Method and system for identifying and classifying atmospheric pollution risk points caused by coal consumption

Abstract

The invention belongs to the technical field of atmospheric pollution cause analysis, and discloses a method and system for identifying and classifying atmospheric pollution risk points caused by coal consumption, and the method comprises the steps: obtaining multi-source data; extracting features of the multi-source data to form a data feature sample, and training the deep learning model by taking the ground monitoring data of the grid point where the data feature sample is located at the current moment as a label; predicting the surface concentration of the atmospheric pollutants by using the trained model; based on a prediction result, calculating a mean value and a standard deviation of the pollutant concentration of each grid point, and screening risk points; and establishing a buffer area by taking the risk point as a center, analyzing POI distribution characteristics in the buffer area, and identifying and classifying the pollution source. According to the method, accurate identification of the atmospheric pollution risk point caused by coal consumption is realized by using the POI point, data support is provided for heavy pollution weather prevention and control, and scientific emission reduction and refined treatment are promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of atmospheric pollution cause analysis, and in particular to a method and system for identifying and classifying atmospheric pollution risk points caused by coal consumption. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The industrial structure dominated by heavy chemical industry, the energy structure dominated by coal, and the transportation structure dominated by road freight have led to a high-risk situation of frequent air pollution. At present and for a long period of time in the future, fossil energy dominated by coal will still occupy a dominant position in the energy structure. The air pollution caused by coal consumption activities cannot be ignored. For example, in the process of coal mining and utilization, a large amount of air pollutants such as SO2, particulate matter, smoke, and dust are emitted. These pollutants will not only cause direct damage to the human respiratory system, but also cause greenhouse effects, acid rain, photochemical smog and haze and other disastrous climates, threatening the natural ecology and public health. Therefore, we should attach great importance to the air pollution caused by coal consumption activities. However, the concentration of air pollutants is affected by many factors, and it is difficult to screen out the air pollution caused by coal consumption. The tracing of air pollution sources is the basis for controlling air pollution caused by coal consumption and formulating coal emission reduction policies. It is urgent to identify the risk points of air pollution caused by coal consumption through technical means and provide means to support the tracing of air pollution sources and control.

[0004] The current methods for analyzing the causes of air pollution mainly include emission inventory method, statistical analysis method, chemical transport method and receptor model method. The emission inventory method systematically collects and organizes emission data from pollution sources, and uses economic activity models and emission factors to comprehensively reflect the emission characteristics and source composition of regional pollutants. However, this method has limitations such as difficulty in data acquisition and long update cycle, and it is difficult to reflect the dynamic changes of short-term pollution, and the spatial resolution is often limited to the urban scale; the statistical analysis method is based on the spatiotemporal distribution characteristics of pollutant concentration data and air quality index (AQI), and uses statistical regression and other methods to identify the causes of pollution. This method is relatively simple to operate, requires less data, and is suitable for preliminary pollution characteristics analysis. However, since the atmospheric pollution process often involves complex nonlinear relationships and multiple interactions, simple statistical regression methods are difficult to accurately characterize these complex relationships. At the same time, due to its reliance on ground monitoring station data, its temporal and spatial coverage is significantly limited; the receptor model method is based on environmental monitoring data and uses mathematical methods such as chemical mass balance and factor analysis to invert the contribution of pollution sources. This method performs well in identifying local pollution sources, but its accuracy depends largely on the quality and representativeness of monitoring data; the chemical transport model method can quantitatively evaluate the contribution of different sources by numerically simulating the physical and chemical processes such as the emission, transmission, and transformation of atmospheric pollutants. This method has a clear physical and chemical mechanism, but the model accuracy is not high, and it is impossible to further improve the accuracy of the model using existing ground observation information. The computing resource requirements are large, and the accuracy of the results is affected by a variety of input data and parameters. In recent years, researchers have proposed analysis methods using new monitoring methods such as characteristic radar maps and lidar maps to identify the causes of pollution based on the characteristics of changes in time series and space of different pollutants. This can achieve long-term or regional-scale atmospheric pollution cause analysis, but it relies on site monitoring data and is difficult to accurately project the spatial distribution characteristics of pollution. In general, traditional methods for analyzing the causes of air pollution have the disadvantages of difficulty in obtaining complete data, strong dependence on data quality, incomplete temporal and spatial coverage, and difficulty in reflecting geographic spatial information. Air pollution caused by coal consumption has the dual characteristics of point sources and surface sources, and its spatial distribution presents complex diversity. In particular, dispersed emissions such as residential coal burning are difficult to effectively capture through fixed monitoring sites due to the randomness and uncertainty of their temporal and spatial distribution. The difficulty of identifying such pollution sources has greatly increased the cost of environmental supervision and law enforcement. At present, there is still a lack of a scientific and systematic method to accurately identify and delineate high-value areas of air pollution caused by coal consumption, which poses a challenge to the precise implementation and effective promotion of pollution prevention and control work.

