Atmospheric pollutant detection method and system based on multi-source data analysis

Abstract

The invention discloses an atmospheric pollutant detection method and system based on multi-source data analysis. The method comprises the following steps: acquiring hyperspectral data, environmental parameters and remote sensing images of pollutants; carrying out feature separation on a spectrum overlapping region by a multi-component decomposition method based on Gaussian distribution, matching a pre-stored pollution spectrum library, and determining a pollutant type and a concentration range; eliminating interference signals in the hyperspectral data through an atmospheric interference model to obtain pure data; inputting the environmental parameters, the pollutant information and the pure data into a pollutant diffusion model, performing layer overlay analysis in combination with a remote sensing image, and identifying a pollution hot spot area; performing abnormal point identification on the hot spot region based on the pure data, and positioning a pollution source; analyzing the time sequence of the spectrum data of the pollution source, and optimizing a diffusion model in combination with environmental parameters; and finally, pollutant types, concentration ranges, hot spot areas, pollution source positions and time characteristics are output, and rapid and accurate space-time monitoring of the atmospheric pollutants is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of air pollutant monitoring, and in particular to an air pollutant detection method and system based on multi-source data analysis. Background Art

[0002] Traditional methods for monitoring atmospheric pollutants mainly rely on a single data source, such as ground monitoring stations or satellite remote sensing data. Although these methods can provide basic information on pollutant concentrations to a certain extent, they are difficult to meet the increasingly complex pollution monitoring needs due to their inherent limitations, such as insufficient spatial coverage of ground monitoring stations and limited spatiotemporal resolution of satellite remote sensing data. In addition, interference from factors such as meteorological conditions and terrain features further reduces the monitoring accuracy and reliability of traditional methods. With the rapid development of big data, artificial intelligence and the Internet of Things, multi-source data fusion technology has shown significant advantages in the field of atmospheric pollution monitoring. This technology can effectively make up for the shortcomings of a single data source by integrating multi-source information such as ground monitoring stations, satellite remote sensing, drone monitoring, meteorological data and social media, and provide more comprehensive, accurate and real-time pollutant monitoring results. Multi-source data fusion technology can not only improve the spatiotemporal coverage and accuracy of pollutant monitoring, but also deeply explore the sources of pollutants, diffusion laws and their correlation with meteorological conditions through big data analysis and machine learning algorithms, thereby providing a scientific basis for pollution control and early warning.

[0003] In the method of monitoring air pollutants with a single data source at a ground monitoring station, several representative locations are first selected in cities or industrial areas to deploy fixed air pollution monitoring stations. Each monitoring station is equipped with a variety of sensors for real-time monitoring of the concentrations of pollutants such as PM2.5, PM10, SO2, NO2, CO, and O3 in the air. The data collected by the sensors is transmitted to the data center via a wired or wireless network, and the data center preprocesses the received raw data, including removing outliers, filling missing values, and data standardization. The processed data is integrated with the geographic location information of the monitoring station to generate a time series of air pollutant concentrations at a specific site. Then, the data center expands the discrete site data into a spatial distribution map of pollutants in the entire monitoring area through interpolation methods or statistical models, such as Kriging interpolation or inverse distance weighted interpolation. Finally, the system regularly updates and publishes a wide range of air pollution status reports for query and reference by relevant departments and the public.

[0004] Due to the limited spatial coverage of the single data source of ground monitoring stations, it is difficult to capture the changes in pollutants outside the monitoring area. In addition, the complex terrain, uneven distribution of monitoring stations, atmospheric background interference and the influence of dynamic environmental parameters have led to sparse data in local areas, which makes the spatial distribution map of pollutant concentration based on ground monitoring stations have large deviations, limiting its application effect in large-scale fine monitoring and precise pollution tracing. Therefore, the existing technology cannot avoid the influence of atmospheric background interference and dynamic environmental parameters, and can quickly and accurately monitor atmospheric pollutants in terms of spatiotemporal characteristics. Summary of the invention

[0005] The present invention provides an atmospheric pollutant detection method and system based on multi-source data analysis, so as to realize rapid and accurate monitoring of atmospheric pollutants in terms of temporal and spatial characteristics by combining the influence of atmospheric background interference and dynamic environmental parameters.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides an atmospheric pollutant detection method based on multi-source data analysis, comprising: Obtain hyperspectral data, environmental parameters and remote sensing images of pollutants in the atmosphere, where environmental parameters include aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity; According to the hyperspectral data, a multi-component decomposition method based on Gaussian distribution is used to separate the characteristics of the spectral overlapping area to obtain the spectral characteristics of the pollutants; According to the spectral characteristics, the spectral characteristics are matched with a pre-stored pollution spectrum library to obtain the type of pollutants and the range of pollutant concentrations; According to the pre-built atmospheric interference model and the environmental parameters, interference signals are removed from the hyperspectral data to obtain pure data; Input the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model, and perform layer overlay analysis in combination with the remote sensing image to obtain the pollution hotspot area; Identify abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source; Performing time series analysis on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions, and optimizing the pollutant diffusion model in combination with the environmental parameters; The pollutant type, the pollutant concentration range, the pollution hotspot area, the pollution source location and the time characteristics are output as the results of atmospheric pollutant detection.

[0007] In an optional embodiment, the method of using a multi-component decomposition method based on Gaussian distribution to separate the characteristics of the spectral overlapping area according to the hyperspectral data to obtain the spectral characteristics of the pollutant includes: Converting the hyperspectral data into a Gaussian function form to obtain Gaussian data; Performing Fourier transformation on the Gaussian data to obtain frequency domain data decomposed into different frequencies; Performing inverse Fourier transform on each frequency domain data to obtain wavelength domain data of different wavelengths; Calculate the mean square error between the decomposed spectral signal and the mixed signal according to the wavelength domain data; Calculating the spectral matching degree according to the wavelength domain data and the preset standard data, and comparing the spectral matching degree with a preset spectral matching threshold value, if the spectral matching degree is less than the preset spectral matching threshold value, adjusting the Gaussian function parameters with the goal of minimizing the mean square error; If the spectral matching degree is greater than a preset spectral matching threshold, the spectral characteristics of the pollutant are obtained; Among them, the hyperspectral data is converted into Gaussian function form by the following formula: The mean square error is calculated by the following formula: The spectral matching degree is calculated by the following formula: in, represents hyperspectral data, Indicates The amplitude of a Gaussian function, Indicates The central wavelength, represents the standard deviation of the hyperspectral data, represents the Gaussian function component, represents the mean square error, The wavelength is The wavelength domain data of Indicates the number of wavelength domain data, express The contamination signal is at wavelength The wavelength domain data at express The contamination signal is at wavelength Standard data, represents the spectral matching degree, and e is a natural constant.

