A method and system for atmospheric environmental management and control zoning based on GIS and big data

Abstract

This invention relates to a method and system for delineating atmospheric environmental control zones based on GIS-big data, comprising: acquiring and processing ground monitoring data, satellite remote sensing data, and meteorological data of a target area; constructing a pollutant concentration prediction model; and predicting future pollutant concentrations in the target area using the pollutant concentration prediction model; simulating the diffusion and deposition processes of pollutants using processed meteorological data and topographic data of the target area, and constructing a dynamic distribution map of pollutants based on future pollutant concentrations; detecting temperature inversion phenomena in the dynamic distribution map of pollutants and marking pollutant accumulation areas; and delineating the boundaries of atmospheric environmental control zones based on the dynamic distribution map of pollutants and pollutant accumulation areas, combined with ecologically sensitive areas, industrial pollution sources, and densely populated areas of the target area. This invention enables the spatiotemporal fusion of multi-source heterogeneous data, improves the accuracy of pollutant concentration estimation, and provides strong support for refined monitoring and scientific management of air pollution.

Description

Technical Field

[0001] This invention relates to the fields of big data and environmental management technology, and in particular to a method and system for delineating atmospheric environmental control zones based on GIS-big data. Background Technology

[0002] A key technical challenge in delineating atmospheric environmental control zones is accurately integrating multi-source heterogeneous data and resolving spatiotemporal scale inconsistencies to ensure the scientific validity and rationality of zone boundaries. Specifically, while satellite remote sensing data offers advantages in terms of wide coverage and high spatiotemporal resolution, its accuracy is significantly affected by factors such as clouds and aerosols, making it difficult to directly reflect the true concentration of ground-based pollutants. Ground-based monitoring station data, although highly accurate, is sparsely distributed, failing to comprehensively cover complex terrain areas, particularly in mountainous regions and valleys where data gaps are particularly pronounced. Furthermore, there are spatiotemporal scale differences between meteorological and topographical data; meteorological data is typically presented in grid format, while topographical data exists in vector or raster form, making direct matching of spatial resolution difficult.

[0003] During the data processing phase, the different sampling frequencies of various data sources—for example, satellite remote sensing data may be updated daily or weekly, while ground monitoring station data may be updated hourly—make effective alignment of these data at different time scales a major technical challenge. Simultaneously, the diffusion and deposition of atmospheric pollutants are influenced by a combination of topography and meteorological conditions. For instance, temperature inversions in valleys can exacerbate pollutant accumulation, while wind can cause rapid dispersion of pollutants in flat areas. Therefore, comprehensively considering these dynamic factors during zoning to avoid unreasonable boundary demarcation due to data bias or model errors is a critical issue that urgently needs to be addressed.

[0004] Furthermore, environmental protection plans and policies often have macro-level and guiding requirements. For example, the delineation of priority protection zones needs to comprehensively consider multiple factors, such as ecologically sensitive areas, while the delineation of key control zones needs to combine specific indicators such as densely populated areas, industrial pollution source distribution, traffic flow, and diffusion conditions. Ensuring that the zoning results conform to both scientific principles and policy constraints during the data-driven zoning process is a complex operational problem. Failure to effectively address this issue may significantly reduce the practicality and operability of the zoning results, thereby affecting the overall effectiveness of atmospheric environmental management. Therefore, this invention proposes a GIS-big data-based method and system for atmospheric environmental control zoning. Summary of the Invention

[0005] The purpose of this invention is to address the aforementioned technical problems by providing a method and system for atmospheric environmental management and control zoning based on GIS-big data, thereby achieving spatiotemporal fusion of multi-source heterogeneous data, improving the accuracy of pollutant concentration estimation, and providing strong support for refined monitoring and scientific management of air pollution.

[0006] To achieve the above objectives, on the one hand, the present invention provides a method for delineating atmospheric environmental management zones based on GIS-big data, comprising:

[0007] Acquire and process ground monitoring data, satellite remote sensing data, and meteorological data for the target area;

[0008] A pollutant concentration prediction model is constructed based on processed ground monitoring data, satellite remote sensing data, and meteorological data, and the future pollutant concentration in the target area is predicted using the pollutant concentration prediction model.

