Atmosphere control monitoring method and system

Abstract

The invention provides an atmospheric control monitoring method and system. The atmospheric control monitoring method comprises the following steps: collecting concentration information of different volatile organic compounds at all sampling moments at each monitoring point through an intelligent pollutant sensor; determining the pollution potential of each volatile organic compound according to the concentration information of each volatile organic compound and the pollution diffusivity of the corresponding volatile organic compound; pollution spectrum information of different pollution sources is collected through an intelligent spectrum sensor, and then concentration contribution ratios when the different pollution sources in the atmospheric environment are converted into ozone pollution are generated on the basis of a machine learning algorithm in combination with the pollution spectrum information of the different pollution sources; carrying out load prediction on ozone pollution of each monitoring point according to the pollution potential of each volatile organic compound and the contribution ratio of different concentrations to obtain a pollution load degree; and performing partition treatment based on all pollution load degrees. By adopting the scheme of the invention, multi-factor nonlinear modeling of the atmospheric environment can be realized.

Description

Technical Field

[0001] The present application relates to the field of air governance technology, and more specifically, to an air governance monitoring method and system. Background Art

[0002] Atmospheric governance involves reducing or eliminating air pollutants through physical, chemical, biological and other means to improve environmental quality and protect ecosystems. This field covers pollution source control, pollutant monitoring, pollutant reduction and air quality optimization, including industrial waste gas treatment, motor vehicle exhaust treatment, dust control and volatile organic compound treatment; atmospheric governance not only focuses on end-of-pipe treatment, but also includes comprehensive governance, that is, emphasizing the reduction of total pollutant emissions and continuous improvement of air quality through source reduction and full process control, such as optimizing energy structure, promoting clean production technology, developing new energy and renewable energy, etc.; the comprehensive governance model also includes policy regulation, technological innovation, public participation and other multi-level coordinated promotion to achieve efficient control of air pollution and environmental sustainable development.

[0003] Atmospheric governance monitoring refers to the real-time or periodic detection of the concentration, distribution and changing trends of air pollutants to provide a scientific basis for air pollution prevention and control, so as to achieve precise control and effective governance. This field covers online monitoring of pollutants, mobile monitoring, remote sensing monitoring, source analysis technology, air quality prediction and early warning, etc. Common monitoring methods include high-precision sensors, lidar, Fourier transform infrared spectroscopy, differential absorption spectroscopy, portable gas chromatography-mass spectrometry and other technologies, combined with drones, satellite remote sensing, geographic information systems and other tools to achieve multi-scale and full coverage of atmospheric environment monitoring. Atmospheric governance monitoring not only focuses on pollutant concentrations, but also includes meteorological parameters (wind speed, wind direction, temperature, humidity, atmospheric pressure, etc.) and pollutant source analysis to evaluate pollution transmission and diffusion characteristics; in the process of atmospheric governance monitoring of ozone pollution, traditional statistical methods such as multivariate regression analysis and time series analysis algorithms are usually used to predict the concentration trend of volatile organic compounds in the atmospheric environment to achieve atmospheric governance monitoring. However, this method often has nonlinear problems between different volatile organic compounds (that is, volatile organic compounds are affected by chemical reactions, diffusion, sedimentation, temperature and humidity, etc., and present complex nonlinear relationships), which makes it difficult for the monitoring system to capture the complex interactions between volatile organic compounds, thereby affecting the reliability of prediction. Therefore, how to achieve multi-factor nonlinear modeling of the atmospheric environment has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides an atmospheric governance monitoring method and system, which can realize multi-factor nonlinear modeling of the atmospheric environment.

[0005] In a first aspect, the present application provides an atmospheric governance monitoring method, comprising the following steps: Set up multiple monitoring points in the atmospheric environment of different functional areas in the target area, and then collect the concentration information of different volatile organic compounds at all sampling times at each monitoring point through intelligent pollutant sensors; Determining the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound; Acquire multiple pollution sources in the target area, collect pollution spectrum information of different pollution sources through intelligent spectral sensors, and then generate the concentration contribution ratio of different pollution sources in the atmospheric environment when converted into ozone pollution based on machine learning algorithms and pollution spectrum information of different pollution sources; According to the ozone pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, the ozone pollution load of each monitoring point is predicted to obtain the pollution load degree of each monitoring point at different sampling times; The atmospheric environment in the target area is zoned and managed based on all pollution loads.

[0006] In some embodiments, determining the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound specifically includes: Determine the loss factor for each volatile organic compound in the atmosphere when it undergoes photochemical reactions; Performing loss correction on the concentration information of each volatile organic compound according to the loss factor; The ozone pollution potential of each volatile organic compound in the atmospheric environment is determined according to the calibration result and in combination with the pollution diffusion capacity of each volatile organic compound.

[0007] In some embodiments, performing loss correction on the concentration information of each volatile organic compound according to the loss factor specifically includes: Selecting a volatile organic compound as the selected volatile organic compound; determining a concentration attenuation coefficient of the selected volatile organic compound according to a loss factor corresponding to the selected volatile organic compound; Performing loss correction on the concentration information of the selected volatile organic compound according to the concentration attenuation coefficient to obtain a correction result of the concentration information of the selected volatile organic compound; Continue to perform loss correction on the concentration information of the remaining volatile organic compounds to obtain a correction result of the concentration information of the remaining volatile organic compounds.