[0005] With the development of satellite remote sensing technology, the cost of obtaining large-scale, long-time, and spatially continuous remote sensing observation data of pollutants is relatively low. With its powerful nonlinear fitting ability, deep learning algorithms can achieve the remote sensing inversion of pollutant concentrations, which has become an important way to obtain the complete distribution of pollutant concentrations in time and space and realize the analysis of the causes of atmospheric pollution with high temporal and spatial resolution. In addition, the widespread application of POI (Point of Interest) data provides a new idea for the identification of pollution sources. POI data contains rich attribute information such as location name, category, address, etc., which can reflect the characteristics of human activities and land use types in specific areas. Combining POI data with atmospheric pollutant distribution data with complete temporal and spatial coverage, according to the combined characteristics of different pollutant concentrations, a pollution source-receptor relationship based on geographical location can be established, and accurate identification and classification of atmospheric pollution risk points caused by coal consumption can be achieved. This method not only overcomes the limitations of traditional methods in data acquisition and computational efficiency, but also provides higher temporal and spatial resolution, providing more powerful technical support for the analysis of the causes of atmospheric pollution and the prevention and control of severe pollution. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a method and system for identifying and classifying air pollution risk points caused by coal consumption. The Transformer model is used to construct a relationship model between remote sensing data and pollutants, and a spatial distribution data set of air pollutants is generated. The buffer zone is calculated for the identified risk points according to the combination relationship of different pollutant concentrations. POI points are used to accurately identify air pollution risk points caused by coal consumption, provide data support for the prevention and control of heavy pollution weather, and promote scientific emission reduction and refined governance.

[0007] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for identifying and classifying air pollution risk points caused by coal consumption, comprising the following steps: Acquire multi-source data and pre-process them to obtain a multi-source dataset with consistent temporal and spatial resolution; Feature extraction is performed on multi-source data sets to form data feature samples, and the ground monitoring data at the current moment of the grid point where the data feature samples are located is used as a label to train the deep learning model; Use the trained deep learning model to predict the surface concentration of air pollutants and generate a data set of the spatial distribution of air pollutants; Based on the spatial distribution data of air pollutants predicted by the model, the mean and standard deviation of pollutant concentrations at each grid point are calculated according to the time scale, and grid points that meet the set conditions are selected as air pollution risk points caused by coal consumption; Establish a buffer zone with the screened risk points as the center, analyze the POI distribution characteristics within the buffer zone, calculate the density and proportion of different types of POIs, and identify and classify pollution sources.

[0008] As an optional implementation, the multi-source data includes meteorological reanalysis data, ground monitoring data of atmospheric pollutants, remote sensing column concentration data of atmospheric pollutants, digital elevation data and land use data.

[0009] As an optional implementation, the atmospheric pollutants that use deep learning models to predict surface concentrations include SO2, PM 2.5 , O3, NO2 and CO.

[0010] As an optional implementation method, the grid points that meet the set conditions are screened out, specifically: Filter out SO2 concentrations above the mean and exceeding the mean plus one standard deviation, CO concentrations above the mean, PM 2.5 , O3 and NO2 concentrations are between the mean plus one standard deviation and the mean minus one standard deviation.

[0011] As an optional implementation method, the pollution source identification classification criteria are specifically: When the proportion of industrial POIs in the buffer zone is higher than that of other types, the risk point is judged as an industrial source. When urban life POIs dominate, the risk point is judged as a life source.