[0009] The diffusion and deposition process of pollutants is simulated using processed meteorological data and topographic data of the target area, and a dynamic distribution map of pollutants is constructed by combining the future pollutant concentration.

[0010] In the dynamic distribution map of pollutants, the inversion layer phenomenon is detected by combining the processed meteorological data, and the areas where pollutants accumulate are marked.

[0011] Based on the dynamic distribution map of pollutants and the areas where pollutants accumulate, and taking into account the ecologically sensitive areas, industrial pollution sources, and densely populated areas of the target region, the boundaries of the atmospheric environmental control zones are delineated based on preset zoning thresholds.

[0012] On the other hand, the present invention also provides an atmospheric environment management and control zoning system based on GIS-big data, comprising:

[0013] The pollution data acquisition module is used to acquire and process ground monitoring data, satellite remote sensing data, and meteorological data of the target area.

[0014] The pollution concentration prediction module is used to construct a pollutant concentration prediction model based on processed ground monitoring data, satellite remote sensing data, and meteorological data, and to predict the future pollutant concentration in the target area through the pollutant concentration prediction model.

[0015] The pollution distribution construction module is used to simulate the diffusion and deposition process of pollutants using processed meteorological data and topographic data of the target area, and to construct a dynamic distribution map of pollutants by combining the future pollutant concentration.

[0016] The pollution accumulation marking module is used to detect temperature inversion phenomena and mark the pollutant accumulation area in the pollutant dynamic distribution map by combining processed meteorological data.

[0017] The control zone delineation module is used to delineate the boundaries of atmospheric environmental control zones based on the pollutant dynamic distribution map and pollutant accumulation areas, combined with the ecologically sensitive areas, industrial pollution sources and densely populated areas of the target area, and based on preset zoning thresholds.

[0018] The beneficial effects of this invention are as follows:

[0019] This invention uses Kriging interpolation to process ground monitoring data, combined with satellite remote sensing data and meteorological data, to obtain high-precision pollutant concentration distribution. It then uses a Lagrange particle diffusion model to simulate pollutant diffusion processes under complex terrain, and combines this with the temperature gradient method to detect temperature inversion phenomena, marking pollutant accumulation areas. Finally, based on the distribution of pollutants, as well as the distribution of ecologically sensitive areas, industrial pollution sources, and densely populated areas, atmospheric environmental control zones are delineated. This invention achieves spatiotemporal fusion of multi-source heterogeneous data, improves the accuracy of pollutant concentration estimation, and provides strong support for refined monitoring and scientific management of air pollution. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of an atmospheric environment management and control zoning method based on GIS-big data according to an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of an atmospheric environment management and zoning system based on GIS-big data, according to an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of 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.

[0024] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] On the one hand, this embodiment provides a method for delineating atmospheric environmental control zones based on GIS-big data, such as... Figure 1As shown, it includes:

[0026] Acquire and process ground monitoring data, satellite remote sensing data, and meteorological data for the target area;

[0027] A pollutant concentration prediction model is constructed based on processed ground monitoring data, satellite remote sensing data, and meteorological data, and the future pollutant concentration in the target area is predicted using the pollutant concentration prediction model.

[0028] The diffusion and deposition process of pollutants is simulated using processed meteorological data and topographic data of the target area, and a dynamic distribution map of pollutants is constructed by combining the future pollutant concentration.

[0029] In the dynamic distribution map of pollutants, the inversion layer phenomenon is detected by combining the processed meteorological data, and the areas where pollutants accumulate are marked.

[0030] Based on the dynamic distribution map of pollutants and the areas where pollutants accumulate, and taking into account the ecologically sensitive areas, industrial pollution sources, and densely populated areas of the target region, the boundaries of the atmospheric environmental control zones are delineated based on preset zoning thresholds.

[0031] Specifically, this embodiment uses Kriging interpolation to process ground monitoring data, combined with satellite remote sensing data and meteorological data, to obtain high-precision pollutant concentration distribution. It then uses a Lagrange particle diffusion model to simulate the pollutant diffusion process under complex terrain, and combines the temperature gradient method to detect temperature inversion phenomena, marking pollutant accumulation areas. Finally, based on the pollutant distribution, as well as the distribution of ecologically sensitive areas, industrial pollution sources, and densely populated areas, atmospheric environmental control zones are delineated. This invention achieves spatiotemporal fusion of multi-source heterogeneous data, improves the accuracy of pollutant concentration estimation, and provides strong support for refined monitoring and scientific management of air pollution.

