GIS-big data-based atmospheric environment management and control partition delimiting method and system

Abstract

The invention relates to an atmospheric environment management and control partition delimiting method and system based on GIS-big data, and the method comprises the steps: obtaining and processing ground monitoring data, satellite remote sensing data and meteorological data of a target region, constructing a pollutant concentration prediction model, and predicting the future pollutant concentration of the target region through the pollutant concentration prediction model; the diffusion and settlement processes of pollutants are simulated through the processed meteorological data and the topographic data of the target area, and a pollutant dynamic distribution diagram is constructed in combination with future pollutant concentration; a thermal inversion layer phenomenon is detected in the pollutant dynamic distribution diagram, and a pollutant accumulation area is marked; and according to the pollutant dynamic distribution map and the pollutant accumulation area, defining the boundary of the atmospheric environment management and control subarea by combining the ecological sensitive area, the industrial pollution source and the densely populated area of the target area. According to the method, time-space fusion of multi-source heterogeneous data can be realized, the pollutant concentration estimation precision is improved, and powerful support is provided for fine monitoring and scientific management and control of atmospheric pollution.

Description

Technical Field

[0001] The present invention relates to the technical fields of big data and environmental management, and particularly to a method and system for delimiting atmospheric environment control zones based on GIS-big data. Background Art

[0002] In the process of delimiting atmospheric environment control zones, there is a technical problem: how to accurately integrate multi-source heterogeneous data and solve its spatio-temporal scale inconsistency to ensure the scientificity and rationality of the zone boundaries. Specifically, satellite remote sensing data has the advantages of large-scale coverage and high spatio-temporal resolution, but its data accuracy is greatly affected by factors such as clouds and aerosols, and it is difficult to directly reflect the true concentration of ground pollutants; although the data of ground monitoring stations has high accuracy, the site distribution is sparse, and it is difficult to comprehensively cover complex terrain and landform areas. Especially in mountainous areas, river valleys and other areas with complex terrain, the data missing problem is particularly prominent. In addition, there are spatio-temporal scale differences between meteorological data and terrain data. Meteorological data is usually presented in a grid form, while terrain data exists in vector or raster form, and it is difficult to directly match their spatial resolutions.

[0003] In the data processing stage, due to the different time sampling frequencies of different data sources, for example, satellite remote sensing data may be updated once a day or a week, while the data of ground monitoring stations may be updated once an hour, how to effectively align these data with different time scales becomes a major technical difficulty. At the same time, the diffusion and settlement processes of atmospheric pollutants are comprehensively affected by terrain and meteorological conditions. For example, the inversion layer phenomenon in valley areas will exacerbate pollutant accumulation, while in flat areas, pollutants may spread rapidly due to the action of wind. Therefore, how to comprehensively consider these dynamic factors in the process of zone delimitation to avoid unreasonable zoning due to data deviation or model error is a key problem to be solved urgently.

[0004] In addition, the requirements of environmental protection plans and policies and regulations are often macroscopic and guiding. For example, the delimitation of priority protection areas needs to comprehensively consider multiple factors such as ecologically sensitive areas, while the delimitation of key control areas needs to combine specific indicators such as population density areas, industrial pollution source distribution, traffic flow, and diffusion conditions. How to ensure that the zoning results not only conform to scientific laws but also meet the constraints of policies and regulations in the data-driven zoning process is a complex business scenario problem. If this problem cannot be effectively solved, it may greatly reduce the practicality and operability of the zoning results, thereby affecting the overall effect of atmospheric environment management. Therefore, the present invention proposes a method and system for delimiting atmospheric environment control zones based on GIS-big data. Summary of the Invention

[0005] The object of the present invention is to provide a method and system for delimiting atmospheric environment control zones based on GIS-big data in view of the above technical problems, realizing the spatio-temporal fusion of multi-source heterogeneous data, improving the estimation accuracy of pollutant concentrations, and providing strong support for refined monitoring and scientific control of air pollution.

[0006] To achieve the above object, on the one hand, the present invention provides a method for delimiting atmospheric environment control zones based on GIS-big data, including:

[0007] Obtaining ground monitoring data, satellite remote sensing data, and meteorological data of the target area and processing them;

[0008] Constructing a pollutant concentration prediction model based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, and predicting the future pollutant concentrations of the target area through the pollutant concentration prediction model;

[0009] Simulating the diffusion and settlement processes of pollutants through the processed meteorological data and the topographic data of the target area, and constructing a pollutant dynamic distribution map in combination with the future pollutant concentrations;

[0010] In the pollutant dynamic distribution map, detecting the inversion layer phenomenon in combination with the processed meteorological data, and marking the pollutant accumulation areas;

[0011] According to the pollutant dynamic distribution map and the pollutant accumulation areas, in combination with the ecological sensitive areas, industrial pollution sources, and densely populated areas of the target area, delimiting the boundaries of the atmospheric environment control zones based on a preset zoning threshold.

