A simulation system of atmospheric pollution diffusion

Abstract

This invention relates to the field of environmental science and technology, and discloses a simulation system for atmospheric pollution diffusion, including a data acquisition module, a data preprocessing module, a dynamic simulation model module, a simulation calculation module, a visualization module, and a decision support module. The data acquisition module collects data from multiple sources; the data preprocessing module cleans, fuses, and optimizes the collected data; the dynamic simulation model module employs a dynamic hybrid diffusion model and combines deep learning to optimize model parameters; the simulation calculation module performs efficient simulation of pollutant diffusion; the visualization module dynamically displays the pollutant concentration distribution and diffusion path in three dimensions; and the decision support module generates pollution control suggestions and risk warning information based on the simulation results. In this invention, by introducing a dynamic hybrid diffusion model, intelligent switching between Gaussian plume models and CFD models is achieved, enabling adaptation to various scenarios ranging from simple to complex terrains.

Description

Technical Field

[0001] This invention relates to the field of environmental science and technology, and in particular to a simulation system for atmospheric pollution diffusion. Background Technology

[0002] Air pollution has become a global environmental problem, posing a serious threat to ecosystems and human health. With accelerated urbanization and increased industrial activity, emissions of air pollutants such as PM2.5, SO2, and NOx have increased significantly, and their diffusion and distribution characteristics are influenced by multiple factors, including meteorological conditions, topography, and the characteristics of pollution sources. Simulation technology has become an important tool for assessing the impact range, concentration distribution, and potential environmental hazards of air pollution.

[0003] While commonly used Gaussian plume models in existing technologies offer high computational efficiency, their simulation accuracy drops significantly under complex terrain and dynamic weather conditions, making it difficult to reflect the impact of turbulence, topographic features, and unsteady weather on pollutant dispersion. CFD models, on the other hand, can provide high-precision simulations in complex scenarios, but their extremely high computational complexity makes them unsuitable for real-time or large-scale dispersion prediction. Furthermore, traditional models typically use a single, fixed simulation method, lacking dynamic switching capabilities and failing to balance computational efficiency with simulation accuracy. Summary of the Invention

[0004] To overcome the above shortcomings, this invention provides a simulation system for atmospheric pollution diffusion, which aims to improve the problem that traditional models usually use a single simulation method and lack dynamic switching capabilities.

[0005] In a first aspect, the present invention provides the following technical solution: a simulation system for atmospheric pollution diffusion, comprising a data acquisition module, a data preprocessing module, a dynamic simulation model module, a simulation calculation module, a visualization module, and a decision support module.

[0006] The data acquisition module is used to collect multi-source data, including pollutant concentration, meteorological parameters, and geographic information.

[0007] The data preprocessing module is used to clean, fuse, and optimize the collected data;

[0008] The dynamic simulation model module adopts a dynamic hybrid diffusion model and combines deep learning to optimize model parameters;

[0009] The simulation calculation module is based on a distributed computing framework and performs efficient simulation of pollutant diffusion.

[0010] The visualization module is used to dynamically display the concentration distribution and diffusion path of pollutants in three dimensions.

[0011] The decision support module generates pollution control suggestions and risk warning information based on simulation results.

[0012] Preferably, the data acquisition module includes:

[0013] The ground-based data acquisition unit uses electrochemical sensors to collect pollutant concentrations through fixed monitoring stations deployed in the target area;

[0014] The mobile data acquisition unit, equipped with a laser spectral sensor on a drone, collects real-time concentrations of trace pollutants in the air and provides precise spatial location data in conjunction with GPS.

[0015] The remote sensing acquisition unit, based on satellite remote sensing technology, uses multispectral image processing algorithms to extract atmospheric pollutant concentration distribution information.

[0016] Preferably, the data preprocessing module includes:

[0017] The data cleaning unit uses a statistical anomaly detection algorithm to remove sensor error data, and at the same time uses a sliding window filtering algorithm to smooth the time series data.

[0018] The missing value imputation unit uses a spatial interpolation method based on Kriging interpolation and an LSTM deep learning model to predict missing values ​​in time series data.

[0019] The data fusion unit uses the weighted least squares method to perform spatiotemporal weighted fusion of multi-source data to generate a high-precision initial concentration field.

[0020] Preferably, the dynamic simulation model module includes:

[0021] The Gaussian model element, based on the Gaussian plume model, is used for large-scale pollution diffusion simulation under simple topographic conditions. The specific steps include:

[0022] S1. Establish the Gaussian model formula.

[0023]

[0024] in:

[0025] C(x,y,z) represents the pollutant concentration;

[0026] Q represents the emission rate of the pollution source;

[0027] u represents the wind speed, with a value ranging from 1 to 20 m / s;

[0028] σ y ,σ z The lateral and vertical diffusion coefficients are calculated using modified formulas based on atmospheric stability category and distance;

[0029] y represents the lateral distance perpendicular to the wind direction;

[0030] z represents the vertical height;

[0031] H represents the emission height of the pollution source;

[0032] exp is an exponential function, representing e x , where e is the base of the natural logarithm;

[0033] S2. Determine the diffusion coefficient σ based on the Pasquill-Gifford stability category. y and σ z The calculation formula is as follows:

[0034] in:

[0035] x is the downwind distance;

[0036] a y ,a z These are the initial coefficients for lateral and vertical diffusion;

[0037] b y ,b z For exponential parameters of lateral and vertical diffusion;

[0038] S3, Introduction of Correction Factor

[0039] Based on the turbulence enhancement effect, correction factors α and β are added, and the correction formula is:

[0040] σ′ y =α·σ y , σ′ z =β·σ z

[0041] The values ​​of α and β range from 1.1 to 1.5, and are dynamically adjusted according to changes in wind speed and temperature.