[0032] Furthermore, acquiring and processing ground monitoring data, satellite remote sensing data, and meteorological data for the target area includes:

[0033] The ground monitoring data were interpolated using the Kriging interpolation algorithm.

[0034] The satellite remote sensing data were corrected using the MODIS cloud correction model and the AERONET aerosol correction model, and then the corrected satellite remote sensing data were denoised.

[0035] The meteorological data were downscaled using bilinear interpolation resampling technology.

[0036] A dynamic time warping algorithm is used to match the time dimension of processed ground monitoring data, satellite remote sensing data, and meteorological data to obtain a fused dataset.

[0037] Specifically, in this embodiment, the Kriging interpolation algorithm is used to interpolate ground monitoring data, including: acquiring pollutant concentration data and geographic coordinate information of ground monitoring stations; dividing the spatial domain according to the geographic coordinate information to determine the spatial distribution range of each monitoring point; using a variogram to analyze the spatial correlation between monitoring points and calculating the variogram parameters; calculating the weight values ​​of the Kriging interpolation algorithm based on the variogram parameters and monitoring point data; generating a grid of prediction points in the spatial domain; applying the Kriging interpolation algorithm to each prediction point to convert the pollutant concentration values ​​of the prediction points into a spatial distribution map, thereby generating a global pollutant concentration distribution map.

[0038] For example, twelve monitoring stations were set up in Chaoyang District, Beijing, to collect data on the concentrations of pollutants such as sulfur dioxide and nitrogen oxides in the atmosphere. The latitude and longitude coordinates of each monitoring station were also recorded; for instance, the Chaoyang Park monitoring station is located at 40.02 degrees North latitude and 116.48 degrees East longitude. Chaoyang District was divided into 100x100 grids using the Thiessen polygon method, with each grid point serving as a prediction point. Variation function analysis was performed on the monitoring data from Chaoyang District, and the spatial correlation of pollutant concentrations was determined by calculating parameters such as the sill value, nugget value, and range of the variation function. For example, the spatial correlation of pollutant concentrations in a certain sub-region was analyzed. The sill value of the sulfur oxide concentration variation function is 0.6, the nugget value is 0.1, and the range is 4 kilometers. Based on these parameters, the weight coefficients of different monitoring points to the prediction point are calculated. Monitoring points closer to the prediction point are given a larger weight. For example, the weight of a monitoring point one kilometer away is 0.4, while the weight of a monitoring point three kilometers away is reduced to 0.1. For each prediction point, the pollutant concentration value at that point is calculated based on the concentration values ​​of surrounding monitoring points and the weight coefficients. By visualizing the concentration values ​​of the prediction points, a pollutant concentration distribution map is generated, which intuitively shows the spatial distribution characteristics of pollutants.

[0039] In this embodiment, the MODIS cloud correction model and the AERONET aerosol correction model are used to correct satellite remote sensing data, and the corrected satellite remote sensing data is then denoised. This includes: acquiring satellite remote sensing data; extracting cloud and aerosol information; correcting the cloud information using the MODIS cloud correction model; and correcting the aerosol information using the AERONET aerosol correction model, resulting in corrected remote sensing data. Based on the corrected remote sensing data, a denoising algorithm is used to denoise the remote sensing data, generating denoised remote sensing data. Ground pollutant concentration information is then extracted from the denoised remote sensing data to generate estimated ground pollutant concentrations.

[0040] Clouds and aerosols can interfere with remote sensing data. The MODIS cloud correction model corrects spectral reflectance values ​​by identifying cloud type and thickness, while the AERONET aerosol correction model corrects remote sensing data based on aerosol optical thickness and particle size distribution. For stripe noise and random noise in remote sensing images, wavelet transform denoising methods can be used. Taking remote sensing monitoring of industrial areas as an example, the noise signal intensity in the original data can reach 20% of the signal itself, which can be reduced to below 5% after wavelet denoising.

[0041] Estimating ground-based pollutant concentrations requires establishing a remote sensing inversion model. By analyzing spectral characteristics and atmospheric transport patterns, the concentrations of pollutants such as nitrogen dioxide and particulate matter can be estimated. In monitoring of an industrial area, based on a corrected atmospheric optical thickness of 0.5, the relative error between the inverted particulate matter concentration and the measured value from the ground station was within 15%.