[0012] On the other hand, the present invention also provides a system for delimiting atmospheric environment control zones based on GIS-big data, including:

[0013] A pollution data acquisition module for obtaining ground monitoring data, satellite remote sensing data, and meteorological data of the target area and processing them;

[0014] A pollution concentration prediction module for constructing a pollutant concentration prediction model based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, and predicting the future pollutant concentrations of the target area through the pollutant concentration prediction model;

[0015] A pollution distribution construction module for simulating the diffusion and settlement processes of pollutants through the processed meteorological data and the topographic data of the target area, and constructing a pollutant dynamic distribution map in combination with the future pollutant concentrations;

[0016] A pollution accumulation marking module for detecting the inversion layer phenomenon in the pollutant dynamic distribution map in combination with the processed meteorological data, and marking the pollutant accumulation areas;

[0017] A control partition delimitation module, configured to delimit the boundary of the atmospheric environment control partition based on a preset partition threshold according to the pollutant dynamic distribution map and the pollutant accumulation area, in combination with the ecological sensitive areas, industrial pollution sources, and population dense areas in the target area.

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

[0019] The present invention processes ground monitoring data through Kriging interpolation, combines satellite remote sensing data and meteorological data to obtain a high-precision pollutant concentration distribution; uses the Lagrangian particle diffusion model to simulate the pollutant diffusion process under complex terrain, combines the temperature gradient method to detect the inversion layer phenomenon, and marks the pollutant accumulation area; finally, delimits the atmospheric environment control partition according to the pollutant distribution and the distributions of ecological sensitive areas, industrial pollution sources, and population dense areas. The present invention realizes the spatio-temporal fusion of multi-source heterogeneous data, improves the accuracy of pollutant concentration estimation, and provides strong support for refined monitoring and scientific control of air pollution. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a flowchart of a method for delimiting an atmospheric environment control partition based on GIS-big data according to an embodiment of the present invention;

[0022] Figure 2 It is a schematic structural diagram of a system for delimiting an atmospheric environment control partition based on GIS-big data according to an embodiment of the present invention. Detailed Embodiments

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

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

[0025] On the one hand, this embodiment provides a method for delimiting an atmospheric environment control partition based on GIS-big data, as Figure 1As shown in the figure, it includes:

[0026] Obtain the ground monitoring data, satellite remote sensing data, and meteorological data of the target area and process them;

[0027] Build a pollutant concentration prediction model based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, and predict the future pollutant concentration of the target area through the pollutant concentration prediction model;

[0028] Simulate the diffusion and settlement process of pollutants through the processed meteorological data and the terrain data of the target area, and construct a pollutant dynamic distribution map in combination with the future pollutant concentration;

[0029] In the pollutant dynamic distribution map, detect the inversion layer phenomenon in combination with the processed meteorological data, and mark the pollutant accumulation area;

[0030] According to the pollutant dynamic distribution map and the pollutant accumulation area, in combination with the ecological sensitive areas, industrial pollution sources, and population dense areas of the target area, delimit the boundaries of the atmospheric environment control zones based on preset zoning thresholds.

[0031] Specifically, in this embodiment, the ground monitoring data is interpolated by Kriging interpolation, combined with satellite remote sensing data and meteorological data to obtain a high-precision pollutant concentration distribution; and the Lagrangian particle diffusion model is used to simulate the pollutant diffusion process under complex terrain, combined with the temperature gradient method to detect the inversion layer phenomenon and mark the pollutant accumulation area; finally, according to the pollutant distribution, as well as the distribution of ecological sensitive areas, industrial pollution sources, and population dense areas, the atmospheric environment control zones are delimited. The present invention realizes the spatio-temporal fusion of multi-source heterogeneous data, improves the accuracy of pollutant concentration estimation, and provides strong support for the refined monitoring and scientific control of air pollution.