[0042] The CFD model unit, based on computational fluid dynamics, simulates pollution diffusion under complex terrain and unsteady meteorological conditions, specifically including the following steps:

[0043] S1. Establishment of governing equations

[0044] mass conservation equation:

[0045] in:

[0046] ρ is the atmospheric density;

[0047] t represents time;

[0048] The rate of change of mass inflow or outflow;

[0049] For fluid velocity vector;

[0050] Momentum equation:

[0051] p represents pressure;

[0052] μ is the dynamic viscosity coefficient;

[0053] It is the vector of gravitational acceleration;

[0054] Pollutant transport equations:

[0055] in:

[0056] C represents the pollutant concentration;

[0057] For fluid velocity vector;

[0058] D is the turbulent diffusion coefficient, calculated from the turbulent viscosity coefficient, and its value ranges from 10. -3 -10 -1 m 2 / s

[0059] S represents the pollution source term, i.e., the emission rate of the pollution source;

[0060] S2, Using the -k-∈turbulence model

[0061] The parameters are:

[0062] Turbulent kinetic energy k = 1.5·(u′)2, where u′ is the turbulence intensity, ranging from 0.1 to 0.3·u;

[0063] Turbulent dissipation rate Where l is the turbulent mixing length, taking a value of 1-10 m, and C μ C is a constant in the turbulence model. μ =0.09;

[0064] S3, Mesh Generation

[0065] Unstructured triangular meshes are used to divide complex terrain;

[0066] The grid density is increased in regions with high concentration gradients, and the grid size ranges from 0.1 to 10 m.

[0067] S4. Numerical Solution

[0068] The finite volume method (FVM) is used to discretize the control equations;

[0069] Solving pressure-velocity coupling problems using the SIMPLE algorithm;

[0070] Model switching unit, setting terrain complexity threshold Slope max =15° and wind speed change threshold Δu / Δt = 2m / s 2 ;

[0071] When the input data meets simple shape and stable meteorological conditions, the Gaussian model unit is enabled;

[0072] When the input data exceeds the above threshold, it will automatically switch to the CFD model unit;

[0073] The parameter optimization unit utilizes a deep neural network (DNN) to optimize the diffusion coefficient. The DNN architecture includes:

[0074] Input layer: Includes 10 input features, including wind speed, wind direction, temperature, and turbulence intensity;

[0075] Hidden layers: 3 layers, each containing 64 neurons, with ReLU activation function;

[0076] Output layer: Outputs the optimized diffusion coefficient σ y and σ z ;

[0077] Training data size: no less than 100,000 pollution event data points, using the Adam optimizer with a learning rate of 0.001;

[0078] Multi-pollutant synergistic diffusion unit, establishing a chemical reaction model for multi-component pollutants:

[0079]

[0080] in:

[0081] NO x It is a nitrogen oxide;

[0082] VOC stands for volatile organic compounds.

[0083] O3 is ozone;

[0084] k is the chemical reaction rate constant;

[0085] The chemical reaction rate k is dynamically adjusted based on experimental data;

[0086] Simulated sedimentation rate ranges for different pollutants:

[0087] PM2.5 (0.01-0.05m / s), SO2 (0.02-0.1m / s).

[0088] Preferably, the simulation calculation module includes:

[0089] Distributed computing units, based on Hadoop or Spark computing frameworks, divide simulation tasks into multiple small regions for parallel computing;

[0090] The real-time computing unit, combined with GPU acceleration technology, optimizes the real-time simulation capability of pollutant diffusion through CUDA programming;

[0091] The adaptive grid division unit dynamically adjusts the grid density based on the changes in pollutant concentration gradient, and concentrates computing resources on regions with high concentration changes.

[0092] Preferably, the visualization module includes:

[0093] The three-dimensional dynamic display unit is a visualization platform developed based on WebGL and GIS technologies, which renders the three-dimensional distribution of pollutant concentrations in real time.

[0094] The time-series animation unit uses a front-end framework based on D3.js to dynamically generate time-series animations of the pollutant diffusion process;

[0095] The pollution source labeling unit locates pollution sources based on a reverse tracing algorithm and marks the location and spread range of pollution sources on a map using a Geographic Information System (GIS).

[0096] Preferably, the decision support module includes:

[0097] The pollution control recommendation unit analyzes simulation results and generates targeted control measures recommendations based on a multi-objective optimization algorithm.

[0098] The risk warning unit uses a classification algorithm to classify the pollution risk level of the simulated area and issue warning information.

[0099] The report generation unit uses automated template generation technology to integrate pollution diffusion paths, risk assessment results, and remediation recommendations into a richly illustrated report.

[0100] Secondly, the present invention provides the following technical solution: a simulation method for atmospheric pollution diffusion, comprising the following steps:

[0101] S1. Data Acquisition

[0102] Air pollution-related data are collected through multi-source acquisition devices, specifically including:

[0103] S101. Collect pollutant concentrations and meteorological parameters through electrochemical sensors at ground monitoring stations;

[0104] S102. Collect pollutant concentrations at spatial locations using a laser spectral sensor mounted on a drone;

[0105] S103. Extract the regional pollutant concentration distribution from multispectral images using satellite remote sensing technology;

[0106] S2. Data Preprocessing

[0107] The collected data is processed, specifically including:

[0108] S201. Data cleaning: smooth time series data based on sliding window filtering algorithm and remove outliers;

[0109] S202, Data imputation: Kriging interpolation is used to handle missing spatial data, and an LSTM deep learning model is used to complete the missing data of the time series.