[0042] In this embodiment, the bilinear interpolation resampling technique is used to downscale meteorological data, including: acquiring gridded meteorological data and extracting its spatial resolution information; acquiring rasterized terrain data and extracting its spatial resolution information; comparing the spatial resolution differences between meteorological data and terrain data; resampling the meteorological data using bilinear interpolation; and adjusting the spatial resolution of the meteorological data using a downscaling algorithm.

[0043] Meteorological gridded data typically records atmospheric conditions such as temperature, humidity, and air pressure using a regular grid. After acquiring meteorological grid data, its resolution information needs to be extracted; this information is usually contained in the metadata of the data file. Topographic raster data is a digital representation of surface elevation. Commonly used digital elevation models (DEMs) offer more refined resolution, typically a 30-meter resolution DEM. Bilinear interpolation is a commonly used spatial data resampling method. Taking meteorological grid data as an example, if the original data resolution is 5 kilometers and needs to be adjusted to 1 kilometer resolution, the value of the new grid point is estimated by weighted averaging of four surrounding known points. The weighting coefficient is determined by the distance from the target point to the known points; the closer the distance, the greater the weight. Downscaling is an important technique for improving spatial resolution. In meteorological data downscaling, in addition to considering spatial interpolation, the influence of topographic factors also needs to be considered. Taking temperature data as an example, in mountainous areas with complex terrain, the temperature decreases with increasing altitude, decreasing by approximately 0.6 degrees Celsius for every 100 meters of elevation gain. By incorporating elevation information for downscaling, a more realistic spatial distribution of temperature can be obtained.

[0044] In this embodiment, a dynamic time warping algorithm is used to match the time dimension of processed ground monitoring data, satellite remote sensing data, and meteorological data to obtain a fused dataset. This includes: extracting the time series features of the processed ground monitoring data, satellite remote sensing data, and meteorological data respectively; using the dynamic time warping algorithm, calculating the time deviation values ​​between the processed ground monitoring data and the processed satellite remote sensing data and meteorological data based on the time series features; and adjusting the time dimension of the time series of the processed ground monitoring data, satellite remote sensing data, and meteorological data based on the time deviation values ​​to obtain the adjusted ground monitoring data, satellite remote sensing data, and meteorological data, and constructing a fused dataset.

[0045] Specifically, time series feature extraction is a crucial processing step for satellite remote sensing data, ground monitoring data, and meteorological data. Satellite remote sensing data is typically acquired at regular time intervals, such as daily or every eight days, and its features include vegetation indices and surface temperature. Ground monitoring data may be collected continuously on an hourly or minute-by-minute basis, recording parameters such as air quality and surface reflectance. Meteorological data covers elements such as temperature and precipitation, and has fixed observation time points.

[0046] Dynamic time warping algorithms calculate time deviations between different data sources. Taking satellite remote sensing data and ground-based vegetation growth monitoring as an example, the satellite's transit time might be 10:00 AM daily, while ground stations might record data hourly. By calculating the time deviation, data from different observation frequencies can be aligned to a unified time point. For instance, data from a ground monitoring station at 9:30 AM and 10:30 AM can be compared using time warping to find the observation closest to the satellite's transit time. Time dimension adjustment addresses the time mismatch problem of multi-source data, aligning three types of data to the same time point. Taking air pollution monitoring as an example, aerosol optical thickness data acquired by satellite remote sensing, particulate matter concentration data from ground-based air quality monitoring stations, and wind speed and direction data from meteorological stations, after time dimension adjustment, can be analyzed on the same time scale to understand pollutant transport patterns. This fusion ensures data temporal consistency and provides multi-dimensional environmental monitoring information, helping to improve the accuracy and reliability of the analysis results.

[0047] Furthermore, the pollutant concentration prediction model constructed based on the processed ground monitoring data, satellite remote sensing data, and meteorological data includes:

[0048] Based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, a random forest algorithm is used to train and construct the pollutant concentration prediction model. During the training process, grid search is used to optimize model parameters, and cross-validation is used to evaluate model performance.