[0012] As an optional implementation, the deep learning model consists of an input layer, a Transformer module based on spatial attention, a feature mapping layer, a position encoding layer, six hidden layers and an output layer, wherein the hidden layer is composed of a multi-head attention Transformer encoder for learning to extract spatial correlation information between features, and the output layer is composed of two fully connected layers with five output units, corresponding to five concentrations of atmospheric pollutants.

[0013] In a second aspect, the present invention provides a system for identifying and classifying air pollution risk points caused by coal consumption, comprising: The data acquisition module is configured to: acquire multi-source data and perform preprocessing to obtain a multi-source data set with consistent temporal and spatial resolution; The model training module is configured to: extract features from multi-source data sets to form data feature samples, and use the current ground monitoring data of the grid points where the data feature samples are located as labels to train the deep learning model; The model prediction module is configured to: use the trained deep learning model to predict the surface concentration of atmospheric pollutants and generate a spatial distribution dataset of atmospheric pollutants; The risk point identification module is configured to: calculate the mean and standard deviation of pollutant concentrations at each grid point according to the time scale based on the spatial distribution data of air pollutants predicted by the model, and select grid points that meet the set conditions as air pollution risk points caused by coal consumption; The identification and classification module is configured to: establish a buffer zone with the screened risk point as the center, analyze the POI distribution characteristics within the buffer zone, calculate the density and proportion of different types of POIs, and identify and classify pollution sources.

[0014] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in the first aspect is performed.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0016] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method described in the first aspect.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a method and system for identifying and classifying air pollution risk points caused by coal consumption. The method uses surface monitoring data, remote sensing data and meteorological reanalysis data of air pollutants, and uses a deep learning model to learn the nonlinear relationship between surface monitoring data and remote sensing data, so as to achieve spatial continuity, complete spatiotemporal coverage and high accuracy of air pollutant spatial distribution prediction, improve the calculation efficiency, precision and accuracy of the model, calculate the monthly mean value by using the predicted spatial distribution of pollutant concentration, screen the air pollution risk points caused by coal consumption according to the combined characteristics of different pollutant concentrations, and further classify them by using POI information, which makes up for the shortcomings of traditional coal consumption pollution identification methods such as strong data quality dependence, incomplete spatiotemporal coverage and difficulty in reflecting geographic space information. The present invention uses POI points to realize accurate identification of air pollution risk points caused by coal consumption, provide data support for the prevention and control of heavy pollution weather, and promote scientific emission reduction and refined governance. It meets the accuracy and practicality requirements in specific applications and provides an effective solution for the field of air pollution cause analysis.

[0018] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0020] Figure 1 A flow chart of a method for identifying and classifying air pollution risk points caused by coal consumption provided in Example 1 of the present invention; Figure 2 This is a network structure diagram of the Transformer deep learning model provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0021] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0022] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0023] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0025] Example 1 like Figure 1 As shown, this embodiment provides a method for identifying and classifying air pollution risk points caused by coal consumption, comprising the following steps: S1. Acquire multi-source data and preprocess them to obtain a multi-source dataset with consistent temporal and spatial resolution.

[0026] S2. Feature extraction is performed on multi-source data sets to form data feature samples, and the ground monitoring data at the current moment of the grid point where the data feature samples are located is used as a label to train the deep learning model.

[0027] S3. Use the trained deep learning model to predict the surface concentration of atmospheric pollutants and generate a spatial distribution dataset of atmospheric pollutants.

[0028] S4. Based on the spatial distribution data of atmospheric pollutants predicted by the model, the mean and standard deviation of the pollutant concentration at each grid point are calculated according to the time scale, and the grid points that meet the set conditions are screened out as the atmospheric pollution risk points caused by coal consumption.

[0029] S5. Establish a buffer zone with the selected risk points as the center, analyze the POI distribution characteristics within the buffer zone, calculate the density and proportion of different types of POIs, and identify and classify pollution sources.

[0030] The multi-source data include meteorological reanalysis data, ground monitoring data of atmospheric pollutants, remote sensing column concentration data of atmospheric pollutants, digital elevation data (DEM) and land use data.

