detection timeliness can be improved, and the detection effect is improved.

This invention provides a method and system for precise transport control of remediation agents in in-situ groundwater remediation, relating to the field of groundwater pollution remediation technology. The method includes: acquiring images and sensor data from borehole cores at contaminated sites; extracting features through visual attention networks and temporal attention networks; fusing these features into a conditional probability diffusion model to generate hydrogeological feature vectors; constructing a high-precision hydrogeological feature model by combining spatial attention mapping and a generative diffusion model; inputting this model into a multi-regional collaborative simulation environment for optimization calculation; fusing monitoring data through edge computing nodes; and training a lightweight control model to execute the transport control of remediation agents.

The invention discloses a Monte Carlo simulation-based soil groundwater monitoring distribution point optimization method and system, and relates to the field of environmental monitoring and groundwater pollution prevention and control, and the optimization method comprises the following steps: S1, obtaining multi-source prior data and initial sampling data; s2, constructing a mixed probability distribution prior model and a probability distribution model; s3, performing posteriori updating on the prior model, and outputting a posteriori mean value and a confidence interval; s4, executing random sampling and spatial diffusion simulation; forming an extended scene set; s5, forming a high-credibility scene subset; s6, dividing risk levels and generating a pollution probability distribution diagram; s7, determining an optimal monitoring point position combination through an optimization algorithm; and S8, updating the model, the scene set and the point distribution scheme. According to the method, the problems of underestimation of high-concentration tail probability and overestimation of low-concentration area probability are effectively avoided, so that the risk of leak detection of pollution hot spots is reduced, and the identification capability of a monitoring network on a high-risk area is improved.

The application relates to the technical field of underground water pollution monitoring, and discloses a method and system for tracing the source of underground water organic pollution by fusing multi-source heterogeneous data. The method comprises the following steps: obtaining attribute fluctuation characteristics by processing geological difference data through a random forest; judging whether space-time dislocation exists in monitoring data fragments according to the attribute fluctuation characteristics; if yes, a first monitoring sequence is obtained by reconstruction processing; if not, concentration values are extracted as a second monitoring sequence; a concentration distribution matrix is obtained by carrying out grid division and spatial interpolation on the monitoring sequence; diffusion evolution processing is carried out on the concentration distribution matrix in combination with the attribute fluctuation characteristics to obtain a spreading track; and a pollution source is obtained by performing reverse tracing on the diffusion path extracted from the spreading track. The method can solve the problem that the fusion of multi-source heterogeneous geological data and monitoring data is insufficient, resulting in low tracing accuracy of the source of underground water organic pollution.

The present application relates to the technical field of edge computing, in particular to a groundwater pollution monitoring method and system based on edge computing, comprising the following steps: acquiring groundwater sequence data and calculating unit time fluctuation intensity parameters, comparing threshold interval to generate sampling frequency, collecting physicochemical indexes to generate deviation value set, extracting emergency weight parameters, combining edge node residual computing power cycle to generate task scheduling strategy, collecting environmental indexes to write into deviation cumulative matrix and accumulate row by row, comparing with the set risk threshold to generate pollution risk grade. In the present application, by adaptively matching the sampling frequency according to the fluctuation intensity state, the fixed interval blind area is effectively discarded and the mutation signal is captured, the scheduling strategy is constructed by combining the multi-dimensional deviation characteristics and the node computing power to generate the scheduling strategy, the dynamic allocation and computing power balance of the task are completed on the edge side, the link congestion caused by redundant baseline transparent transmission is avoided, the pollution trend is tracked based on the cumulative matrix, and the prepositioned research and judgment are realized.

This invention relates to the field of groundwater pollution remediation technology, specifically to a multifunctional synergistic filler and a green electricity-driven electrochemical groundwater remediation method. The filler uses attapulgite or montmorillonite-modified biomass pyrolytic carbon as a substrate, in-situ constructing a three-dimensional interconnected conductive network of graphene quantum dots and carboxylated carbon nanotubes. It anchors bifunctional catalytic sites composed of layered bimetallic hydroxides and defective metal oxides, possessing multiple functions including water permeability, adsorption and capture, electron transfer, and electrocatalytic reduction. Based on this filler, this invention constructs an e-PRB remediation wall, using solar green electricity to drive a fluctuating electric field to enhance the directional migration and in-situ fixation of heavy metals. An integrated multi-field coupling numerical model and dual intelligent control algorithm enable adaptive operation, simultaneously completing targeted heavy metal remediation, resource recovery, and in-situ regeneration of the filler. This method boasts high remediation efficiency, low carbon footprint, and environmental friendliness, making it suitable for various in-situ remediation scenarios for heavy metal pollution in groundwater.