[0008] In an optional implementation, the matching of the spectral features with a pre-stored pollution spectrum library to obtain the pollutant type and pollutant concentration range includes: Using wavelet transform to perform denoising on the spectral features to obtain denoised data; Extracting characteristic points and characteristic lines according to the denoised data, and matching them with a preset pollution spectrum library to obtain pollutant types; Calculate the pollution concentration according to the denoised data and the pollution spectrum library to obtain a pollutant concentration range; Among them, the characteristic points and characteristic lines are calculated by the following formula: Among them, the pollutant concentration range is calculated by the following formula: in, Represents feature points, represents the characteristic line, represents the wavelength, represents the denoised data, and Indicates the starting wavelength and ending wavelength of the absorption peak. Indicates the pollutant concentration range, The wavelength in the contamination spectrum library is Reference data, represents the maximum wavelength, Indicates the preset molar absorptivity, represents the optical path length, The wavelength is The denoised data, Represents the constraint condition, taking Wavelength As a feature point .

[0009] In an optional implementation, removing interference signals from the hyperspectral data to obtain pure data based on the pre-constructed atmospheric interference model and the environmental parameters includes: Calculating the interference amount of aerosol scattered light in the atmosphere according to the aerosol concentration to obtain the aerosol interference amount; Calculate the influence of water vapor absorption light on the spectral value according to the water vapor concentration to obtain the water vapor influence; Extracting a signal amount in the hyperspectral data according to the aerosol interference amount and the water vapor influence amount; Correcting the signal quantity by a linear regression model to obtain correction data; Extracting pure values ​​from the correction data by a principal component analysis algorithm to obtain pure data; The atmospheric disturbance model is as follows: in, represents the amount of aerosol interference, represents the amount of water vapor influence, represents the aerosol concentration, Indicates wavelength The scattering coefficient, represents the wavelength, represents the spectrum value when there is no absorption, represents the water vapor absorption coefficient, represents the water vapor concentration, represents the optical path length, represents hyperspectral data, Indicates a semaphore. represents the calibration data, and represents the regression coefficients fitted by the least squares method, represents the preset error term, represents the eigenvector matrix, represents the eigenvalue matrix, represents the transposed matrix of the eigenvector matrix, Before k The matrix consists of eigenvectors, and P represents the pure data.

[0010] In an optional implementation, the environmental parameters, the pollutant types, the pollutant concentration range and the pure data are input into a pre-built pollutant diffusion model, and layer overlay analysis is performed in combination with the remote sensing image to obtain the pollution hotspot area, including: Inputting the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model to obtain predicted pollution data and generate a pollutant distribution map; Perform layer overlay analysis on the pollutant distribution map and the remote sensing image to obtain pollution hotspot areas; The pollutant diffusion model is as follows: in, represents the pollutant concentration, represents the impact coefficient of pollution type, represents the wind speed vector, and represents the diffusion coefficient, represents the pollution emission height obtained through remote sensing images, , , and represents the preset empirical coefficient, , and Indicates the distance in the downwind, acrosswind and vertical directions from the pollutant.

[0011] In an optional implementation, the identifying of abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source includes: Using a K-value clustering algorithm to perform cluster analysis on the clean data corresponding to the pollution hotspot area, obtain a spectrum category and use the spectrum category containing the most clean data as the background spectrum category; Calculating the difference between each of the spectrum categories and the background spectrum category, and comparing the difference with a preset abnormal threshold, if the difference is less than the abnormal threshold, marking the spectrum category as a normal point; If the difference is greater than the abnormal threshold, the spectrum category is marked as an abnormal point; Combining all the abnormal points to perform spatial distribution analysis and obtain the location of the pollution source; The difference is calculated by the following formula: in, Indicates the difference, spectral feature values ​​representing spectral classes, The spectral feature value representing the background spectral category.

[0012] In an optional implementation, the performing of time series analysis on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions and optimizing the pollutant diffusion model in combination with the environmental parameters includes: Performing time series analysis on the spectral data of the pollution source location and pre-stored historical spectral data to obtain the time characteristics of pollutant emissions; According to the time characteristics and the environmental parameters, the parameters of the pollutant diffusion model are optimized by using a gradient descent method.