[0110] S203, Data fusion: Ground, mobile, and remote sensing data are fused using the weighted least squares method to generate a high-precision initial concentration field of pollutants;

[0111] S3. Dynamic Simulation Modeling

[0112] A dynamic mixing-diffusion model is used to simulate pollutant diffusion, specifically including:

[0113] S301. Dynamically switch between Gaussian plume model and CFD model based on terrain complexity and meteorological conditions;

[0114] S302, the Gaussian plume model is used for rapid diffusion calculations under simple shape conditions;

[0115] The S303 and CFD models, combined with the finite volume method and turbulence model, are used to perform high-precision simulations of diffusion under complex terrain conditions.

[0116] S304. Introduce deep learning to optimize model parameters, including diffusion coefficient and turbulence mixing parameters;

[0117] S305. Establish a multi-pollutant co-diffusion model to simulate the chemical reactions and co-diffusion processes between pollutants;

[0118] S4. Simulation Calculation

[0119] Solving the diffusion model using a distributed parallel computing framework includes:

[0120] S401. Divide the simulation area into multiple sub-regions and use the Hadoop or Spark framework for parallel computing.

[0121] S402. Apply adaptive mesh generation technology in high-concentration gradient regions;

[0122] S403: Utilizing GPU acceleration technology and CUDA programming to optimize computational speed, it performs real-time pollution diffusion prediction.

[0123] S5. Results Visualization

[0124] The simulation results are dynamically visualized, including:

[0125] S501. Develop a 3D visualization platform using WebGL technology to display the spatial distribution of pollutant concentrations in real time;

[0126] S502. Based on D3.js, a time-series animation is generated to dynamically present the time evolution process of pollutant diffusion;

[0127] S503. In the visualization platform, combine GIS to mark the location of pollution sources and their impact range;

[0128] S6. Decision Support

[0129] Based on the simulation results, pollution control suggestions and risk warning information are generated, specifically including:

[0130] S601. Utilize multi-objective optimization algorithms to provide targeted governance recommendations, including pollution source closure and traffic restriction measures;

[0131] S602. Use the Support Vector Machine (SVM) model to classify pollution risks and issue health protection recommendations.

[0132] S603. Automatically generate comprehensive reports, including pollutant diffusion path maps, governance recommendations, and health warning information.

[0133] Thirdly, the invention provides the following technical solution: a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned simulation method for atmospheric pollution diffusion.

[0134] Fourthly, the present invention provides the following technical solution: a readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned simulation method for atmospheric pollution diffusion.

[0135] The present invention has the following beneficial effects:

[0136] 1. In this invention, by introducing a dynamic mixing diffusion model, intelligent switching between the Gaussian plume model and the CFD model is achieved, enabling adaptation to various scenarios ranging from simple to complex terrains. Simultaneously, deep learning technology is used to optimize the diffusion coefficient and turbulent mixing parameters, giving the model high accuracy and adaptability under dynamic weather conditions and sudden events, significantly outperforming the limitations of traditional single models.

[0137] 2. In this invention, the system employs a distributed computing architecture and GPU acceleration technology, significantly improving computational efficiency through task decomposition and parallel processing. Combined with adaptive mesh generation technology, the computational mesh is densified in high-concentration variation regions to achieve refined simulation while reducing the computational burden in low-concentration regions. This method balances simulation speed and accuracy, meeting the needs of real-time prediction and large-scale region simulation.

[0138] 3. In this invention, through a multi-pollutant synergistic diffusion model, the system can dynamically simulate the interactions between various pollutants (such as chemical reactions and sedimentation), such as the reaction process of NOx and VOCs generating ozone. This capability enables the system to provide more realistic simulation results in complex pollution scenarios, providing a scientific basis for the treatment of multi-source complex pollution.

[0139] 4. In this invention, the system utilizes GIS and WebGL technologies to develop a three-dimensional dynamic visualization platform, which can intuitively display the distribution of pollutant concentrations, diffusion paths, and temporal evolution processes. Users can adjust simulation parameters and view updated results in real time through an interactive interface. This function not only enhances the interpretability of simulation results but also provides clear decision-making references for environmental management departments. Attached Figure Description

[0140] Figure 1 This is a diagram showing the overall architecture of a simulation system for atmospheric pollution diffusion proposed in this invention.

[0141] Figure 2 This is a data acquisition module architecture diagram of an atmospheric pollution diffusion simulation system proposed in this invention;

[0142] Figure 3 This is a data preprocessing module architecture diagram of an atmospheric pollution diffusion simulation system proposed in this invention;

[0143] Figure 4 This is a diagram of the dynamic simulation model module architecture of an atmospheric pollution diffusion simulation system proposed in this invention.

[0144] Figure 5 This is a simulation calculation module architecture diagram of an atmospheric pollution diffusion simulation system proposed in this invention;

[0145] Figure 6 This is a visualization module architecture diagram of an atmospheric pollution diffusion simulation system proposed in this invention;

[0146] Figure 7 This is a diagram of the decision support module architecture of a simulation system for atmospheric pollution diffusion proposed in this invention.