[0032] Furthermore, obtaining the ground monitoring data, satellite remote sensing data, and meteorological data of the target area and processing them includes:

[0033] Perform interpolation processing on the ground monitoring data by using the Kriging interpolation algorithm;

[0034] Perform calibration processing on the satellite remote sensing data by using the MODIS cloud calibration model and the AERONET aerosol calibration model, and perform denoising processing on the calibrated satellite remote sensing data;

[0035] Perform downscaling processing on the meteorological data by using the bilinear interpolation resampling technique;

[0036] Perform time dimension matching on the processed ground monitoring data, satellite remote sensing data, and meteorological data by using the dynamic time warping algorithm to obtain a fusion data set.

[0037] Specifically, in this embodiment, the Kriging interpolation algorithm is used to interpolate the ground monitoring data, which includes: obtaining the pollutant concentration data and geographical coordinate information of the ground monitoring stations; dividing the spatial domain according to the geographical coordinate information to determine the spatial distribution range of each monitoring point; analyzing the spatial correlation between the monitoring points by using the variogram and calculating the variogram parameters; calculating the weight values of the Kriging interpolation algorithm according to the variogram parameters and the monitoring point data; generating a prediction point grid in the spatial domain, applying the Kriging interpolation algorithm to each prediction point, converting the pollutant concentration value of the prediction point into a spatial distribution map, and generating a global pollutant concentration distribution map.

[0038] For example, twelve monitoring points are set in Chaoyang District, Beijing, and the concentration data of pollutants such as sulfur dioxide and nitrogen oxides in the atmosphere are collected. At the same time, the longitude and latitude coordinate information of each monitoring point is recorded. For example, the Chaoyang Park monitoring station is located at 40.02 degrees north latitude and 116.48 degrees east longitude. The Chaoyang District is divided into 100×100 grids by the Thiessen polygon method, and each grid point is used as a prediction point. The variogram analysis is carried out on the monitoring data in Chaoyang District, and the spatial correlation of pollutant concentration is determined by calculating parameters such as the sill value, nugget value, and range of the variogram. For example, the sill value of the sulfur dioxide concentration variogram in a certain sub-region 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 for the prediction point are calculated. The monitoring points closer to the prediction point are given larger weights. For example, the weight of a monitoring point 1 kilometer away is 0.4, while the weight of a monitoring point 3 kilometers away drops to 0.1. For each prediction point, the pollutant concentration value of this point is calculated according to the concentration values and weight coefficients of the surrounding monitoring points. 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 the satellite remote sensing data, and the denoising process of the corrected satellite remote sensing data includes: obtaining the satellite remote sensing data, extracting the cloud information and aerosol information, correcting the cloud information by using the MODIS cloud correction model, correcting the aerosol information by using the AERONET aerosol correction model, and obtaining the corrected remote sensing data. According to the corrected remote sensing data, a denoising algorithm is used to denoise the remote sensing data to generate the denoised remote sensing data, and the ground pollutant concentration information in the denoised remote sensing data is extracted to generate the estimated value of the ground pollutant concentration.

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

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

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

[0043] Meteorological grid data usually records the atmospheric state in the form of regular grid division, such as elements like temperature, humidity, and air pressure. After obtaining the meteorological grid data, its resolution information needs to be extracted, and this information is usually included in the metadata of the data file. Terrain raster data is a digital representation of the surface elevation, and the resolution of the commonly used digital elevation model is more refined, such as the digital elevation model with a resolution of 30 meters. 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 the weighted average of the surrounding four known points. The weight coefficient is determined by the distance from the target point to the known point, and the closer the distance, the greater the weight. Downscaling is an important technical means to improve spatial resolution. In the downscaling of meteorological data, in addition to considering spatial interpolation, the influence of terrain factors also needs to be considered. Taking temperature data as an example, in mountainous areas with complex terrain, the temperature decreases with the increase in altitude, about 0.6 degrees per 100 meters of ascent. By introducing elevation information for downscaling, a more realistic spatial distribution of temperature can be obtained.

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

[0045] Specifically, time series feature extraction is an important processing step for satellite remote sensing data, ground monitoring data, and meteorological data. Satellite remote sensing data is usually obtained at regular time intervals, such as daily or every eight days, and its features include vegetation indices, surface temperature, etc.; ground monitoring data may be continuously collected in hours or minutes, recording parameters such as air quality, surface reflectance, etc.; meteorological data covers elements such as temperature and precipitation, and has fixed observation time points.