This invention relates to a method for groundwater safety assessment under extreme climate events, comprising: collecting heterogeneous data from multiple sources such as meteorology, geology, hydrology, and remote sensing; standardizing, cleaning, semantically aligning, and completing missing data to construct a unified groundwater safety knowledge graph; monitoring extreme climate events in real time; updating node relationship weights and sparsifying transmission paths based on the dynamic evolution of the knowledge graph and a temporal attention mechanism; combining an improved graph neural network to infer risk propagation paths from the dynamic knowledge graph, identifying key pollution nodes, and outputting structured risk levels and response suggestions; the system continuously optimizes the graph and model parameters based on evolutionary feedback to achieve high adaptability and inference accuracy in emergency response. This method improves the intelligence, real-time performance, and accuracy of groundwater risk assessment, and solves the problems of difficulty in dynamically identifying groundwater pollution propagation paths and insufficient adaptability in decision-making under extreme climate events.

The application discloses a method and system for identifying and evaluating groundwater diffusion risk damage, and belongs to the technical field of risk assessment. The technical problem to be solved is that the prediction of future pollution risk trend is not considered, the pollution diffusion process cannot be dynamically responded, the groundwater diffusion risk damage cannot be quantified, and the quantification precision is low. The technical points are that the method comprises the following steps: S1, obtaining a pollution source and hydrological parameters; S2, constructing a pollution diffusion model; S3, calculating the concentration of a coordinate position at a t time in real time, and forming an over-standard area according to the over-standard groups; S4, calculating a risk index; S5, calculating a diffusion risk damage quantification value according to the risk index; S6, constructing a fusion network according to the risk index, performing risk space-time prediction, and obtaining a future risk index.

The invention provides a method and device for evaluating underground water pollution caused by carbon sequestration engineering, and relates to the technical field of carbon sequestration, and the method comprises the steps: setting a plurality of monitoring points in an underground water region of the carbon sequestration engineering, and setting various types of monitoring sensors at each monitoring point, the monitoring sensor comprises a dissolved carbon dioxide sensor, a heavy metal ion sensor, a pH sensor and a total dissolved solid sensor; for any monitoring point, acquiring monitoring data of the monitoring point under a plurality of monitoring indexes based on a monitoring sensor arranged on the monitoring point, and transmitting the monitoring data to a data processing center in real time; and performing groundwater pollution assessment on the received monitoring data of each monitoring point under the plurality of monitoring indexes based on the data processing center to obtain a groundwater pollution assessment score corresponding to the groundwater area. According to the method, it is ensured that the pollution source can be found in time when appearing, and diffusion and aggravation of potential pollution are avoided.

The invention discloses a water quality-water quantity-ecology coupled groundwater environment risk early warning method, and belongs to the technical field of groundwater resource management and ecological environment protection. According to the method, an underground water environmental risk early warning PQLRT model is constructed based on five types of underground water environmental risk early warning indexes, namely an underground water pollution risk P, an underground water quality change trend Q, an underground water level change trend L, an ecological risk R and an ecological evolution trend T; giving grade values 1-3 to the five types of early warning indexes respectively; carrying out weighted summation on the five index equal weights to form an underground water environment risk score; and according to the underground water environment risk score, an equal-distance grading method is adopted to divide into five early warning levels: no alarm, light alarm, medium alarm, heavy alarm and huge alarm. According to the invention, based on multi-source data fusion and factor weight construction, multi-dimensional risk identification, graded early warning and driving element determination of underground water environment risks are realized, and technical support is provided for sustainable utilization and ecological safety management of underground water resources.