[0031] Preprocessing of multi-source data: By removing missing values ​​and outliers, resampling and interpolation, the temporal and spatial resolutions of meteorological data, remote sensing data of atmospheric pollutants, DEM and land use data are unified. Specifically, a standard grid with a spatial resolution of 1km*1km is created and stacked into a two-dimensional array to construct a list of geographic coordinates of all grid points. At the same time, feature engineering is used to extract feature information in the temporal and spatial dimensions to form a unified data format.

[0032] A KD tree (K-Dimensional Tree) is created based on the grid longitude and latitude information of the dataset to find the nearest grid point of the air pollution monitoring station, map the surface pollutant data monitored by the station to the grid, and generate a mask with station data to distinguish between grid points with measured data and those that need to be predicted. Finally, a training dataset containing meteorological data, ground monitoring station data of air pollutants, remote sensing data of air pollutants, DEM and land use data and a prediction dataset containing meteorological data, remote sensing data of air pollutants, DEM and land use data are generated.

[0033] In the feature generation process, all environmental variables are first stacked to form a basic feature layer (the basic feature layer is formed by merging and stacking all input variables with the grid row and column relationship preserved), and the surface concentration observations of atmospheric pollutants at the sites mapped to the grid and the site mask are used as additional feature layers. Finally, the calculated spatial encoding is used as an auxiliary feature layer. These feature layers are spliced ​​in the last dimension to form a complete input feature tensor, corresponding to the surface monitoring data of atmospheric pollutant concentration at the current moment as labels for training deep learning models. The training dataset is used to train and verify the model, and the prediction dataset is used for prediction.

[0034] Atmospheric pollutants that use deep learning models to predict surface concentrations include SO2, PM 2.5 , O3, NO2 and CO.

[0035] Use the trained deep learning model to analyze SO2 and PM 2.5 , O3, NO2, and CO surface concentrations are predicted to generate a spatial distribution data set of atmospheric pollutants. Based on the spatial distribution data of atmospheric pollutants predicted by the model, the mean and standard deviation of the pollutant concentration at each grid point are calculated according to the time scale, and the grid points where the SO2 concentration is significantly higher than the mean and exceeds the mean plus one standard deviation, the CO concentration is higher than the mean, and the concentrations of the other three pollutants are within the range of the mean plus one standard deviation and the mean minus one standard deviation are screened out as atmospheric pollution risk points caused by coal consumption.

[0036] In order to further clarify the source of pollution, a buffer zone with a radius of 1 km was established with the screened risk point as the center, and the POI distribution characteristics within the buffer zone were analyzed. By calculating the density and proportion of different types of POIs, the pollution source identification criteria were established: when the proportion of industrial POIs in the buffer zone is significantly higher than that of other types, the risk point is judged as an industrial source; when urban living POIs such as residential areas and commercial areas dominate, they are judged as living sources.

[0037] Analyze the distribution characteristics of POIs in the buffer zone. By screening out pollution-related POIs within the designated buffer zone and classifying them according to their source information, the distribution characteristics of POIs can be analyzed. The specific method is as follows: 1. POI density calculation method: Divide the number of relevant POI points in the buffer by the area of ​​the buffer to get the POI density. The calculation formula is: ; This density value can be used as a reference for judging the possibility of high-value points in the buffer zone. The density index can be used as a reference for the degree of concentration of spatial distribution. High-density areas usually indicate that the spatial agglomeration of such POIs is strong and can be considered as potential areas of high-value points, but areas with lower density still need to be comprehensively judged in combination with other factors and cannot be directly excluded.

[0038] 2. Calculation method of POI ratio: Divide the number of different types of POI points by the total number of POI points to get the proportion of each type of source. The calculation formula is:

[0039] According to the proportion results, the source type with the highest proportion is selected as the dominant emission source of the buffer zone.

[0040] Optional meteorological reanalysis data include: 10m wind speed, 2m dew point temperature, 2m temperature, ground pressure, total precipitation, boundary layer height, surface net solar radiation, total cloud cover, etc.; remote sensing data include: SO2 remote sensing column concentration data, atmospheric aerosol thickness (AOD), O3 remote sensing column concentration data, NO2 remote sensing column concentration data, CO remote sensing column concentration data; surface monitoring data of atmospheric pollutants include: SO2 surface concentration monitoring data, O3 surface concentration monitoring data, NO2 surface concentration monitoring data, CO surface concentration monitoring data, PM 2.5 Surface concentration monitoring data.