[0147] Figure 8 This is a flowchart of a simulation method for atmospheric pollution diffusion proposed in this invention. Detailed Implementation

[0148] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 skilled in the art without creative effort are within the scope of protection of the present invention.

[0149] Example 1

[0150] Reference Figures 1-7 In the first embodiment of the present invention, an atmospheric pollution diffusion simulation system is provided, comprising a data acquisition module, a data preprocessing module, a dynamic simulation model module, a simulation calculation module, a visualization module, and a decision support module.

[0151] The data acquisition module is used to collect multi-source data, including pollutant concentrations, meteorological parameters, and geographic information.

[0152] The data preprocessing module is used to clean, fuse, and optimize the collected data;

[0153] The dynamic simulation model module adopts a dynamic hybrid diffusion model and combines deep learning to optimize model parameters;

[0154] The simulation calculation module is based on a distributed computing framework to achieve efficient simulation of pollutant diffusion;

[0155] The visualization module is used to dynamically display the concentration distribution and diffusion path of pollutants in three dimensions;

[0156] The decision support module generates pollution control suggestions and risk warning information based on simulation results.

[0157] Specifically, this system achieves intelligent switching between Gaussian plume and CFD models through an innovative dynamic hybrid diffusion model, giving it excellent adaptability under both simple and complex terrains, as well as static and dynamic meteorological conditions. Deep learning technology is used to optimize the diffusion coefficient and turbulent mixing parameters in real time, further improving the model's accuracy. Simultaneously, the system employs a distributed computing architecture combined with GPU acceleration technology, significantly improving computational efficiency, and optimizes resource allocation through adaptive mesh partitioning technology, refining the simulation of high-concentration variation areas. Combined with a multi-pollutant collaborative diffusion model, the system can dynamically simulate the chemical reactions and interactive diffusion processes between multiple pollutants, such as the chemical transformation of NOx and VOCs into ozone. This comprehensive and innovative design significantly improves the accuracy, dynamic adaptability, and computational efficiency of pollution diffusion simulation, providing reliable technical support for pollution prediction and control in complex scenarios.

[0158] The data acquisition module includes:

[0159] The ground-based data acquisition unit uses electrochemical sensors to collect pollutant concentrations through fixed monitoring stations deployed in the target area;

[0160] The mobile data acquisition unit, equipped with a laser spectral sensor on a drone, collects real-time concentrations of trace pollutants in the air and provides precise spatial location data in conjunction with GPS.

[0161] The remote sensing acquisition unit, based on satellite remote sensing technology, uses multispectral image processing algorithms to extract atmospheric pollutant concentration distribution information.

[0162] Specifically, this module ensures the comprehensiveness and real-time nature of data through collaborative acquisition and transmission from multiple sources. The ground monitoring station is equipped with various electrochemical sensors to collect concentrations of pollutants such as PM2.5, SO2, and NOx, while simultaneously recording meteorological conditions (such as wind speed, wind direction, temperature, and humidity). This data is uploaded to a central server via LoRa or 5G networks, ensuring stable transmission and low latency.

[0163] Furthermore, using a laser spectrometer mounted on a drone, high spatial resolution pollutant concentration data can be acquired in real time, and its built-in GPS module can record precise geographical location information. Remote sensing data is derived from multispectral satellite imagery; through a custom image processing algorithm, the pollutant concentration distribution in specific areas is extracted, and the collected data is spatiotemporally unified.

[0164] The data preprocessing module includes:

[0165] The data cleaning unit uses a statistical anomaly detection algorithm to remove sensor error data, and at the same time uses a sliding window filtering algorithm to smooth the time series data.

[0166] The missing value imputation unit uses a spatial interpolation method based on Kriging interpolation and an LSTM deep learning model to predict missing values ​​in time series data.

[0167] The data fusion unit uses the weighted least squares method to perform spatiotemporal weighted fusion of multi-source data to generate a high-precision initial concentration field.

[0168] Specifically, this module aims to improve data quality and provide high-precision input for subsequent simulation modeling. During data cleaning, a sliding window filtering algorithm is used to smooth noisy data, and an outlier removal method based on box plot analysis is designed to reduce measurement errors.

[0169] For missing data, Kriging interpolation is used to handle spatial incompleteness, while Long Short-Term Memory (LSTM) networks are used to predict and complete time-series data, ensuring data continuity and integrity. Finally, multi-source data fusion technology is combined, using weighted least squares to fuse data from different sources, and by adjusting the weight coefficients, the fusion results are kept consistent in spatiotemporal resolution.

[0170] The dynamic simulation model module includes:

[0171] The Gaussian model element, based on the Gaussian plume model, is used for large-scale pollution diffusion simulation under simple topographic conditions. The specific steps include:

[0172] S1. Establish the Gaussian model formula.

[0173]

[0174] in:

[0175] C(x,y,z) represents the pollutant concentration;

[0176] Q represents the emission rate of the pollution source;

[0177] u represents the wind speed, with a value ranging from 1 to 20 m / s;

[0178] σ y ,σ z The lateral and vertical diffusion coefficients are calculated using modified formulas based on atmospheric stability category and distance;

[0179] y represents the lateral distance perpendicular to the wind direction;

[0180] z represents the vertical height;

[0181] H represents the emission height of the pollution source;

[0182] exp is an exponential function, representing e x , where e is the base of the natural logarithm;

[0183] S2. Determine the diffusion coefficient σ based on the Pasquill-Gifford stability category. y and σ z The calculation formula is as follows:

[0184] in:

[0185] x is the downwind distance;

[0186] a y ,a z These are the initial coefficients for lateral and vertical diffusion;

[0187] by ,b z For exponential parameters of lateral and vertical diffusion;

[0188] S3, Introduction of Correction Factor

[0189] Based on the turbulence enhancement effect, correction factors α and β are added, and the correction formula is:

[0190] σ′ y =α·σ y , σ′ z =β·σ z

[0191] The values ​​of α and β range from 1.1 to 1.5, and are dynamically adjusted according to changes in wind speed and temperature.