[0046] The dynamic time warping algorithm calculates the time deviation between different data sources. Taking the vegetation growth monitoring of satellite remote sensing data and ground monitoring as an example, the satellite overpass time may be 10 am every day, while the ground station may have records every hour. By calculating the time deviation, data with different observation frequencies can be aligned to the same time point. For example, the data at 9:30 am and 10:30 am at the ground monitoring station can find the observation value closest to the satellite overpass time through time warping. Time dimension adjustment is to solve the problem of time mismatch of multi-source data. The three types of data can be aligned to the same time point. Taking air pollution monitoring as an example, the aerosol optical depth data obtained by satellite remote sensing, the particulate matter concentration data at the ground air quality monitoring station, and the wind speed and direction data at the meteorological station can analyze the pollutant transmission law on the same time scale after time dimension adjustment. This kind of fusion not only ensures the time consistency of the data, but also provides multi-dimensional environmental monitoring information, which helps to improve the accuracy and reliability of the analysis results.

[0047] Furthermore, constructing a pollutant concentration prediction model 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, the random forest algorithm is used for training to construct the pollutant concentration prediction model. Among them, in the training process, grid search is used to optimize the model parameters, and cross-validation is used to evaluate the model performance.

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

[0050] During the training process, grid search is used to optimize the model parameters. The range of the number of decision trees is set from one hundred to five hundred, and the maximum depth of the tree is from five to fifteen to find the optimal parameter combination. Five-fold cross-validation is used to evaluate the model performance. The data set is randomly divided into five parts, four of which are used for training and one for validation. After five cycles, the average performance index is taken.

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

[0052] Combining the topographic data of the target area and the processed meteorological data, the Lagrangian particle diffusion model is used to simulate the diffusion and sedimentation processes of the pollutants under the terrain of the target area;

[0053] Align and combine the future pollutant concentrations with the diffusion and sedimentation processes of the pollutants on the time scale to construct the dynamic distribution map of the pollutants.

[0054] Specifically, in this embodiment, the time series features of the topographic data and the meteorological data are first obtained to generate the first basic data and the second basic data; according to the Lagrangian particle diffusion model, combining the first basic data and the second basic data, the diffusion process of pollutants under complex terrain is simulated to generate a diffusion simulation result; on the basis of the diffusion simulation result, the sedimentation process of pollutants under complex terrain is simulated to generate a sedimentation simulation result.

[0055] The time series features of the topographic data mainly include information such as elevation data, slope, and aspect. The meteorological data includes wind speed, wind direction, temperature, and humidity. The Lagrangian particle diffusion model describes the diffusion process of pollutants by simulating the movement trajectories of a large number of particles. In a complex terrain environment, the blocking and guiding effects of the terrain on the airflow need to be considered. Taking a valley area as an example, when pollutants diffuse from a high place to a low place, they will be blocked by the mountain and accumulate in the valley, forming an area with a relatively high pollutant concentration. The pollutant sedimentation process is divided into two forms: dry sedimentation and wet sedimentation. Dry sedimentation is mainly affected by gravity. For example, the sedimentation speed of particulate matter in still air is related to the particle size. The sedimentation speed of particulate matter with a particle size of ten microns is about 0.3 cm per second. Wet sedimentation is closely related to the precipitation process. When the rainfall intensity is 10 mm per hour, the pollutant concentration in the air can be reduced by about 30%.

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

[0057] The vertical temperature distribution in the processed meteorological data is analyzed by using the temperature gradient method, and the temperature gradient value is calculated;

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

[0059] According to the spatial coordinates, the inversion layer phenomenon and the corresponding pollutant accumulation areas are marked in the dynamic pollutant distribution map, and the marked dynamic pollutant distribution map is obtained.

[0060] Specifically, in this embodiment, the temperature gradient method is used to analyze the vertical temperature distribution information in the meteorological data, calculate the temperature gradient value, judge whether there is an inversion layer phenomenon. If there is an inversion layer, the pollutant accumulation areas are identified, the spatial coordinates of these areas are obtained, and the inversion layer and its corresponding pollutant accumulation areas are marked in the dynamic pollutant distribution map to generate a marked distribution map.

[0061] The temperature gradient method is mainly used to analyze the law of vertical temperature change in the atmosphere, and the atmospheric stability is determined by the temperature change per 100-meter height. Under normal circumstances, as the height increases, the temperature gradually decreases, and the vertical temperature gradient is negative. When an inversion layer appears, the temperature rises with the increase of height, and the vertical temperature gradient is positive. For example, in the meteorological observation of a certain area, the surface temperature is 20 degrees, the temperature at 100-meter height is 22 degrees, and the temperature at 200-meter height is 23 degrees, indicating a typical inversion layer phenomenon.