[0041] Optionally, the time and space information extracted by the feature engineering includes: spatial position information and Julian day. The calculation formula of the spatial position information is: ; In the formula, is the longitude, is the latitude, It is the spatial location information.

[0042] Optionally, the pre-trained deep learning model is a Transformer regression prediction neural network based on a self-attention mechanism, which is used for spatial prediction of pollutant concentrations.

[0043] Optional, such as Figure 2 As shown in the figure, the pre-trained deep learning model consists of an input layer, a Transformer module based on spatial attention, a feature mapping layer, a position encoding layer, six hidden layers and an output layer. The hidden layer is composed of an 8-head attention Transformer encoder for learning to extract spatial correlation information between features; the output layer is composed of 2 fully connected layers with 5 output units, corresponding to 5 concentrations of atmospheric pollutants.

[0044] Optionally, the spatial attention-based Transformer module calculates the average and maximum values ​​of the channel dimensions of the feature map, and then generates spatial attention weights using a 7×7 convolution kernel and a sigmoid function after connection to highlight key spatial areas.

[0045] Optionally, the feature mapping layer of the model normalizes input features through linear transformation and LayerNorm; the position encoding layer generates position-aware information using sine and cosine functions.

[0046] Optionally, the model uses dropout=0.1 for regularization during training to prevent overfitting, and dynamically adjusts the learning rate through ReduceLROnPlateau, automatically reducing the learning rate when the validation loss does not decrease within 5 consecutive epochs. In addition, the model supports DistributedDataParallel to implement distributed training, and uses mixed precision training (AMP) to improve training efficiency.

[0047] Optionally, the model uses the GELU function as the activation function: ; The loss is trained using the mean square error loss function (MSE): ; In the formula, is the model prediction value, is the true value, is the sample size.

[0048] Optionally, the model predicts the pollutant concentration using the coefficient of determination The determination coefficient is calculated as follows: ; In the formula, For two copies, is the true value, is the predicted value, is the mean of the true values, is the mean of the predicted values, is the standard deviation of the true value, is the standard deviation of the predicted values.

[0049] Optionally, the POI information calls the Amap POI data interface to obtain the POI information in the buffer, which mainly includes industrial POIs such as industrial parks and factories, and urban life POIs such as residential areas and commercial areas.

[0050] Example 2 This embodiment provides a system for identifying and classifying air pollution risk points caused by coal consumption, including: The data acquisition module is configured to: acquire multi-source data and perform preprocessing to obtain a multi-source data set with consistent temporal and spatial resolution; The model training module is configured to: extract features from multi-source data sets to form data feature samples, and use the current ground monitoring data of the grid points where the data feature samples are located as labels to train the deep learning model; The model prediction module is configured to: use the trained deep learning model to predict the surface concentration of atmospheric pollutants and generate a spatial distribution dataset of atmospheric pollutants; The risk point identification module is configured to: calculate the mean and standard deviation of pollutant concentrations at each grid point according to the time scale based on the spatial distribution data of air pollutants predicted by the model, and select grid points that meet the set conditions as air pollution risk points caused by coal consumption; The identification and classification module is configured to: establish a buffer zone with the screened risk point as the center, analyze the POI distribution characteristics within the buffer zone, calculate the density and proportion of different types of POIs, and identify and classify pollution sources.

[0051] It should be noted that the above modules correspond to the steps described in Example 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above Example 1. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer executable instructions.

[0052] In further embodiments, there is also provided: An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in Embodiment 1 is performed. For the sake of brevity, it will not be described in detail here.

[0053] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0054] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0055] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in Example 1 is completed.

[0056] The method in Example 1 can be directly embodied as a hardware processor, or a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it is not described in detail here.

[0057] A computer program product includes a computer program, and when the computer program is executed by a processor, the method described in embodiment 1 is implemented.

[0058] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer executable instructions, such as instructions included in a program module, which are executed in a device on a real or virtual processor of the target to perform the process / method as described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of program modules can be combined or divided between program modules as needed. Machine executable instructions for program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0059] The computer program code for implementing the method of the present invention can be written in one or more programming languages. These computer program codes can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the computer or other programmable data processing device, causes the function / operation specified in the flow chart and / or block diagram to be implemented. The program code can be executed completely on a computer, partially on a computer, as an independent software package, partially on a computer and partially on a remote computer or completely on a remote computer or server.