[0192] The CFD model unit, based on computational fluid dynamics, simulates pollution diffusion under complex terrain and unsteady meteorological conditions, specifically including the following steps:

[0193] S1. Establishment of governing equations

[0194] mass conservation equation:

[0195] in:

[0196] ρ is the atmospheric density;

[0197] t represents time;

[0198] The rate of change of mass inflow or outflow;

[0199] For fluid velocity vector;

[0200] Momentum equation:

[0201] p represents pressure;

[0202] μ is the dynamic viscosity coefficient;

[0203] It is the vector of gravitational acceleration;

[0204] Pollutant transport equations:

[0205] in:

[0206] C represents the pollutant concentration;

[0207] For fluid velocity vector;

[0208] D is the turbulent diffusion coefficient, calculated from the turbulent viscosity coefficient, and its value ranges from 10. -3-10 -1 m 2 / s

[0209] S represents the pollution source term, i.e., the emission rate of the pollution source;

[0210] S2, Using the -k-∈turbulence model

[0211] The parameters are:

[0212] Turbulent kinetic energy k = 1.5·(u′)2, where u′ is the turbulence intensity, ranging from 0.1 to 0.3·u;

[0213] Turbulent dissipation rate Where l is the turbulent mixing length, taking a value of 1-10 m, and C μ C is a constant in the turbulence model. μ =0.09;

[0214] S3, Mesh Generation

[0215] Unstructured triangular meshes are used to divide complex terrain;

[0216] The grid density is increased in regions with high concentration gradients, and the grid size ranges from 0.1 to 10 m.

[0217] S4. Numerical Solution

[0218] The finite volume method (FVM) is used to discretize the control equations;

[0219] Solving pressure-velocity coupling problems using the SIMPLE algorithm;

[0220] Model switching unit, setting terrain complexity threshold Slope max =15° and wind speed change threshold Δu / Δt = 2m / s 2 ;

[0221] When the input data meets simple shape and stable meteorological conditions, the Gaussian model unit is enabled;

[0222] When the input data exceeds the above threshold, it will automatically switch to the CFD model unit;

[0223] The parameter optimization unit utilizes a deep neural network (DNN) to optimize the diffusion coefficient. The DNN architecture includes:

[0224] Input layer: Includes 10 input features, including wind speed, wind direction, temperature, and turbulence intensity;

[0225] Hidden layers: 3 layers, each containing 64 neurons, with ReLU activation function;

[0226] Output layer: Outputs the optimized diffusion coefficient σ yand σ z ;

[0227] Training data size: no less than 100,000 pollution event data points, using the Adam optimizer with a learning rate of 0.001;

[0228] Multi-pollutant synergistic diffusion unit, establishing a chemical reaction model for multi-component pollutants:

[0229]

[0230] in:

[0231] NO x It is a nitrogen oxide;

[0232] VOC stands for volatile organic compounds.

[0233] O3 is ozone;

[0234] k is the chemical reaction rate constant;

[0235] The chemical reaction rate k is dynamically adjusted based on experimental data;

[0236] Simulated sedimentation rate ranges for different pollutants:

[0237] PM2.5 (0.01-0.05m / s), SO2 (0.02-0.1m / s).

[0238] Specifically, the core of this module lies in dynamically selecting a suitable diffusion model and improving the model's adaptability through intelligent parameter optimization. In the Gaussian plume model part, a parameter table based on Pasquill-Gifford stability classification is constructed to correct the diffusion coefficient in real time and adapt to diffusion calculations under different meteorological conditions.

[0239] In the CFD modeling section, a three-dimensional turbulent flow field model was constructed, and the governing equations for pollutant diffusion were discretized using the finite volume method (FVM). In complex terrain, terrain mesh generation techniques were employed to generate unstructured meshes, with dynamic adjustment of mesh density to improve the simulation accuracy of pollutant concentration distribution. For the deep learning optimization section, a deep neural network (DNN) was designed, taking meteorological data and pollutant concentration characteristics as input and outputting optimized model parameters, significantly improving the efficiency of dynamic modeling.

[0240] The simulation calculation module includes:

[0241] Distributed computing units, based on Hadoop or Spark computing frameworks, divide simulation tasks into multiple small regions for parallel computing;

[0242] The real-time computing unit, combined with GPU acceleration technology, optimizes the real-time simulation capability of pollutant diffusion through CUDA programming;

[0243] The adaptive grid division unit dynamically adjusts the grid density based on the changes in pollutant concentration gradient, and concentrates computing resources on regions with high concentration changes.

[0244] Specifically, this module employs a distributed computing framework in its computing architecture, using Hadoop for large-scale data sharding and Spark for real-time simulation task scheduling. In terms of computing resource optimization, GPU acceleration technology is introduced, and CUDA programming is used to optimize computationally complex pollutant diffusion simulations.