[0062] When identifying the pollutant accumulation areas, the terrain and meteorological conditions need to be combined. Taking a valley area as an example, when an inversion layer appears over the valley, the cold air is trapped at the bottom of the valley, forming a similar lid effect, which makes it difficult for pollutants to diffuse upward. Through spatial coordinate positioning, it can be determined that the area is a valley at an altitude of 500 meters, the height of the inversion layer is between 700 meters and 900 meters, and the pollutants mainly accumulate within this range. When marking the inversion layer area, the layered marking method is used, and the inversion layers at different heights are represented by different colors. For example, in the pollutant distribution map of a certain city, the inversion layer below 600 meters is marked in red, the inversion layer between 600 meters and 800 meters is marked in yellow, and the inversion layer above 800 meters is marked in green, intuitively showing the spatial distribution characteristics of the inversion layer.

[0063] Further, according to the dynamic pollutant distribution map and the pollutant accumulation areas, combined with the ecological sensitive areas, industrial pollution sources and population dense areas in the target area, the boundaries of the atmospheric environment control zones are delimited based on the preset zoning thresholds, including:

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

[0065] Obtain the spatial distribution data of the ecological sensitive areas, industrial pollution sources and densely populated areas in the target area, and construct a spatial overlay analysis model in combination with the spatial coordinates;

[0066] In the spatial overlay analysis model, divide the boundaries of the atmospheric environment control zones according to the preset pollutant concentration thresholds and ecological protection priorities, and obtain the pollutant sources and diffusion paths within each control zone to generate a map of the boundaries of the atmospheric environment control zones.

[0067] On the other hand, this embodiment provides a system for delimiting atmospheric environment control zones based on GIS-big data, as Figure 2 shown, including:

[0068] A pollution data acquisition module, configured to acquire and process ground monitoring data, satellite remote sensing data, and meteorological data of the target area;

[0069] A pollution concentration prediction module, configured to construct a pollutant concentration prediction model based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, and predict the future pollutant concentration of the target area through the pollutant concentration prediction model;

[0070] A pollution distribution construction module, configured to simulate the diffusion and settlement processes of pollutants through the processed meteorological data and the topographic data of the target area, and construct a dynamic distribution map of pollutants in combination with the future pollutant concentration;

[0071] A pollution accumulation marking module, configured to detect the inversion layer phenomenon in the dynamic distribution map of pollutants in combination with the processed meteorological data, and mark the pollutant accumulation areas;

[0072] A control zone delimitation module, configured to delimit the boundaries of the atmospheric environment control zones based on the dynamic distribution map of pollutants and the pollutant accumulation areas, in combination with the ecological sensitive areas, industrial pollution sources and densely populated areas in the target area, based on a preset zoning threshold.

[0073] The above-described embodiments are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for delimiting atmospheric environment control zones based on GIS-big data, characterized in that Including: Obtain the ground monitoring data, satellite remote sensing data, and meteorological data of the target area and process them; Build a pollutant concentration prediction model based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, and predict the future pollutant concentration of the target area through the pollutant concentration prediction model; Simulate the diffusion and sedimentation process of pollutants through the processed meteorological data and the terrain data of the target area, and build a pollutant dynamic distribution map in combination with the future pollutant concentration; In the pollutant dynamic distribution map, detect the inversion layer phenomenon in combination with the processed meteorological data, and mark the pollutant accumulation area; According to the pollutant dynamic distribution map and the pollutant accumulation area, in combination with the ecological sensitive areas, industrial pollution sources, and densely populated areas of the target area, delimit the boundaries of the atmospheric environment control zones based on the preset zoning threshold.

2. The method for delimiting an atmospheric environment control area based on GIS-big data according to claim 1, wherein Obtaining the ground monitoring data, satellite remote sensing data, and meteorological data of the target area and processing them includes: Interpolate the ground monitoring data using the Kriging interpolation algorithm; Correct the satellite remote sensing data using the MODIS cloud correction model and the AERONET aerosol correction model, and denoise the corrected satellite remote sensing data; Downscale the meteorological data using the bilinear interpolation resampling technique; Match the processed ground monitoring data, satellite remote sensing data, and meteorological data in the time dimension using the dynamic time warping algorithm to obtain a fusion dataset.