[0013] In a second aspect, the present invention provides an atmospheric pollutant detection system based on multi-source data analysis, comprising: A data acquisition module is used to obtain hyperspectral data, environmental parameters and remote sensing images of pollutants in the atmosphere, wherein the environmental parameters include aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity; A spectral feature analysis module, used to perform feature separation on the spectral overlapping area according to the hyperspectral data by using a multi-component decomposition method based on Gaussian distribution to obtain the spectral features of the pollutants; A pollutant matching module, used to match the spectral characteristics with a pre-stored pollution spectrum library to obtain the type of pollutants and the range of pollutant concentrations; A data optimization module, used to remove interference signals from the hyperspectral data according to a pre-built atmospheric interference model and the environmental parameters to obtain pure data; A pollution area analysis module is used to input the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model, and perform layer overlay analysis in combination with the remote sensing image to obtain pollution hotspot areas; A pollution source analysis module, used to identify abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source; A diffusion model optimization module, used to perform time series analysis on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions, and optimize the pollutant diffusion model in combination with the environmental parameters; The output module is used to output the pollutant type, the pollutant concentration range, the pollution hotspot area, the pollution source location and the time characteristics as the result of atmospheric pollutant detection.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses an atmospheric pollutant detection method based on multi-source data analysis, comprising obtaining hyperspectral data, environmental parameters and remote sensing images of pollutants in the atmosphere, wherein the environmental parameters include aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity; according to the hyperspectral data, using a multi-component decomposition method based on Gaussian distribution to perform feature separation on spectral overlapping areas to obtain spectral features of pollutants; according to the spectral features, matching is performed with a pre-stored pollution spectrum library to obtain pollutant types and pollutant concentration ranges; according to a pre-constructed atmospheric interference model and the environmental parameters, interference signals are removed from the hyperspectral data to obtain pure data; The environmental parameters, the pollutant types, the pollutant concentration range and the pure data are input into a pre-constructed pollutant diffusion model, and layer overlay analysis is performed in combination with the remote sensing image to obtain pollution hotspot areas; outliers are identified in the pollution hotspot areas based on the pure data to obtain the location of the pollution source; time series analysis is performed on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions, and the pollutant diffusion model is optimized in combination with the environmental parameters; the pollutant types, the pollutant concentration range, the pollution hotspot areas, the pollution source locations and the time characteristics are output as the results of atmospheric pollutant detection. The present invention obtains hyperspectral data, environmental parameters and remote sensing images of pollutants; performs feature separation on spectral overlapping areas based on a multi-component decomposition method of Gaussian distribution, matches a pre-stored pollution spectrum library, and determines the types and concentration ranges of pollutants; eliminates interference signals in hyperspectral data through an atmospheric interference model to obtain pure data; inputs environmental parameters, pollutant information and pure data into a pollutant diffusion model, performs layer overlay analysis in combination with remote sensing images, and identifies pollution hotspots; identifies abnormal points in hotspots based on pure data and locates pollution sources; analyzes the time series of pollution source spectral data, and optimizes the diffusion model in combination with environmental parameters; and finally outputs pollutant types, concentration ranges, hotspots, pollution source locations and time characteristics to achieve rapid and accurate spatiotemporal monitoring of atmospheric pollutants. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic flow chart of an atmospheric pollutant detection method based on multi-source data analysis provided by the first embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of an air pollutant detection system based on multi-source data analysis provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Reference Figure 1 The first embodiment of the present invention provides an atmospheric pollutant detection method based on multi-source data analysis, comprising the following steps: S11, obtaining hyperspectral data, environmental parameters and remote sensing images of pollutants in the atmosphere, wherein the environmental parameters include aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity; S12, according to the hyperspectral data, using a multi-component decomposition method based on Gaussian distribution to perform feature separation on the spectral overlapping area to obtain spectral features of the pollutants; S13, matching the spectral features with a pre-stored pollution spectrum library to obtain pollutant types and pollutant concentration ranges; S14, removing interference signals from the hyperspectral data according to a pre-built atmospheric interference model and the environmental parameters to obtain pure data; S15, inputting the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model, and performing layer overlay analysis in combination with the remote sensing image to obtain the pollution hotspot area; S16, identifying abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source; S17, performing time series analysis on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions, and optimizing the pollutant diffusion model in combination with the environmental parameters; S18, outputting the pollutant type, the pollutant concentration range, the pollution hotspot area, the pollution source location and the time characteristics as the result of atmospheric pollutant detection.

[0018] In step S11, hyperspectral data, environmental parameters and remote sensing images of pollutants in the atmosphere are obtained, wherein the environmental parameters include aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity.

[0019] Hyperspectral data are collected by satellites, aircraft or ground sensors. These data contain rich spectral information and can reflect the spectral characteristics of different substances in the atmosphere. The acquisition of environmental parameters mainly relies on meteorological stations, ground monitoring equipment and satellite remote sensing technology. Aerosol concentration and water vapor concentration can be measured by laser radar, sun photometer and other equipment; wind speed, wind direction, temperature and humidity are obtained by meteorological stations or other meteorological sensors. Remote sensing images are taken by multispectral or hyperspectral satellite sensors to provide a wide range of surface information and atmospheric conditions.

[0020] In step S12, according to the hyperspectral data, a multi-component decomposition method based on Gaussian distribution is used to perform feature separation on the spectral overlapping area to obtain the spectral characteristics of the pollutant.

[0021] In a specific embodiment, the method of separating the characteristics of the spectral overlapping area by using a multi-component decomposition method based on Gaussian distribution according to the hyperspectral data to obtain the spectral characteristics of the pollutants includes: Converting the hyperspectral data into a Gaussian function form to obtain Gaussian data; Performing Fourier transformation on the Gaussian data to obtain frequency domain data decomposed into different frequencies; Performing inverse Fourier transform on each frequency domain data to obtain wavelength domain data of different wavelengths; Calculate the mean square error between the decomposed spectral signal and the mixed signal according to the wavelength domain data; Calculating the spectral matching degree according to the wavelength domain data and the preset standard data, and comparing the spectral matching degree with a preset spectral matching threshold value, if the spectral matching degree is less than the preset spectral matching threshold value, adjusting the Gaussian function parameters with the goal of minimizing the mean square error; If the spectral matching degree is greater than a preset spectral matching threshold, the spectral characteristics of the pollutant are obtained; Among them, the hyperspectral data is converted into Gaussian function form by the following formula: The mean square error is calculated by the following formula: The spectral matching degree is calculated by the following formula: in, represents hyperspectral data, Indicates The amplitude of a Gaussian function, Indicates The central wavelength, represents the standard deviation of the hyperspectral data, represents the Gaussian function component, represents the mean square error, The wavelength is The wavelength domain data of Indicates the number of wavelength domain data, express The contamination signal is at wavelength The wavelength domain data at express The contamination signal is at wavelength Standard data, represents the spectral matching degree, and e is a natural constant.

[0022] Specifically, the hyperspectral data is first Converted into Gaussian function form. Hyperspectral data usually contains light intensity information at multiple wavelengths, which can be represented by the superposition of multiple Gaussian functions. The specific formula is: in, represents hyperspectral data, Indicates The amplitude of a Gaussian function, Indicates The central wavelength, represents the standard deviation of the hyperspectral data, represents the Gaussian function component, and e is a natural constant. Through this formula, the hyperspectral data is decomposed into the superposition of multiple Gaussian functions, each of which corresponds to a spectral component.