[0049] Specifically, in this embodiment, when constructing the prediction model using the random forest algorithm, the fused data is used as the feature input. The features include aerosol optical thickness retrieved from remote sensing, historical concentration values ​​from ground monitoring stations, and meteorological elements such as wind speed and direction, temperature, and humidity.

[0050] During training, grid search was used to optimize model parameters, with the number of decision trees ranging from 100 to 500 and the maximum tree depth from 5 to 15, to find the optimal parameter combination. Cross-validation used the five-fold method to evaluate model performance, randomly dividing the dataset into five parts, four for training and one for validation, and then repeating the process five times before taking the average performance metric.

[0051] Furthermore, the diffusion and deposition processes of pollutants are simulated using processed meteorological data and topographic data of the target area, and a dynamic distribution map of pollutants is constructed by combining the future pollutant concentrations, including:

[0052] By combining the topographic data of the target area and the processed meteorological data, a Lagrange particle diffusion model is used to simulate the diffusion and deposition process of the pollutants under the topography of the target area.

[0053] By aligning and combining the future pollutant concentration with the diffusion and deposition processes of the pollutants on a time scale, a dynamic distribution map of the pollutants is constructed.

[0054] Specifically, this implementation first acquires the time-series characteristics of topographic and meteorological data to generate first and second basic data; based on the Lagrange particle diffusion model, combined with the first and second basic data, it simulates the diffusion process of pollutants under complex terrain and generates diffusion simulation results; based on the diffusion simulation results, it simulates the sedimentation process of pollutants under complex terrain and generates sedimentation simulation results.

[0055] The time-series characteristics of topographic data mainly include information such as elevation, slope, and aspect, while meteorological data includes wind speed, wind direction, temperature, and humidity. The Lagrange particle diffusion model describes the diffusion process of pollutants by simulating the trajectories of a large number of particles. In complex terrain environments, the obstruction and guidance effects of terrain on airflow need to be considered. Taking a valley area as an example, when pollutants diffuse from high to low altitudes, they are blocked by mountains and accumulate in the valley, forming areas with high pollutant concentrations. Pollutant deposition processes are divided into two forms: dry deposition and wet deposition. Dry deposition is mainly affected by gravity; for example, the deposition velocity of particulate matter in still air is related to particle size, with particles with a diameter of ten micrometers settling at a velocity of approximately 0.3 centimeters per second. Wet deposition is closely related to precipitation processes; a rainfall intensity of ten millimeters per hour can reduce the concentration of pollutants in the air by about 30%.

[0056] Furthermore, in the pollutant dynamic distribution map, the inversion layer phenomenon is detected by combining the processed meteorological data, and the pollutant accumulation areas are marked as follows:

[0057] The temperature gradient method was used to analyze the vertical temperature distribution in the processed meteorological data and to calculate the temperature gradient value.

[0058] Based on the temperature gradient value, an inversion layer phenomenon is determined. Based on the inversion layer phenomenon, pollutant accumulation areas are identified in the pollutant dynamic distribution map, and the spatial coordinates of the pollutant accumulation areas are obtained.

[0059] The inversion layer phenomenon and the corresponding pollutant accumulation area are marked on the pollutant dynamic distribution map according to the spatial coordinates, and the marked pollutant dynamic distribution map is obtained.

[0060] Specifically, this embodiment uses the temperature gradient method to analyze the vertical temperature distribution information in meteorological data, calculate the temperature gradient value, determine whether there is a temperature inversion layer, and if there is a temperature inversion layer, identify the pollutant accumulation area, obtain the spatial coordinates of these areas, mark the temperature inversion layer and its corresponding pollutant accumulation area in the pollutant dynamic distribution map, and generate the marked distribution map.

[0061] The temperature gradient method is mainly used to analyze the vertical temperature variation of the atmosphere, determining atmospheric stability by measuring temperature changes per 100 meters of altitude. Under normal circumstances, temperature gradually decreases with increasing altitude, resulting in a negative vertical temperature gradient. However, when a temperature inversion layer is present, temperature increases with altitude, resulting in a positive vertical temperature gradient. For example, in meteorological observations of a certain region, a surface temperature of 20 degrees Celsius, 22 degrees Celsius at 100 meters altitude, and 23 degrees Celsius at 200 meters altitude indicate the presence of a typical temperature inversion layer.