[0060] In the context of the present invention, computer program codes or related data may be carried by any appropriate carrier to enable a device, apparatus or processor to perform the various processes and operations described above. Examples of carriers include signals, computer readable media, and the like. Examples of signals may include electrical, optical, radio, acoustic or other forms of propagation signals, such as carrier waves, infrared signals, and the like.

[0061] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0062] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for identifying and classifying air pollution risk points caused by coal consumption, characterized in that: The following steps are involved: Acquire multi-source data and pre-process them to obtain a multi-source dataset with consistent temporal and spatial resolution; Feature extraction is performed on multi-source data sets to form data feature samples, and the ground monitoring data at the current moment of the grid point where the data feature samples are located is used as a label to train the deep learning model; Use the trained deep learning model to predict the surface concentration of air pollutants and generate a data set of the spatial distribution of air pollutants; Based on the spatial distribution data of air pollutants predicted by the model, the mean and standard deviation of pollutant concentrations at each grid point are calculated according to the time scale, and grid points that meet the set conditions are selected as air pollution risk points caused by coal consumption; Establish a buffer zone with the screened risk points as the center, analyze the POI distribution characteristics within the buffer zone, calculate the density and proportion of different types of POIs, and identify and classify pollution sources.

2. A method for identifying and classifying air pollution risk points caused by coal consumption as claimed in claim 1, characterized in that: The multi-source data include meteorological reanalysis data, ground monitoring data of atmospheric pollutants, remote sensing column concentration data of atmospheric pollutants, digital elevation data and land use data.

3. A method for identifying and classifying air pollution risk points caused by coal consumption as claimed in claim 1, characterized in that: Atmospheric pollutants that use deep learning models to predict surface concentrations include SO2, PM 2.5 , O3, NO2 and CO.

4. A method for identifying and classifying air pollution risk points caused by coal consumption as claimed in claim 3, characterized in that: Filter out the grid points that meet the set conditions, specifically: Filter out SO2 concentrations above the mean and exceeding the mean plus one standard deviation, CO concentrations above the mean, PM 2.5 , O3 and NO2 concentrations are between the mean plus one standard deviation and the mean minus one standard deviation.

5. The method for identifying and classifying air pollution risk points caused by coal consumption as claimed in claim 1, characterized in that: The pollution source identification and classification criteria are as follows: When the proportion of industrial POIs in the buffer zone is higher than that of other types, the risk point is judged as an industrial source. When urban life POIs dominate, the risk point is judged as a life source.

6. A method for identifying and classifying air pollution risk points caused by coal consumption as claimed in claim 1, characterized in that: The deep learning model consists of an input layer, a Transformer module based on spatial attention, a feature mapping layer, a position encoding layer, six hidden layers and an output layer, wherein the hidden layer is composed of a multi-head attention Transformer encoder for learning to extract spatial correlation information between features; the output layer consists of two fully connected layers with five output units, corresponding to five concentrations of atmospheric pollutants.

7. A system for identifying and classifying air pollution risk points caused by coal consumption, characterized in that: include: The data acquisition module is configured to: acquire multi-source data and perform preprocessing to obtain a multi-source data set with consistent temporal and spatial resolution; The model training module is configured to: extract features from multi-source data sets to form data feature samples, and use the current ground monitoring data of the grid points where the data feature samples are located as labels to train the deep learning model; The model prediction module is configured to: use the trained deep learning model to predict the surface concentration of atmospheric pollutants and generate a spatial distribution dataset of atmospheric pollutants; The risk point identification module is configured to: calculate the mean and standard deviation of the pollutant concentration at each grid point according to the time scale based on the spatial distribution data of atmospheric pollutants predicted by the model, and select the grid points that meet the set conditions as the atmospheric pollution risk points caused by coal consumption; The identification and classification module is configured to: establish a buffer zone with the screened risk point as the center, analyze the POI distribution characteristics within the buffer zone, calculate the density and proportion of different types of POIs, and identify and classify pollution sources.

8. An electronic device, characterized in that: The method comprises a memory and a processor and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 6 is completed.

9. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the method described in any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images