[0023] Next, the Gaussian data is Fourier transformed to convert the time domain data into frequency domain data. The formula for Fourier transform is: Fourier transform decomposes Gaussian data into frequency domain data of different frequencies, and each frequency component corresponds to a spectral feature. After Fourier transform, each frequency domain data is inverse Fourier transformed to obtain wavelength domain data of different wavelengths. The formula for inverse Fourier transform is: The inverse Fourier transform converts the frequency domain data back into the wavelength domain data to obtain the decomposed spectral signal. Based on the wavelength domain data, the mean square error between the decomposed spectral signal and the original mixed signal is calculated. The calculation formula for the mean square error is: in, Indicates the number of wavelength domain data, The wavelength is The wavelength domain data of , and They represent the amplitude, central wavelength and standard deviation of the Gaussian function respectively, and e is a natural constant. The mean square error is used to measure the degree of fit between the decomposed spectral signal and the original signal. The smaller the value, the better the fit.

[0024] Calculate the spectral matching degree based on the wavelength domain data and the preset standard data. The calculation formula for spectral matching degree is: in, express The contamination signal is at wavelength The wavelength domain data at express The contamination signal is at wavelength The spectral matching degree is used to measure the similarity between the decomposed spectral signal and the standard spectrum. The larger the value, the higher the matching degree. The spectral matching degree is compared with the preset spectral matching threshold. If the spectral matching degree is less than the threshold, the amplitude of the Gaussian function is adjusted with the goal of minimizing the mean square error. , center wavelength and standard deviation , until the spectral matching degree is greater than the threshold, thus obtaining the accurate spectral characteristics of the pollutant.

[0025] Through the above process, the spectral overlap areas in the hyperspectral data are effectively decomposed, and the spectral characteristics of each pollutant can be accurately extracted. The implementation of this method not only relies on the mathematical modeling of hyperspectral data, but also involves signal processing technologies such as Fourier transform, inverse Fourier transform, and calculation of spectral matching. During the decomposition process, iterative optimization of mean square error and spectral matching ensures high accuracy of the analysis results.

[0026] In step S13, the spectral features are matched with a pre-stored pollution spectrum library to obtain the type of pollutant and the range of pollutant concentration.

[0027] In a specific embodiment, the matching of the spectral features with a pre-stored pollution spectrum library to obtain the pollutant type and pollutant concentration range includes: Using wavelet transform to perform denoising on the spectral features to obtain denoised data; Extracting characteristic points and characteristic lines according to the denoised data, and matching them with a preset pollution spectrum library to obtain pollutant types; Calculate the pollution concentration according to the denoised data and the pollution spectrum library to obtain a pollutant concentration range; Among them, the characteristic points and characteristic lines are calculated by the following formula: Among them, the pollutant concentration range is calculated by the following formula: in, Represents feature points, represents the characteristic line, represents the wavelength, represents the denoised data, and Indicates the starting wavelength and ending wavelength of the absorption peak. Indicates the pollutant concentration range, The wavelength in the contamination spectrum library is Reference data, represents the maximum wavelength, Indicates the preset molar absorptivity, represents the optical path length, The wavelength is The denoised data, Represents the constraint condition, taking Wavelength As a feature point .

[0028] Specifically, the spectral features are first denoised, and the wavelet transform method is used to remove the noise in the spectral data. Wavelet transform can effectively separate noise and useful signals by decomposing the spectral signal into frequency components of different scales. After removing the noise through wavelet transform, the denoised data is obtained. .

[0029] Next, extract feature points and feature lines from the denoised data. Feature points refer to the extreme value or inflection point position in the spectral curve, and feature lines refer to the spectral intensity integral within a specific wavelength range. The calculation formula for feature points is: in, Represents feature points, Indicates the spectrum curve at wavelength The derivative at , the position where the derivative is zero is the characteristic point. The calculation formula of the characteristic line is: in, represents the characteristic line, and The characteristic line is obtained by integrating and calculating the spectral intensity within a specific wavelength range.

[0030] After extracting the characteristic points and characteristic lines, they are matched with the pre-stored pollution spectrum library. The pollution spectrum library contains standard spectrum data of various pollutants. By comparing the similarity between the characteristic points and characteristic lines and the standard spectrum, the type of pollutant can be determined. The matching process uses a spectral similarity algorithm, such as Euclidean distance or correlation coefficient, to calculate the similarity between the spectrum to be tested and the standard spectrum, and selects the pollutant type corresponding to the standard spectrum with the highest similarity.

[0031] After determining the type of pollutant, further calculate the pollutant concentration range. According to the Lambert-Beer law, the pollutant concentration is proportional to the spectral absorption intensity. The calculation formula for the pollutant concentration is: in, Indicates the pollutant concentration range, The spectrum to be measured is at the maximum wavelength The strength of The wavelength in the pollution spectrum library is The reference intensity, Indicates the preset molar absorptivity, represents the optical path length, The wavelength is The denoised data, Represents the constraint condition, taking Wavelength As a feature point . Through this formula, the concentration range of pollutants in the sample to be tested can be calculated.

[0032] Through wavelet transform denoising, feature point and feature line extraction, spectrum matching and concentration calculation, accurate identification of pollutant types and concentration ranges is achieved. Wavelet transform denoising improves the signal-to-noise ratio of spectral data, feature point and feature line extraction enhances the recognition of spectral features, spectrum matching achieves accurate classification of pollutant types, and concentration calculation provides quantitative information on pollutant content, improving the efficiency and accuracy of pollution source identification and pollution diffusion analysis.

[0033] In step S14, interference signals are removed from the hyperspectral data according to the pre-constructed atmospheric interference model and the environmental parameters to obtain pure data.

[0034] In a specific implementation, removing interference signals from the hyperspectral data to obtain pure data based on the pre-constructed atmospheric interference model and the environmental parameters includes: Calculating the interference amount of aerosol scattered light in the atmosphere according to the aerosol concentration to obtain the aerosol interference amount; Calculate the influence of water vapor absorption light on the spectral value according to the water vapor concentration to obtain the water vapor influence; Extracting the signal amount in the hyperspectral data according to the aerosol interference amount and the water vapor influence amount; Correcting the signal quantity by a linear regression model to obtain correction data; Extracting pure values ​​from the correction data by a principal component analysis algorithm to obtain pure data; The atmospheric disturbance model is as follows: in, represents the amount of aerosol interference, represents the amount of water vapor influence, represents the aerosol concentration, Indicates wavelength The scattering coefficient, represents the wavelength, represents the spectrum value when there is no absorption, represents the water vapor absorption coefficient, represents the water vapor concentration, represents the optical path length, represents hyperspectral data, Indicates a semaphore. represents the calibration data, and represents the regression coefficients fitted by the least squares method, represents the preset error term, represents the eigenvector matrix, represents the eigenvalue matrix, represents the transposed matrix of the eigenvector matrix, Before k The matrix consists of eigenvectors, and P represents the pure data.