[0245] Furthermore, to ensure computational accuracy, an adaptive mesh generation algorithm was developed. This algorithm automatically refines the mesh in areas with drastic changes in pollutant concentration and reduces the mesh density in areas with gentle concentration distribution, thereby achieving dynamic allocation and optimization of computational resources. This module can effectively support real-time pollutant diffusion simulation in large-scale complex environments.

[0246] The visualization module includes:

[0247] The three-dimensional dynamic display unit is a visualization platform developed based on WebGL and GIS technologies, which renders the three-dimensional distribution of pollutant concentrations in real time.

[0248] The time-series animation unit uses a front-end framework based on D3.js to dynamically generate time-series animations of the pollutant diffusion process;

[0249] The pollution source labeling unit locates pollution sources based on a reverse tracing algorithm and marks the location and spread range of pollution sources on a map using a Geographic Information System (GIS).

[0250] Specifically, the visualization module is built on GIS technology and can present the concentration distribution and diffusion trend of pollutants in real time. A 3D dynamic visualization platform developed using WebGL technology allows users to observe the 3D distribution structure of pollutant diffusion from multiple angles.

[0251] To enhance user experience, a time-series animation tool based on D3.js was developed to dynamically display the evolution of pollutant diffusion processes. Furthermore, the platform integrates pollution source localization functionality, using a reverse tracing algorithm to identify pollution sources and mark their specific locations and impact ranges on a map. Users can also input parameters through an interactive interface to update simulation results in real time and observe their changes.

[0252] The decision support module includes:

[0253] The pollution control recommendation unit analyzes simulation results and generates targeted control measures recommendations based on a multi-objective optimization algorithm.

[0254] The risk warning unit uses a classification algorithm to classify the pollution risk level of the simulated area and issue warning information.

[0255] The report generation unit uses automated template generation technology to integrate pollution diffusion paths, risk assessment results, and remediation recommendations into a richly illustrated report.

[0256] Specifically, this module generates remediation plans and risk warning information through comprehensive analysis of simulation results. In the pollution remediation recommendation section, a multi-objective optimization algorithm is used to calculate the effectiveness of different remediation plans, and the optimal plan is recommended based on indicators such as cost and timeliness.

[0257] For risk warning, a machine learning-based risk classification model was designed. This model uses Support Vector Machine (SVM) to classify contaminated areas and combines this with regional health standards to generate personalized protection recommendations. The module also features automatic report generation, integrating simulation results and recommendations into a richly illustrated document, including a pollution diffusion path map, the impact range of pollution sources, and health protection guidelines.

[0258] Example 2:

[0259] Reference Figure 8 In a second embodiment of the present invention, the present invention provides a simulation method for atmospheric pollution diffusion, comprising the following steps:

[0260] S1. Data Acquisition

[0261] Air pollution-related data are collected through multi-source acquisition devices, specifically including:

[0262] S101. Collect pollutant concentrations and meteorological parameters through electrochemical sensors at ground monitoring stations;

[0263] S102. Collect pollutant concentrations at spatial locations using a laser spectral sensor mounted on a drone;

[0264] S103. Extract the regional pollutant concentration distribution from multispectral images using satellite remote sensing technology;

[0265] S2. Data Preprocessing

[0266] The collected data is processed, specifically including:

[0267] S201. Data cleaning: smooth time series data based on sliding window filtering algorithm and remove outliers;

[0268] S202, Data imputation: Kriging interpolation is used to handle missing spatial data, and an LSTM deep learning model is used to complete the missing data of the time series.

[0269] S203, Data fusion: Ground, mobile, and remote sensing data are fused using the weighted least squares method to generate a high-precision initial concentration field of pollutants;

[0270] S3. Dynamic Simulation Modeling

[0271] A dynamic mixing-diffusion model is used to simulate pollutant diffusion, specifically including:

[0272] S301. Dynamically switch between Gaussian plume model and CFD model based on terrain complexity and meteorological conditions;

[0273] S302, the Gaussian plume model is used for rapid diffusion calculations under simple shape conditions;

[0274] The S303 and CFD models, combined with the finite volume method and turbulence model, are used to perform high-precision simulations of diffusion under complex terrain conditions.

[0275] S304. Introduce deep learning to optimize model parameters, including diffusion coefficient and turbulence mixing parameters;

[0276] S305. Establish a multi-pollutant co-diffusion model to simulate the chemical reactions and co-diffusion processes between pollutants;

[0277] S4. Simulation Calculation

[0278] Solving the diffusion model using a distributed parallel computing framework includes:

[0279] S401. Divide the simulation area into multiple sub-regions and use the Hadoop or Spark framework for parallel computing.

[0280] S402. Apply adaptive mesh generation technology in high-concentration gradient regions;

[0281] S403: Utilizing GPU acceleration technology and CUDA programming to optimize computational speed, it performs real-time pollution diffusion prediction.

[0282] S5. Results Visualization

[0283] The simulation results are dynamically visualized, including:

[0284] S501. Develop a 3D visualization platform using WebGL technology to display the spatial distribution of pollutant concentrations in real time;

[0285] S502. Based on D3.js, a time-series animation is generated to dynamically present the time evolution process of pollutant diffusion;

[0286] S503. In the visualization platform, combine GIS to mark the location of pollution sources and their impact range;

[0287] S6. Decision Support

[0288] Based on the simulation results, pollution control suggestions and risk warning information are generated, specifically including:

[0289] S601. Utilize multi-objective optimization algorithms to provide targeted governance recommendations, including pollution source closure and traffic restriction measures;

[0290] S602. Use the Support Vector Machine (SVM) model to classify pollution risks and issue health protection recommendations.