[0062] When identifying areas where pollutants accumulate, it is necessary to consider both topography and meteorological conditions. Taking a valley as an example, when a temperature inversion layer forms over the valley, cold air is trapped at the bottom, creating a "bowl-lid effect" that hinders the upward dispersion of pollutants. Spatial coordinates can pinpoint the location as a valley at an altitude of 500 meters, with the inversion layer between 700 and 900 meters in height; pollutants primarily accumulate within this range. A stratified marking method is used when marking inversion layer areas, using different colors to represent inversion layers at different altitudes. For instance, in a city's pollutant distribution map, inversion layers below 600 meters are marked in red, those between 600 and 800 meters in yellow, and those above 800 meters in green, visually demonstrating the spatial distribution characteristics of the inversion layers.

[0063] Furthermore, based on the pollutant dynamic distribution map and pollutant accumulation areas, and in conjunction with the ecologically sensitive areas, industrial pollution sources, and densely populated areas of the target region, the boundaries of the atmospheric environmental control zones are delineated based on preset zoning thresholds, including:

[0064] Extract the spatial coordinates of all pollutant accumulation areas from the marked pollutant dynamic distribution map;

[0065] Acquire spatial distribution data of ecologically sensitive areas, industrial pollution sources, and densely populated areas in the target region, and construct a spatial overlay analysis model based on the spatial coordinates;

[0066] In the spatial overlay analysis model, the boundaries of atmospheric environmental control zones are delineated based on preset pollutant concentration thresholds and ecological protection priorities, and the sources and diffusion paths of pollutants within each control zone are obtained to generate an atmospheric environmental control zone boundary map.

[0067] On the other hand, this embodiment provides an atmospheric environment management and control zoning system based on GIS-big data, such as... Figure 2 As shown, it includes:

[0068] The pollution data acquisition module is used to acquire and process ground monitoring data, satellite remote sensing data, and meteorological data of the target area.

[0069] The pollution concentration prediction module is used to construct a pollutant concentration prediction model based on processed ground monitoring data, satellite remote sensing data, and meteorological data, and to predict the future pollutant concentration in the target area through the pollutant concentration prediction model.

[0070] The pollution distribution construction module is used to simulate the diffusion and deposition process of pollutants using processed meteorological data and topographic data of the target area, and to construct a dynamic distribution map of pollutants by combining the future pollutant concentration.

[0071] The pollution accumulation marking module is used to detect temperature inversion phenomena and mark the pollutant accumulation area in the pollutant dynamic distribution map by combining processed meteorological data.

[0072] The control zone delineation module is used to delineate the boundaries of atmospheric environmental control zones based on the pollutant dynamic distribution map and pollutant accumulation areas, combined with the ecologically sensitive areas, industrial pollution sources and densely populated areas of the target area, and based on preset zoning thresholds.