[0035] Specifically, the interference amount of aerosol scattered light in the atmosphere is calculated based on the aerosol concentration. The interference amount of aerosol scattered light is related to the aerosol concentration and wavelength. The specific formula is: in, represents the amount of aerosol interference, represents the aerosol concentration, Indicates wavelength The formula shows that the amount of interference from aerosol scattered light is proportional to the aerosol concentration and inversely proportional to the fourth power of the wavelength.

[0036] Next, the influence of water vapor absorption on the spectral value is calculated based on the water vapor concentration. The influence of water vapor absorption on the spectral value is calculated using the Lambert-Beer law, and the specific formula is: in, represents the amount of water vapor influence, represents the spectral value when there is no absorption, represents the water vapor absorption coefficient, represents the water vapor concentration, The formula shows that the amount of water vapor absorption of light is exponentially related to the water vapor concentration and the optical path length.

[0037] According to the aerosol interference and water vapor influence, the signal amount in the hyperspectral data is extracted. The calculation formula of the signal amount is: in, Indicates a semaphore. Represents hyperspectral data. Through this formula, the interference of aerosol scattered light and water vapor absorbed light is removed from the hyperspectral data to obtain the preliminary signal amount.

[0038] In order to further improve the accuracy of the data, the signal quantity is corrected through a linear regression model. The form of the linear regression model is: in, represents the calibration data, and represents the regression coefficients fitted by the least squares method, Represents the preset error term. The fitting process of the linear regression model is achieved by minimizing the sum of squared errors, thereby improving the linear relationship of the data.

[0039] Finally, the pure values ​​in the correction data are extracted by principal component analysis algorithm. Principal component analysis projects the data into a low-dimensional space through eigenvalue decomposition. The specific formula is: in, represents the eigenvector matrix, represents the eigenvalue matrix, represents the transposed matrix of the eigenvector matrix. k The matrix of eigenvectors , calculate the pure data P: Where P represents pure data. Through principal component analysis, the noise and redundant information in the correction data are removed, and the main feature information is retained, thereby obtaining high-precision pure data.

[0040] Through the calculation of aerosol interference and water vapor absorption, signal extraction, linear regression correction and principal component analysis, the interference signal in the hyperspectral data is effectively eliminated. The interference model of aerosol and water vapor is based on physical laws to ensure the accuracy of interference calculation; linear regression correction improves the linear relationship of the data; principal component analysis extracts the main features of the data, enhances the reliability of the analysis results, and improves the accuracy and efficiency of pollution source location and pollutant diffusion analysis.

[0041] In step S15, the environmental parameters, the pollutant types, the pollutant concentration range and the pure data are input into a pre-built pollutant diffusion model, and layer overlay analysis is performed in combination with the remote sensing image to obtain the pollution hotspot area.

[0042] In a specific implementation, the environmental parameters, the pollutant types, the pollutant concentration range and the pure data are input into a pre-built pollutant diffusion model, and layer overlay analysis is performed in combination with the remote sensing image to obtain the pollution hotspot area, including: Inputting the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model to obtain predicted pollution data and generate a pollutant distribution map; Perform layer overlay analysis on the pollutant distribution map and the remote sensing image to obtain pollution hotspot areas; The pollutant diffusion model is as follows: in, represents the pollutant concentration, represents the impact coefficient of pollution type, represents the wind speed vector, and represents the diffusion coefficient, represents the pollution emission height obtained through remote sensing images, , , and represents the preset empirical coefficient, , and Indicates the distance in the downwind, acrosswind and vertical directions from the pollutant.

[0043] Specifically, first, the concentration distribution of pollutants at different spatial locations is calculated based on environmental parameters, pollutant types, pollutant concentration range and pure data. The pollutant diffusion model is based on the Gaussian diffusion equation, and the specific formula is: in, represents the pollutant concentration, represents the impact coefficient of pollution type, represents the wind speed vector, and represents the diffusion coefficient, represents the pollution emission height obtained through remote sensing images, , and Indicates the distance from the pollutant in the downwind direction, crosswind direction and vertical direction. Diffusion coefficient and Calculated by empirical formula: in, , , and Represents the preset empirical coefficient, which is used to describe the variation of diffusion coefficient with distance. Through this model, the pollution data can be predicted And generate pollutant distribution map.

[0044] In the pollutant distribution map, the spatial distribution information of pollutant concentration is visualized, and high-concentration areas are marked as potential pollution hotspots. The pollutant distribution map is then overlaid with the remote sensing image for layer analysis. Layer overlay analysis combines pollutant distribution information with geographical features (such as terrain, vegetation, buildings, etc.) in remote sensing images by aligning spatial coordinates. The specific steps of overlay analysis include coordinate system 1, data interpolation, and layer fusion. Through overlay analysis, the relationship between the spatial distribution of pollutants and the geographical environment is clarified, thereby further accurately locating pollution hotspots.

[0045] Pollution hotspots are identified based on pollutant concentration thresholds , that is, when the pollutant concentration When the preset threshold is exceeded, the area is marked as a pollution hotspot. This process is achieved through spatial query and conditional screening to form the final pollution hotspot area map.

[0046] Through the prediction of the pollutant diffusion model and the layer overlay analysis of remote sensing images, the pollution hotspot areas are accurately located. The pollutant diffusion model is based on the Gaussian equation and empirical coefficients, which accurately describes the diffusion behavior of pollutants in space; the layer overlay analysis combines the distribution of pollutants with the geographical environment, enhancing the practicality and visualization of the analysis results. This method improves the accuracy and efficiency of pollution source identification and pollution diffusion analysis.

[0047] In step S16, outlier points in the pollution hotspot area are identified based on the clean data to obtain the location of the pollution source.

[0048] In a specific implementation, the step of identifying abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source includes: Using a K-value clustering algorithm to perform cluster analysis on the clean data corresponding to the pollution hotspot area, obtain a spectrum category and use the spectrum category containing the most clean data as the background spectrum category; Calculating the difference between each of the spectrum categories and the background spectrum category, and comparing the difference with a preset abnormal threshold, if the difference is less than the abnormal threshold, marking the spectrum category as a normal point; If the difference is greater than the abnormal threshold, the spectrum category is marked as an abnormal point; Combining all the abnormal points to perform spatial distribution analysis and obtain the location of the pollution source; The difference is calculated by the following formula: in, Indicates the difference, spectral feature values ​​representing spectral classes, The spectral feature value representing the background spectral category.