[0291] S603. Automatically generate comprehensive reports, including pollutant diffusion path maps, governance recommendations, and health warning information.

[0292] Example 3

[0293] In the third embodiment of the present invention, based on the same inventive concept, the present invention proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the simulation method for atmospheric pollution diffusion described in the above embodiments.

[0294] Example 4

[0295] In the fourth embodiment of the present invention, based on the same inventive concept, the present invention proposes a computer device, the terminal comprising: a processor and a memory; the processor and the memory communicate with each other; the memory is used to store instructions; the processor is used to execute the instructions in the memory to execute the simulation method for atmospheric pollution diffusion of the above embodiment.

[0296] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0297] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A simulation system for atmospheric pollution diffusion, comprising a data acquisition module, a data preprocessing module, a dynamic simulation model module, a simulation calculation module, a visualization module, and a decision support module, characterized in that: The data acquisition module is used to collect multi-source data, including pollutant concentration, meteorological parameters, and geographic information. The data preprocessing module is used to clean, fuse, and optimize the collected data; The dynamic simulation model module adopts a dynamic hybrid diffusion model and combines deep learning to optimize model parameters; The simulation calculation module is based on a distributed computing framework and performs efficient simulation of pollutant diffusion. The visualization module is used to dynamically display the concentration distribution and diffusion path of pollutants in three dimensions. The decision support module generates pollution control suggestions and risk warning information based on simulation results; The dynamic simulation model module includes: The Gaussian model element, based on the Gaussian plume model, is used for large-scale pollution diffusion simulation under simple topographic conditions. The specific steps include: S1. Establish the Gaussian model formula. ； in: C(x,y,z) represents the pollutant concentration; Q represents the emission rate of the pollution source; u represents the wind speed, with a value ranging from 1 to 20 m / s; σ y ,σ z The lateral and vertical diffusion coefficients are calculated using modified formulas based on atmospheric stability category and distance; y represents the lateral distance perpendicular to the wind direction; z represents the vertical height; H represents the emission height of the pollution source; exp is an exponential function, representing e x , where e is the base of the natural logarithm; S2. Determine the diffusion coefficient σ based on the Pasquill-Gifford stability category. y and σ z The calculation formula is as follows: ; in: x is the downwind distance; a y ,a z These are the initial coefficients for lateral and vertical diffusion; b y ,b z For exponential parameters of lateral and vertical diffusion; S3, Introduction of Correction Factor Based on the turbulence enhancement effect, correction factors α and β are added, and the correction formula is: ； The values ​​of α and β range from 1.1 to 1.5, and are dynamically adjusted according to changes in wind speed and temperature. The CFD model unit, based on computational fluid dynamics, simulates pollution diffusion under complex terrain and unsteady meteorological conditions, specifically including the following steps: S1. Establishment of governing equations mass conservation equation: ; in: ρ is the atmospheric density; t represents time; The rate of change of mass inflow or outflow; For fluid velocity vector; Momentum equation: ; p represents pressure; μ is the dynamic viscosity coefficient; It is the vector of gravitational acceleration; Pollutant transport equations: ; in: C represents the pollutant concentration; For fluid velocity vector; D is the turbulent diffusion coefficient, calculated from the turbulent viscosity coefficient, and its value ranges from 10. -3 -10 -1 m 2 / s S represents the pollution source term, i.e., the emission rate of the pollution source; S2, Using the -k-ϵ turbulence model The parameters are: Turbulent kinetic energy k = 1.5⋅(u′)², where u′ is the turbulence intensity, ranging from 0.1 to 0.3⋅u; Turbulent dissipation rate Where l is the turbulent mixing length, which takes a value of 1-10 m, and C μ C is a constant in the turbulence model. μ =0.09; S3, Mesh Generation Unstructured triangular meshes are used to divide complex terrain; The grid density is increased in regions with high concentration gradients, and the grid size ranges from 0.1 to 10 m. S4. Numerical Solution The finite volume method (FVM) is used to discretize the control equations; Solving pressure-velocity coupling problems using the SIMPLE algorithm; Model switching unit, setting terrain complexity threshold Slope max =15 ∘ And the threshold of wind speed change Δu / Δt = 2m / s 2 ; When the input data meets simple shape and stable meteorological conditions, the Gaussian model unit is enabled; When the input data exceeds the above threshold, it will automatically switch to the CFD model unit; The parameter optimization unit utilizes a deep neural network (DNN) to optimize the diffusion coefficient. The DNN architecture includes: Input layer: Includes 10 input features, including wind speed, wind direction, temperature, and turbulence intensity; Hidden layers: 3 layers, each containing 64 neurons, with ReLU activation function; Output layer: Outputs the optimized diffusion coefficient σ y and σ z ; Training data size: no less than 100,000 pollution event data points, using the Adam optimizer with a learning rate of 0.001; Multi-pollutant synergistic diffusion unit, establishing a chemical reaction model for multi-component pollutants: ； in: NO x It is a nitrogen oxide; VOC stands for volatile organic compounds. O3 is ozone; k is the chemical reaction rate constant; The chemical reaction rate k is dynamically adjusted based on experimental data; Simulated sedimentation rate ranges for different pollutants: PM2.5 (0.01-0.05m / s), SO2 (0.02-0.1m / s).