This invention belongs to the field of soil and groundwater pollution remediation technology, specifically relating to a combined remediation device and method for vadose zone soil in contaminated sites. It includes at least four swing arms and a sampling and remediation mechanism located at the end of each swing arm. The sampling and remediation mechanism is perpendicular to the ground and includes a drilling section and a sampling monitoring system. The drilling section includes a longitudinal remediation chamber and a sample chamber inside, a telescopic sampling component located at the center of the remediation chamber, and several injection components located on the sidewalls of the remediation chamber. The telescopic sampling component transports soil samples to the sample chamber. After monitoring and analyzing the soil samples through the sampling monitoring system, monitoring results are generated. Based on the monitoring results, a remediation agent is injected into the contaminated vadose zone soil. This invention provides an in-situ remediation device and method that does not require moving the soil, offering high flexibility. The injection depth and injection pressure can be adjusted according to the soil pollution level in the vadose zone, enabling targeted remediation of soil layers in different spatial longitudinal or transverse directions.

The invention belongs to the technical field of groundwater environment, and relates to a multi-source heterogeneous data fused groundwater pollution risk prediction method, which comprises the following steps of: constructing a standardized multi-dimensional input data set containing a water quality state and an environment driving factor; constructing an initial hydrogeological topological graph of the underground water monitoring area; generating a dynamic physical state diagram reflecting the real-time hydraulic conduction capability; generating a node depth feature sequence capable of representing an independent change rule of each monitoring point; calculating a space source intensity attention matrix representing local emission abnormity; constructing a time conduction attention flow based on physical state constraint; and generating a global groundwater pollution risk prediction result, fusing the space source intensity attention matrix and the time conduction attention flow, and outputting the future risk probability of each node. According to the method, the problem that data adaptability and physical consistency of the model are difficult to consider due to the fact that a physical mechanism model and a data driving model are separated from each other in an existing prediction method is solved.

The invention discloses a groundwater interaction zone pollution monitoring natural attenuation restoration prediction method, and relates to the technical field of groundwater pollution simulation and prediction.The groundwater interaction zone pollution monitoring natural attenuation restoration prediction method comprises the steps that an unstable flow model is built based on real-time water level monitoring data, and bidirectional interaction flux is calculated through a transient hydraulic gradient inversion algorithm; establishing a three-dimensional solute displacement model, taking bidirectional interaction flux as dynamic boundary condition input, synchronously simulating pollutant dissolved phase concentration and adsorption phase concentration, and generating historical adsorption load distribution; setting a full-real scene and an oxygen-free contrast scene in the model, and quantitatively calculating positive contribution of oxygen supply and negative contribution of underground water back drainage by comparing output results; and predicting the natural attenuation restoration trend of the interaction zone pollution under the current water level fluctuation condition based on the positive and negative contribution data. Accurate capture and contribution quantitative stripping in the dynamic exchange process are achieved, and the problem that the historical adsorption release risk is underestimated due to the fact that the hysteresis effect is ignored in the prior art is solved.

This invention relates to the field of edge computing technology, specifically to a groundwater pollution monitoring method and system based on edge computing. The method includes the following steps: acquiring groundwater sequence data and calculating unit-time fluctuation intensity parameters; comparing threshold intervals to generate sampling frequencies; collecting physicochemical indicators to generate deviation difference sets and extracting urgency weight parameters; combining the remaining computing power of edge nodes to generate task scheduling strategies; collecting environmental indicators and writing them into a deviation accumulation matrix and accumulating them row by row; and comparing with set risk thresholds to generate pollution risk levels. In this invention, by adaptively matching the sampling frequency based on the fluctuation intensity state, the fixed interval blind zone is effectively eliminated and abrupt signals are captured. Combining multi-dimensional deviation features and node computing power to construct an allocation index to generate a scheduling strategy, dynamic task allocation and computing power balancing are completed at the edge, avoiding link congestion caused by redundant baseline transmission. Based on the accumulation matrix, pollution trends are tracked, achieving proactive assessment.

The application discloses a groundwater level prediction method and system based on big data, relates to the technical field of groundwater pollution prevention and control and hydrological environment monitoring, and comprises the following steps: step S1, determining a pollution source position, setting a time stamp of a pollution migration state; step S2, obtaining a space-time correlation feature; and step S3, constructing a correlation relationship and obtaining a groundwater level of a target monitoring station. Through fusion analysis of data, the time stamp of the pollution migration state is established, accurate synchronous benchmarks are provided for subsequent groundwater level prediction, multi-dimensional data can be integrated into a structured space-time correlation feature by extracting a correlation matrix, the pollution diffusion data of the ground that is easy to monitor can indirectly serve the groundwater level prediction by direct mapping, the problems of insufficient data or difficult acquisition are solved, and the prediction cost is reduced.