[0049] Specifically, first, the K-value clustering algorithm is used to perform cluster analysis on the clean data corresponding to the pollution hotspot area. The K-value clustering algorithm divides the data into K clusters so that the data points in the same cluster have higher similarity, while the data points between different clusters have lower similarity. The goal of cluster analysis is to obtain spectral categories, which represent areas with similar spectral characteristics. In the clustering process, the clean data is divided into K clusters by calculating the distance between data points. The distance calculation formula is the Euclidean distance: in, Represents data points and The distance between and Represents data points and In the The spectral characteristic value of Represents the dimension of spectral features. After clustering, the spectral category containing the most pure data is marked as the background spectral category.

[0050] Next, the difference between each spectrum category and the background spectrum category is calculated. The difference is calculated by cosine similarity, and the specific formula is: in, Indicates the difference, spectral feature values ​​representing spectral classes, represents the spectral characteristic value of the background spectrum category, Representation vector and The dot product of and Represents vectors and The norm of . It reflects the similarity between the spectral category and the background spectral category.

[0051] The difference is compared with the preset anomaly threshold: if the difference is less than the anomaly threshold, the spectral category is marked as a normal point; if the difference is greater than the anomaly threshold, the spectral category is marked as an anomaly. Anomalies indicate areas where the spectral features are significantly different from the background spectral category and are potential locations of pollution sources.

[0052] Finally, all outliers are combined for spatial distribution analysis to determine the location of the pollution source. Spatial distribution analysis calculates the spatial density and distribution pattern of outliers to identify high-density areas as pollution source locations. Specific methods include kernel density estimation and spatial clustering. Kernel density estimation calculates the density of outliers within a certain range to generate a density distribution map, and the high-density area is the location of the pollution source. The kernel density estimation formula is: in, Indicates location The density value at represents the number of outliers, represents the bandwidth parameter, represents the kernel function, Indicates location With outliers Through kernel density estimation, high-density areas are identified as pollution source locations.

[0053] The above steps achieve accurate identification of pollution source locations through K-value clustering analysis, difference calculation and spatial distribution analysis. K-value clustering divides pure data into spectral categories, difference calculation identifies abnormal points that are significantly different from the background spectral categories, and spatial distribution analysis locates high-density areas as pollution sources. This method effectively locates pollution sources quickly and improves the efficiency and accuracy of environmental pollution monitoring and management.

[0054] In step S17, a time series analysis is performed on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions, and the pollutant diffusion model is optimized in combination with the environmental parameters.

[0055] In a specific implementation, the time series analysis of the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions and optimizing the pollutant diffusion model in combination with the environmental parameters includes: Performing time series analysis on the spectral data of the pollution source location and pre-stored historical spectral data to obtain the time characteristics of pollutant emissions; According to the time characteristics and the environmental parameters, the parameters of the pollutant diffusion model are optimized by using a gradient descent method.

[0056] In step S17, the spectral data at the pollution source location is subjected to time series analysis to obtain the temporal characteristics of pollutant emissions, and the pollutant diffusion model is optimized in combination with environmental parameters. The specific implementation process is as follows: First, the spectral data at the pollution source location is extracted and integrated with the pre-stored historical spectral data to form a time series data set. Time series analysis reveals the dynamic characteristics of pollutant emissions by modeling the temporal variation of spectral data. The time series analysis method adopts the autoregressive integrated moving average model (ARIMA), and the ARIMA model is expressed as: in, Indicates time Spectral data of contaminated sites at represents the autoregressive coefficient polynomial, represents the sliding mean coefficient polynomial, represents the lag operator, represents the difference order, Represents the random error term. The ARIMA model is used to fit time series data to extract the temporal characteristics of pollutant emissions, including periodic changes, trend patterns, and abnormal fluctuations.

[0057] Next, the parameters of the pollutant diffusion model are optimized by gradient descent method using the extracted time characteristics and environmental parameters. The parameters of the pollutant diffusion model include the pollution type influence coefficient , Diffusion coefficient empirical coefficient , , and The optimization goal is to minimize the error between the model's prediction results and the measured data. The error function is defined as the mean square error: in, represents the error function, represents the total number of data points, represents the pollutant concentration predicted by the model, Represents the measured pollutant concentration. The model parameters are iteratively updated by the gradient descent method to minimize the error function. The parameter update formula of the gradient descent method is: in, Indicates The model parameters of the iteration, represents the learning rate, Represents the error function Parameters Through multiple iterations, the model parameters gradually converge to the optimal value, thereby optimizing the pollutant diffusion model.

[0058] The optimized pollutant diffusion model can more accurately predict the spatial diffusion behavior of pollutants. Combined with the time characteristics obtained by time series analysis, the dynamic prediction ability of the model is further enhanced. The optimized model form is: in, represents the optimized pollutant concentration, represents the impact coefficient of the optimized pollution type, and Through the optimized empirical coefficient , , and calculate.

[0059] Through time series analysis and gradient descent optimization, the extraction of pollutant emission time characteristics and the optimization of pollutant diffusion model are realized. Time series analysis reveals the dynamic law of pollutant emissions, and the gradient descent method improves the prediction accuracy of the model. The optimized model provides a reliable tool for real-time monitoring, dynamic prediction and precise governance of environmental pollution.

[0060] In step S18, the pollutant type, the pollutant concentration range, the pollution hotspot area, the pollution source location and the time characteristics are output as the result of atmospheric pollutant detection.

[0061] Specifically, first, the pollutant types, pollutant concentration ranges, pollution hotspots, pollution source locations and time characteristics are integrated into a structured data set. Indicates that the pollutant concentration range passes through the minimum concentration and maximum concentration Indicates that the pollution hotspot area is represented by the spatial coordinate set Indicates that the pollution source location is expressed by the spatial coordinates Indicates that the time feature is extracted through the time series model express.