3. The method for delimiting the atmospheric environment control area based on GIS-big data according to claim 2, characterized in that Matching the processed ground monitoring data, satellite remote sensing data, and meteorological data in the time dimension using the dynamic time warping algorithm to obtain a fusion dataset includes: Extract the time series features of the processed ground monitoring data, satellite remote sensing data, and meteorological data respectively; Using the dynamic time warping algorithm, calculate 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; Based on the time deviation values, adjust the time series of the processed ground monitoring data, satellite remote sensing data, and meteorological data in the time dimension respectively to obtain the adjusted ground monitoring data, satellite remote sensing data, and meteorological data, and build the fusion dataset.

4. The method for demarcating an atmospheric environment control area based on GIS-big data according to claim 1, wherein, Building a pollutant concentration prediction model based on the processed ground monitoring data, satellite remote sensing data, and meteorological data includes: Based on the processed ground monitoring data, satellite remote sensing data, and meteorological data, train using the random forest algorithm to build the pollutant concentration prediction model, where grid search is used to optimize the model parameters and cross-validation is used to evaluate the model performance during the training process.

5. The method for delimiting atmospheric environment control zones based on GIS-big data according to claim 1, characterized in that, Simulating the diffusion and sedimentation process of pollutants through the processed meteorological data and the terrain data of the target area, and building a pollutant dynamic distribution map in combination with the future pollutant concentration includes: Combining the terrain data of the target area and the processed meteorological data, use the Lagrangian particle diffusion model to simulate the diffusion and sedimentation process of the pollutants under the terrain of the target area; Align and combine the future pollutant concentration with the diffusion and sedimentation processes of the pollutant on a time scale to construct the dynamic distribution map of the pollutant.

6. The method for demarcating an atmospheric environment control area based on GIS-big data according to claim 1, wherein In the dynamic distribution map of the pollutant, detect the inversion layer phenomenon by combining the processed meteorological data, and mark the pollutant accumulation areas, including: Analyze the vertical temperature distribution in the processed meteorological data using the temperature gradient method, and calculate the temperature gradient value; Judge the inversion layer phenomenon based on the temperature gradient value, identify the pollutant accumulation areas in the dynamic distribution map of the pollutant according to the inversion layer phenomenon, and obtain the spatial coordinates of the pollutant accumulation areas; Mark the inversion layer phenomenon and the corresponding pollutant accumulation areas in the dynamic distribution map of the pollutant according to the spatial coordinates to obtain the marked dynamic distribution map of the pollutant.

7. The method for delimiting the atmospheric environment control area based on GIS-big data according to claim 1, characterized in that According to the dynamic distribution map of the pollutant and the pollutant accumulation areas, combine the ecological sensitive areas, industrial pollution sources and population dense areas in the target area, and delimit the boundaries of the atmospheric environment control zones based on the preset zoning thresholds, including: Extract the spatial coordinates of all pollutant accumulation areas in the marked dynamic distribution map of the pollutant; Obtain the spatial distribution data of the ecological sensitive areas, industrial pollution sources and population dense areas in the target area, and construct a spatial overlay analysis model in combination with the spatial coordinates; In the spatial overlay analysis model, divide the boundaries of the atmospheric environment control zones according to the preset pollutant concentration thresholds and ecological protection priorities, and obtain the pollutant sources and diffusion paths within each control zone to generate the boundary map of the atmospheric environment control zones.

8. An atmospheric environment control zoning delineation system based on GIS-big data, characterized in that, Including: A pollution data acquisition module for acquiring and processing the ground monitoring data, satellite remote sensing data and meteorological data of the target area; A pollution concentration prediction module for constructing a pollutant concentration prediction model based on the processed ground monitoring data, satellite remote sensing data and meteorological data, and predicting the future pollutant concentration of the target area through the pollutant concentration prediction model; A pollution distribution construction module for simulating the diffusion and sedimentation processes of pollutants through the processed meteorological data and the topographic data of the target area, and constructing a dynamic distribution map of pollutants in combination with the future pollutant concentration; A pollution accumulation marking module for detecting the inversion layer phenomenon by combining the processed meteorological data in the dynamic distribution map of the pollutant and marking the pollutant accumulation areas; A control zone delimitation module for delimiting the boundaries of the atmospheric environment control zones based on the dynamic distribution map of the pollutant and the pollutant accumulation areas, combining the ecological sensitive areas, industrial pollution sources and population dense areas in the target area, and based on the preset zoning thresholds.

Images