A method for zoning and grading evaluation of groundwater pollution in an industrial agglomeration area, in which current enterprise data information of a plurality of enterprises within the industrial agglomeration area is acquired; potential pollution-emitting enterprises are screened based on the current enterprise data information; a pollution monitoring network is constructed based on the potential pollution-emitting enterprises; pollution monitoring data information is acquired through the pollution monitoring network; soil pollution data information of areas near the potential pollution-emitting enterprises is acquired; based on the pollution monitoring data information and the soil pollution data information, groundwater pollution within the industrial agglomeration area is evaluated to obtain an evaluation result; when the evaluation result is greater than a preset evaluation threshold, a graded early-warning signal is generated based on the evaluation result, and a remediation strategy is generated based on the graded early-warning signal.

The application discloses an ISCO remediation system and a remediation method, and the remediation system comprises a multiphase extraction well, a groundwater circulation well and an auxiliary injection well, the multiphase extraction well is connected with a first ground system, the groundwater circulation well is connected with a second ground system, and the auxiliary injection well is connected with a third ground system. The method comprises the following steps: S1, pollution assessment; S2, remediation of a simple soil pollution area; S3, remediation of a simple groundwater pollution area; and S4, remediation of a soil and groundwater composite pollution area. The application provides various remediation wells with different structures aiming at various pollution conditions of soil and groundwater, can realize extraction of NAPL and multi-point synchronous injection of a remediation agent, realizes the purpose of shrinking the boundary of a pollution plume, and thus can achieve good remediation effect and remediation efficiency in a short term and a long term, and has important practical significance for ISCO remediation of soil and groundwater.

The application discloses a full-process automatic multi-phase flow multi-field coupling finite element code generation method, relates to the technical field of finite element analysis software development, and comprises the following steps: graphical modeling and information separation storage; intelligent analysis and automatic scheduling; code generation and source code level modification; data preparation and compilation execution; and result visualization. The application is used for realizing efficient numerical simulation of multi-phase flow and multi-field coupling problems in energy and environmental geotechnical engineering. The application is particularly suitable for numerical simulation of multi-phase flow and multi-field coupling problems in the fields of energy and environmental geotechnical engineering, such as groundwater pollution migration, geothermal energy development, CO2 geological storage and nuclear waste disposal.

The application discloses an intelligent control electric geotechnical barrier system and a construction and operation method thereof, characterized by comprising an electric geotechnical barrier device and an intelligent control device, wherein the electric geotechnical barrier device comprises a cathode row and an anode row arranged vertically and in parallel, the cathode row comprises at least two cathode electrode plates and a plurality of cathode conductive cores wrapped in the cathode electrode plates and distributed at equal intervals, and the gap between the two adjacent cathode electrode plates is filled with a permeable reaction wall; the cathode row comprises at least two anode electrode plates and a plurality of anode conductive cores wrapped in the anode electrode plates and distributed at equal intervals, and the gap between the two adjacent anode electrode plates is filled with an anode backfill soil; and the intelligent control device comprises a power module and a monitoring and control module, and the advantage is that the active interception, in-situ repair and intelligent control can be combined, and the efficient, durable and intelligent interception and repair of groundwater pollutants can be realized.

The application discloses a soil-groundwater pollution intelligent early warning method and system based on Internet of Things, and relates to application of the Internet of Things technology in the field of environmental monitoring and intelligent decision management, and comprises the following steps: S1: collecting soil and groundwater pollution data through an Internet of Things sensor network arranged in a monitoring area.The soil-groundwater pollution intelligent early warning method and system based on the Internet of Things solves the pain points of unclear management subject rights and responsibilities and delayed response in a cross-regional pollution event by constructing a pollution path driven dynamic rights and responsibilities topology network. A geographic fence triggers an automatic reorganization mechanism to realize synchronization of a management grid and pollution diffusion, thereby breaking the rigid constraint of administrative boundaries; and a double verification interlocking design ensures that the early warning decision has both environmental risk control accuracy and cross-regional cooperation feasibility.