[0062] The output structured data set is represented in matrix form as follows: In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0063] The following describes the working process of the present invention by taking a relatively common scenario as an example. The specific implementation of the present invention includes the following steps: In a certain industrial area, firstly, hyperspectral data of pollutants in the atmosphere, environmental parameters including aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity, and multispectral remote sensing images were obtained through satellite, aircraft and ground sensors.

[0064] After the hyperspectral data was processed by a multi-component decomposition method based on Gaussian distribution, the spectral overlapping areas were effectively separated and the spectral characteristics of the pollutants were extracted. By matching with the pre-stored pollution spectrum library, the main pollutants in the industrial area were determined to be sulfur dioxide (SO2) and nitrogen oxides (NO X ), and calculated that the concentration range of SO2 is 50-80 μg / m³, and NO X The concentration range is 60-100 μg / m³.

[0065] Subsequently, the atmospheric interference model was used to remove the interference signals in the hyperspectral data and obtain pure data. Environmental parameters, pollutant information and pure data were input into the pollutant diffusion model, and layer overlay analysis was performed in combination with remote sensing images to identify two major pollution hotspots. The first pollution hotspot is located in the northeast corner of the industrial zone, and the second hotspot is located in the southwest corner.

[0066] By identifying abnormal points in the pure data, the pollution sources were further located. The pollution source in the northeast corner was determined to be the emission outlet of a chemical plant, while the pollution source in the southwest corner was a blast furnace in a steel plant. Subsequently, a time series analysis of the spectral data of the pollution sources was performed, and it was found that the emission peaks of SO2 occurred at 8 am and 6 pm, and NO XThe peak of emissions occurs at 12 noon.

[0067] The pollutant diffusion model was optimized by gradient descent method based on the time characteristics of pollutant emissions and environmental parameters. The optimized model shows that wind speed and wind direction have a significant impact on the diffusion of pollutants, especially when the wind speed exceeds 5 m / s, pollutants will diffuse to the southeast, and the impact range will expand to the residential areas around the industrial area.

[0068] Finally, the system outputs the pollutant types (SO2 and NO X ), concentration range (SO2: 50-80 μg / m³, NO X : 60-100 μg / m³), pollution hotspots (northeast and southwest corners), pollution source locations (chemical plants and steel plants), and the time characteristics of pollutant emissions (SO2 at 8 am and 6 pm, NO X These results provide accurate monitoring data for environmental protection departments to support them in formulating effective pollution control measures.

[0069] In practical applications in industrial areas, this method has effectively improved the accuracy and efficiency of pollution source identification and pollutant diffusion analysis.

[0070] Reference Figure 2 The second embodiment of the present invention provides an air pollutant detection system based on multi-source data analysis, comprising: A data acquisition module is used to obtain hyperspectral data, environmental parameters and remote sensing images of pollutants in the atmosphere, wherein the environmental parameters include aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity; A spectral feature analysis module, used to perform feature separation on the spectral overlapping area according to the hyperspectral data by using a multi-component decomposition method based on Gaussian distribution to obtain the spectral features of the pollutants; A pollutant matching module, used to match the spectral characteristics with a pre-stored pollution spectrum library to obtain the type of pollutants and the range of pollutant concentrations; A data optimization module, used to remove interference signals from the hyperspectral data according to a pre-built atmospheric interference model and the environmental parameters to obtain pure data; A pollution area analysis module is used to input the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model, and perform layer overlay analysis in combination with the remote sensing image to obtain pollution hotspot areas; A pollution source analysis module, used to identify abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source; A diffusion model optimization module, used to perform time series analysis on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions, and optimize the pollutant diffusion model in combination with the environmental parameters; The output module is used to output the pollutant type, the pollutant concentration range, the pollution hotspot area, the pollution source location and the time characteristics as the result of atmospheric pollutant detection.

[0071] It should be noted that the atmospheric pollutant detection device based on multi-source data analysis provided in an embodiment of the present invention is used to execute all the process steps of the atmospheric pollutant detection method based on multi-source data analysis in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0072] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting air pollutants based on multi-source data analysis, characterized in that: include: Obtain hyperspectral data, environmental parameters and remote sensing images of pollutants in the atmosphere, where environmental parameters include aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity; According to the hyperspectral data, a multi-component decomposition method based on Gaussian distribution is used to separate the characteristics of the spectral overlapping area to obtain the spectral characteristics of the pollutants; According to the spectral characteristics, the spectral characteristics are matched with a pre-stored pollution spectrum library to obtain the type of pollutants and the range of pollutant concentrations; According to the pre-built atmospheric interference model and the environmental parameters, interference signals are removed from the hyperspectral data to obtain pure data; Input the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model, and perform layer overlay analysis in combination with the remote sensing image to obtain the pollution hotspot area; Identify abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source; Performing time series analysis on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions, and optimizing the pollutant diffusion model in combination with the environmental parameters; The pollutant type, the pollutant concentration range, the pollution hotspot area, the pollution source location and the time characteristics are output as the results of atmospheric pollutant detection.

2. The method for detecting air pollutants based on multi-source data analysis according to claim 1, characterized in that: According to the hyperspectral data, a multi-component decomposition method based on Gaussian distribution is used to separate the characteristics of the spectral overlapping area to obtain the spectral characteristics of the pollutants, including: Converting the hyperspectral data into a Gaussian function form to obtain Gaussian data; Performing Fourier transformation on the Gaussian data to obtain frequency domain data decomposed into different frequencies; Performing inverse Fourier transform on each frequency domain data to obtain wavelength domain data of different wavelengths; Calculate the mean square error between the decomposed spectral signal and the mixed signal according to the wavelength domain data; Calculating the spectral matching degree according to the wavelength domain data and the preset standard data, and comparing the spectral matching degree with a preset spectral matching threshold value, if the spectral matching degree is less than the preset spectral matching threshold value, adjusting the Gaussian function parameters with the goal of minimizing the mean square error; If the spectral matching degree is greater than a preset spectral matching threshold, the spectral characteristics of the pollutant are obtained; Among them, the hyperspectral data is converted into Gaussian function form by the following formula: The mean square error is calculated by the following formula: The spectral matching degree is calculated by the following formula: in, represents hyperspectral data, Indicates The amplitude of a Gaussian function, Indicates The central wavelength, represents the standard deviation of the hyperspectral data, represents the Gaussian function component, represents the mean square error, The wavelength is The wavelength domain data of Indicates the number of wavelength domain data, express The contamination signal is at wavelength The wavelength domain data at express The contamination signal is at wavelength Standard data, represents the spectral matching degree, and e is a natural constant.