[0073] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A GIS-big data-based atmospheric environment management and control zoning method, characterized in that, The method comprises the following steps: acquiring ground monitoring data, satellite remote sensing data and meteorological data of a target area and processing the data; constructing a pollutant concentration prediction model based on the processed ground monitoring data, satellite remote sensing data and meteorological data, and predicting future pollutant concentration of the target area through the pollutant concentration prediction model; simulating the diffusion and deposition process of pollutants through the processed meteorological data and terrain data of the target area, and combining the future pollutant concentration to construct a pollutant dynamic distribution map; in the pollutant dynamic distribution map, detecting the inversion layer phenomenon combined with the processed meteorological data, and marking the pollutant accumulation area; in the pollutant dynamic distribution map, detecting the inversion layer phenomenon combined with the processed meteorological data, and marking the pollutant accumulation area comprises: analyzing and processing the temperature vertical distribution in the processed meteorological data by using the temperature gradient method, and calculating the temperature gradient value; judging the inversion layer phenomenon based on the temperature gradient value, identifying the pollutant accumulation area in the pollutant dynamic distribution map according to the inversion layer phenomenon, and obtaining the spatial coordinates of the pollutant accumulation area; marking the inversion layer phenomenon and the corresponding pollutant accumulation area in the pollutant dynamic distribution map according to the spatial coordinates, and obtaining the marked pollutant dynamic distribution map; based on the pollutant dynamic distribution map and the pollutant accumulation area, combining the ecological sensitive area, industrial pollution source and population dense area of the target area, and dividing the boundary of atmospheric environmental control partition based on the preset partition threshold. 2.The GIS-big data based atmospheric environment management partitioning method according to claim 1, characterized in that, The method comprises the following steps: using the Kriging interpolation algorithm to perform interpolation processing on the ground monitoring data; using the MODIS cloud correction model and the AERONET aerosol correction model to perform correction processing on the satellite remote sensing data, and performing denoising processing on the corrected satellite remote sensing data; using the bilinear interpolation resampling technology to perform downscaling processing on the meteorological data; using the dynamic time warping algorithm to perform time dimension matching on the processed ground monitoring data, satellite remote sensing data and meteorological data, and obtaining a fusion data set. 3.The GIS-big data based atmospheric environmental management partitioning method according to claim 2, characterized in that, The method comprises the following steps: extracting the time sequence features of the processed ground monitoring data, satellite remote sensing data and meteorological data respectively; using the dynamic time warping algorithm, calculating the time deviation values of the processed ground monitoring data, satellite remote sensing data and meteorological data based on the time sequence features respectively; based on the time deviation values, adjusting the time sequence of the processed ground monitoring data, satellite remote sensing data and meteorological data in the time dimension respectively, obtaining the adjusted ground monitoring data, satellite remote sensing data and meteorological data, and constructing the fusion data set. 4.The GIS-big data based atmospheric environmental management partitioning and delineation method according to claim 1, characterized in that, The method comprises the following steps: based on the processed ground monitoring data, satellite remote sensing data and meteorological data, constructing a pollutant concentration prediction model comprises: The pollution concentration prediction model is constructed by training a random forest algorithm based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, wherein model parameter optimization is performed by grid search and model performance evaluation is performed by cross-validation during the training process. 5.The GIS-big data based atmospheric environmental management partitioning and delineation method according to claim 1, characterized in that, The pollution dynamic distribution map is constructed by simulating the diffusion and deposition process of the pollutants through the processed meteorological data and the topographic data of the target area, and combining the future pollution concentration. The diffusion and deposition process of the pollutants in the topography of the target area is simulated by using a Lagrangian particle diffusion model in combination with the topographic data of the target area and the processed meteorological data. The pollution dynamic distribution map is constructed by aligning and combining the future pollution concentration with the diffusion and deposition process of the pollutants in the time scale. 6.The GIS-big data based atmospheric environmental management partitioning and delineation method according to claim 1, characterized in that, The boundaries of the atmospheric environmental control zoning are delineated based on preset zoning thresholds in combination with the ecological sensitive areas, industrial pollution sources, and densely populated areas of the target area according to the pollution dynamic distribution map and the pollution accumulation area. The spatial coordinates of all pollution accumulation areas are extracted from the marked pollution dynamic distribution map. The spatial distribution data of the ecological sensitive areas, industrial pollution sources, and densely populated areas of the target area are obtained, and a spatial overlay analysis model is constructed in combination with the spatial coordinates. In the spatial overlay analysis model, the boundaries of the atmospheric environmental control zoning are divided according to the preset pollution concentration threshold and ecological protection priority, and the pollution sources and diffusion paths in each control zoning are obtained to generate an atmospheric environmental control zoning boundary map.

7. A GIS-big data-based atmospheric environmental management and control zoning system for implementing the method of any one of claims 1-6, characterized in that, The pollution data acquisition module is used to acquire and process ground monitoring data, satellite remote sensing data, and meteorological data of the target area. The pollution concentration prediction module is used to construct a pollution concentration prediction model based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, and to predict the future pollution concentration of the target area through the pollution concentration prediction model. The pollution distribution construction module is used to simulate the diffusion and deposition process of the pollutants through the processed meteorological data and the topographic data of the target area, and to construct a pollution dynamic distribution map in combination with the future pollution concentration. The pollution accumulation marking module is used to mark the pollution accumulation area in the pollution dynamic distribution map in combination with the processed meteorological data to detect the inversion layer phenomenon. The control zoning delineation module is used to delineate the boundaries of the atmospheric environmental control zoning based on preset zoning thresholds in combination with the ecological sensitive areas, industrial pollution sources, and densely populated areas of the target area according to the pollution dynamic distribution map and the pollution accumulation area. ​

Images