The invention provides an underground water copper and nickel pollution traceability method suitable for a village-town-level industrial cluster area, relates to the technical field of underground water pollution traceability, and is sequentially carried out according to source identification, source preliminary judgment and source evidence stages under the condition of meeting traceability starting conditions. According to the method, the pollution area is determined by judging the standard exceeding degree of copper and nickel, the traceability range is delineated in combination with hydrogeological data and the Darcy law, a potential pollution source screening list is established, and source-approach-receptor pollution possibility analysis is carried out; under a multi-source condition, a suspected pollution source is determined by adopting a geophysical method and / or batched well building water quality analysis, and a final traceability conclusion is obtained through evidence of multiple technologies such as hydrochemistry, isotope, numerical simulation and tracer agent tracing when necessary. The method is staged, can jump, is high in technology coupling, and can improve the accuracy and the implementability of underground water pollution traceability in a complex area on the premise of controlling the cost.

The invention relates to the technical field of soil and groundwater pollution remediation and bioengineering, and discloses a complex microbial inoculant with a polycyclic aromatic hydrocarbon and petroleum hydrocarbon degradation function and application. The invention relates to a compound bacterial agent, which comprises Pseudomonas geniculata, Microdochium sp. And Bacillus velezensis, and is characterized in that the compound bacterial agent comprises Pseudomonas geniculata, Microdochium sp. And Bacillus velezensis, and the compound bacterial agent comprises Pseudomonas geniculata, Microdochium sp. And Bacillus velezensis. The composite microbial agent provided by the invention has high degradation efficiency on polycyclic aromatic hydrocarbon and petroleum hydrocarbon combined pollution, can be used for repairing polycyclic aromatic hydrocarbon and petroleum hydrocarbon combined pollution soil or polycyclic aromatic hydrocarbon and petroleum hydrocarbon combined pollution underground water, and has a good application prospect in green and sustainable repairing of petrochemical pollution sites.

The invention relates to the technical field of environmental monitoring and restoration, and discloses an intelligent groundwater pollution source tracing system based on multi-source remote sensing fusion, and the system comprises the steps: constructing a high-dimensional tensor representing the response of multiple physical fields of the earth surface through the multi-source remote sensing data of hyperspectrum, thermal infrared, synthetic aperture radar and the like; then, a core coupling physical forward simulation and self-consistent constraint engine module performs self-consistent constraint test on an internal coupling relationship among different physical dimensions in the high-dimensional tensor based on physical laws such as energy mass conservation so as to filter out pseudo abnormal signals irrelevant to the underground process; and the probability reverse traceability module based on causal inference performs Bayesian inversion matching on the effective signal passing the test and a pre-generated and physical self-consistent tensor fingerprint database, and outputs four-dimensional space-time probability distribution of the pollution source. According to the method, physical self-consistent constraints are introduced, data fusion is improved to a causal verification level from phenomenon association, and the tracing accuracy and reliability are improved.

This application relates to the field of groundwater monitoring, and in particular to a multi-parameter groundwater depth determination device. The device includes an integrated template on which a water level gauge, a thermometer, a conductivity meter, a pH meter, and a GPS positioning device are respectively installed. These components are modularly integrated into the template. A main control unit is mounted on the template, and the main control unit is connected to the water level gauge, thermometer, conductivity meter, pH meter, and GPS positioning device via a corresponding data transmission bus. A cable encoder and a depth-determining float are also installed on the template, and the float is lowered via a guide rod. The purpose of this application is to provide effective support for practical production work such as groundwater pollution prevention and control and ecological restoration.

The application discloses an industrial park-oriented groundwater pollution source Top-N probability tracing method, belongs to the technical field of groundwater pollution prevention and hydrogeological exploration, and comprises the following steps: preprocessing groundwater monitoring data and enterprise discharge information, constructing an enterprise-level candidate pollution source unit set and calculating initial prior probability; constructing a groundwater propagation graph and a candidate pollution source correlation graph to form a double-graph coupling structure; completing node feature initialization, abnormal information back propagation and posterior probability calculation based on a graph neural network to obtain Top-N sorting; and finally constructing a three-dimensional path probability cloud through reverse particle tracking, correcting the posterior probability by spatial overlap degree, and outputting the final result. The application integrates the advantages of physical mechanism and data driving, adapts to a multi-source pollution scene, improves tracing accuracy and practicability, and provides support for park pollution control.