2. The simulation system for atmospheric pollution diffusion according to claim 1, characterized in that, The data acquisition module includes: The ground-based data acquisition unit uses electrochemical sensors to collect pollutant concentrations through fixed monitoring stations deployed in the target area; The mobile data acquisition unit, equipped with a laser spectral sensor on a drone, collects real-time concentrations of trace pollutants in the air and provides precise spatial location data in conjunction with GPS. The remote sensing acquisition unit, based on satellite remote sensing technology, uses multispectral image processing algorithms to extract atmospheric pollutant concentration distribution information.

3. The simulation system for atmospheric pollution diffusion according to claim 1, characterized in that, The data preprocessing module includes: The data cleaning unit uses a statistical anomaly detection algorithm to remove sensor error data, and at the same time uses a sliding window filtering algorithm to smooth the time series data. The missing value imputation unit uses a spatial interpolation method based on Kriging interpolation and an LSTM deep learning model to predict missing values ​​in time series data. The data fusion unit uses the weighted least squares method to perform spatiotemporal weighted fusion of multi-source data to generate a high-precision initial concentration field.

4. The simulation system for atmospheric pollution diffusion according to claim 1, characterized in that, The simulation calculation module includes: Distributed computing units, based on Hadoop or Spark computing frameworks, divide simulation tasks into multiple small regions for parallel computing; The real-time computing unit, combined with GPU acceleration technology, optimizes the real-time simulation capability of pollutant diffusion through CUDA programming; The adaptive grid division unit dynamically adjusts the grid density based on the changes in pollutant concentration gradient, and concentrates computing resources on regions with high concentration changes.

5. The simulation system for atmospheric pollution diffusion according to claim 1, characterized in that, The visualization module includes: The three-dimensional dynamic display unit is a visualization platform developed based on WebGL and GIS technologies, which renders the three-dimensional distribution of pollutant concentrations in real time. The time-series animation unit uses a front-end framework based on D3.js to dynamically generate time-series animations of the pollutant diffusion process; The pollution source labeling unit locates pollution sources based on a reverse tracing algorithm and marks the location and spread range of pollution sources on a map using a Geographic Information System (GIS).

6. The simulation system for atmospheric pollution diffusion according to claim 1, characterized in that, The decision support module includes: The pollution control recommendation unit analyzes simulation results and generates targeted control measures recommendations based on a multi-objective optimization algorithm. The risk warning unit uses a classification algorithm to classify the pollution risk level of the simulated area and issue warning information. The report generation unit uses automated template generation technology to integrate pollution diffusion paths, risk assessment results, and remediation recommendations into a richly illustrated report.

7. A simulation method for atmospheric pollution diffusion, characterized in that, A simulation system for atmospheric pollution diffusion according to any one of claims 1-6, comprising the following steps: S1. Data Acquisition Air pollution-related data are collected through multi-source acquisition devices, specifically including: S101. Collect pollutant concentrations and meteorological parameters through electrochemical sensors at ground monitoring stations; S102. Collect pollutant concentrations at spatial locations using a laser spectral sensor mounted on a drone; S103. Extract the regional pollutant concentration distribution from multispectral images using satellite remote sensing technology; S2. Data Preprocessing The collected data is processed, specifically including: S201. Data cleaning: smooth time series data based on sliding window filtering algorithm and remove outliers; S202, Data imputation: Kriging interpolation is used to handle missing spatial data, and an LSTM deep learning model is used to complete the missing data of the time series. S203, Data fusion: Ground, mobile, and remote sensing data are fused using the weighted least squares method to generate a high-precision initial concentration field of pollutants; S3. Dynamic Simulation Modeling A dynamic mixing-diffusion model is used to simulate pollutant diffusion, specifically including: S301. Dynamically switch between Gaussian plume model and CFD model based on terrain complexity and meteorological conditions; S302, the Gaussian plume model is used for rapid diffusion calculations under simple shape conditions; The S303 and CFD models, combined with the finite volume method and turbulence model, are used to perform high-precision simulations of diffusion under complex terrain conditions. S304. Introduce deep learning to optimize model parameters, including diffusion coefficient and turbulence mixing parameters; S305. Establish a multi-pollutant co-diffusion model to simulate the chemical reactions and co-diffusion processes between pollutants; S4. Simulation Calculation Solving the diffusion model using a distributed parallel computing framework includes: S401. Divide the simulation area into multiple sub-regions and use the Hadoop or Spark framework for parallel computing. S402. Apply adaptive mesh generation technology in high-concentration gradient regions; S403: Utilizing GPU acceleration technology and CUDA programming to optimize computational speed, it performs real-time pollution diffusion prediction. S5. Results Visualization The simulation results are dynamically visualized, including: S501. Develop a 3D visualization platform using WebGL technology to display the spatial distribution of pollutant concentrations in real time; S502. Based on D3.js, a time-series animation is generated to dynamically present the time evolution process of pollutant diffusion; S503. In the visualization platform, combine GIS to mark the location of pollution sources and their impact range; S6. Decision Support Based on the simulation results, pollution control suggestions and risk warning information are generated, specifically including: S601. Utilize multi-objective optimization algorithms to provide targeted governance recommendations, including pollution source closure and traffic restriction measures; S602. Use the Support Vector Machine (SVM) model to classify pollution risks and issue health protection recommendations. S603. Automatically generate comprehensive reports, including pollutant diffusion path maps, governance recommendations, and health warning information.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the simulation method for atmospheric pollution diffusion as described in claim 7.

9. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the simulation method for atmospheric pollution diffusion as described in claim 7.

Images