3. The method for detecting air pollutants based on multi-source data analysis according to claim 1, characterized in that: The method of matching the spectral features with a pre-stored pollution spectrum library to obtain the type of pollutants and the range of pollutant concentrations includes: Using wavelet transform to perform denoising on the spectral features to obtain denoised data; Extracting characteristic points and characteristic lines according to the denoised data, and matching them with a preset pollution spectrum library to obtain pollutant types; Calculate the pollution concentration according to the denoised data and the pollution spectrum library to obtain a pollutant concentration range; Among them, the characteristic points and characteristic lines are calculated by the following formula: Among them, the pollutant concentration range is calculated by the following formula: in, Represents feature points, represents the characteristic line, represents the wavelength, represents the denoised data, and Indicates the starting wavelength and ending wavelength of the absorption peak. Indicates the pollutant concentration range, The wavelength in the contamination spectrum library is Reference data, represents the maximum wavelength, Indicates the preset molar absorptivity, represents the optical path length, The wavelength is The denoised data, Represents the constraint condition, taking Wavelength As a feature point .

4. The method for detecting air pollutants based on multi-source data analysis according to claim 1, characterized in that: The step of removing interference signals from the hyperspectral data according to the pre-built atmospheric interference model and the environmental parameters to obtain pure data includes: Calculating the interference amount of aerosol scattered light in the atmosphere according to the aerosol concentration to obtain the aerosol interference amount; Calculate the influence of water vapor absorption light on the spectral value according to the water vapor concentration to obtain the water vapor influence; Extracting a signal amount in the hyperspectral data according to the aerosol interference amount and the water vapor influence amount; Correcting the signal quantity by a linear regression model to obtain correction data; Extracting pure values ​​from the correction data by a principal component analysis algorithm to obtain pure data; The atmospheric disturbance model is as follows: in, represents the amount of aerosol interference, represents the amount of water vapor influence, represents the aerosol concentration, Indicates wavelength The scattering coefficient, represents the wavelength, represents the spectrum value when there is no absorption, represents the water vapor absorption coefficient, represents the water vapor concentration, represents the optical path length, represents hyperspectral data, Indicates the semaphore. represents the calibration data, and represents the regression coefficients fitted by the least squares method, represents the preset error term, represents the eigenvector matrix, represents the eigenvalue matrix, represents the transposed matrix of the eigenvector matrix, Before k The matrix consists of eigenvectors, and P represents the pure data.

5. The method for detecting air pollutants based on multi-source data analysis according to claim 1, characterized in that: The environmental parameters, pollutant types, pollutant concentration ranges and pure data are input into a pre-built pollutant diffusion model, and layer overlay analysis is performed in combination with the remote sensing image to obtain pollution hotspots, including: Inputting the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model to obtain predicted pollution data and generate a pollutant distribution map; Perform layer overlay analysis on the pollutant distribution map and the remote sensing image to obtain pollution hotspot areas; The pollutant diffusion model is as follows: in, represents the pollutant concentration, represents the impact coefficient of pollution type, represents the wind speed vector, and represents the diffusion coefficient, represents the pollution emission height obtained through remote sensing images, , , and represents the preset empirical coefficient, , and Indicates the distance in the downwind, acrosswind and vertical directions from the pollutant.

6. The method for detecting air pollutants based on multi-source data analysis according to claim 1, characterized in that: The step of identifying abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source includes: Using a K-value clustering algorithm to perform cluster analysis on the clean data corresponding to the pollution hotspot area, obtain a spectrum category and use the spectrum category containing the most clean data as the background spectrum category; Calculating the difference between each of the spectrum categories and the background spectrum category, and comparing the difference with a preset abnormal threshold, if the difference is less than the abnormal threshold, marking the spectrum category as a normal point; If the difference is greater than the abnormal threshold, the spectrum category is marked as an abnormal point; Combining all the abnormal points to perform spatial distribution analysis and obtain the location of the pollution source; The difference is calculated by the following formula: in, Indicates the difference, spectral feature values ​​representing spectral classes, The spectral feature value representing the background spectral category.

7. The method for detecting air pollutants based on multi-source data analysis according to claim 1, characterized in that: The time series analysis of the spectral data at the pollution source location is performed to obtain the time characteristics of pollutant emissions, and the pollutant diffusion model is optimized in combination with the environmental parameters, including: Performing time series analysis on the spectral data of the pollution source location and pre-stored historical spectral data to obtain the time characteristics of pollutant emissions; According to the time characteristics and the environmental parameters, the parameters of the pollutant diffusion model are optimized by using a gradient descent method.

8. An atmospheric pollutant detection system based on multi-source data analysis, characterized in that: include: A data acquisition module is used to obtain hyperspectral data, environmental parameters and remote sensing images of pollutants in the atmosphere, wherein the environmental parameters include aerosol concentration, water vapor concentration, wind speed, wind direction, temperature and humidity; A spectral feature analysis module, used to perform feature separation on the spectral overlapping area according to the hyperspectral data by using a multi-component decomposition method based on Gaussian distribution to obtain the spectral features of the pollutants; A pollutant matching module, used to match the spectral characteristics with a pre-stored pollution spectrum library to obtain the type of pollutants and the range of pollutant concentrations; A data optimization module, used to remove interference signals from the hyperspectral data according to a pre-built atmospheric interference model and the environmental parameters to obtain pure data; A pollution area analysis module is used to input the environmental parameters, the pollutant types, the pollutant concentration range and the pure data into a pre-built pollutant diffusion model, and perform layer overlay analysis in combination with the remote sensing image to obtain pollution hotspot areas; A pollution source analysis module, used to identify abnormal points in the pollution hotspot area according to the clean data to obtain the location of the pollution source; A diffusion model optimization module, used to perform time series analysis on the spectral data at the pollution source location to obtain the time characteristics of pollutant emissions, and optimize the pollutant diffusion model in combination with the environmental parameters; The output module is used to output the pollutant type, the pollutant concentration range, the pollution hotspot area, the pollution source location and the time characteristics as the result of atmospheric pollutant detection.

Images