[0008] In some embodiments, determining the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the calibration result combined with the pollution diffusion capacity of each volatile organic compound specifically includes: Obtaining the pollution diffusion coefficient of each volatile organic compound in the atmospheric environment; Determining the reaction activity factor when each volatile organic compound is converted into ozone by the pollution diffusion coefficient; The ozone pollution potential of each volatile organic compound in the atmospheric environment is determined by the reactivity factor and the correction result.

[0009] In some embodiments, the concentration contribution ratio of different pollution sources in the atmospheric environment converted into ozone pollution based on the machine learning algorithm combined with the pollution spectrum information of different pollution sources specifically includes: Determine the characteristic spectrum of each pollution source according to the pollution spectrum information of various pollution sources; The characteristic spectra of various pollution sources are combined with machine learning algorithms to generate the concentration contribution ratio of each pollution source in the atmospheric environment when it is converted into ozone pollution.

[0010] In some embodiments, the ozone pollution load of each monitoring point is predicted based on the pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, and the pollution load degree of each monitoring point at different sampling times is obtained, which specifically includes: Select a sampling time as the selected sampling time; Determine the amount of ozone generated at each monitoring point by selecting the concentration values ​​of various volatile organic compounds at each monitoring point at the sampling time and the ozone pollution potential of each volatile organic compound in the atmospheric environment; Determine the pollution load at each monitoring point at the selected sampling time based on all ozone generation and the concentration contribution ratio of the different pollution sources when converted into ozone pollution; Continue to determine the pollution load at each monitoring point during the remaining sampling moments.

[0011] In some embodiments, the zoning management of the atmospheric environment of the target area based on all pollution loads specifically includes: The atmospheric environment of the target area at the corresponding sampling time is divided into multiple pollution load areas according to the pollution load degree of all monitoring points at different sampling times; The atmospheric environment of the target area is zoned and managed based on all pollution load areas.

[0012] In a second aspect, the present application provides an atmospheric governance monitoring system, comprising: The acquisition module is used to set up multiple monitoring points in the atmospheric environment of different functional areas of the target area, and then collect the concentration information of different volatile organic compounds at all sampling times at each monitoring point through intelligent pollutant sensors; A processing module, used for determining the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound; The processing module is also used to obtain multiple pollution sources in the target area, collect pollution spectrum information of different pollution sources through intelligent spectrum sensors, and then generate concentration contribution ratios of different pollution sources in the atmospheric environment when converted into ozone pollution based on machine learning algorithms and pollution spectrum information of different pollution sources; The processing module is further used to predict the ozone pollution load of each monitoring point according to the ozone pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, so as to obtain the pollution load degree of each monitoring point at different sampling times; The execution module is used to perform zoning management of the atmospheric environment in the target area based on all pollution loads.

[0013] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned atmospheric governance monitoring method when executing the computer program.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned atmospheric governance monitoring method are implemented.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: In the atmospheric governance monitoring method and system provided by the present application, multiple monitoring points are set in the atmospheric environment of different functional zones in the target area, and then the concentration information of different volatile organic compounds at all sampling times at each monitoring point is collected through intelligent pollutant sensors; the pollution potential of ozone of each volatile organic compound in the atmospheric environment is determined based on the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound; multiple pollution sources in the target area are obtained, and the pollution spectrum information of different pollution sources is collected through intelligent spectral sensors, and then the concentration contribution ratio of different pollution sources in the atmospheric environment when converted into ozone pollution is generated based on the machine learning algorithm combined with the pollution spectrum information of different pollution sources; the ozone pollution load of each monitoring point is predicted according to the pollution potential of ozone of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, so as to obtain the pollution load degree of each monitoring point at different sampling times; and the atmospheric environment of the target area is zoned for governance based on all pollution load degrees.

[0016] It can be seen that in this application, first, the concentration information of different volatile organic compounds at each monitoring point at all sampling times is collected through intelligent pollutant sensors, and then the possibility of their conversion into ozone (pollution potential of ozone) is evaluated by combining the diffusion capacity of volatile organic compounds, thereby enhancing the model's understanding of the complex relationship between various volatile organic compounds, so that the atmospheric governance monitoring system can still maintain a high prediction accuracy when dealing with different environmental conditions, and improve the reliability of volatile organic compound concentration prediction; then, the concentration contribution ratio of different pollution sources to ozone pollution is determined by combining pollution spectral information through machine learning algorithms, so as to accurately model the source analysis of volatile organic compounds, thereby avoiding the limitations of traditional linear regression methods that are difficult to deal with the complex interactive effects of volatile organic compounds, making volatile organic compounds The source analysis process of volatile organic compounds is more accurate; finally, the ozone pollution load of each monitoring point is predicted according to the ozone pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, and the pollution load degree of each monitoring point at different sampling times is obtained, thereby integrating the ozone pollution potential of volatile organic compounds and the concentration contribution ratio of pollution sources, so that the prediction model can dynamically evaluate the evolution trend of different volatile organic compounds in the atmospheric environment. This application is based on the analysis of pollution load degree, so as to quantify the contribution of different pollution sources to ozone pollution at each monitoring point under different meteorological conditions, thereby improving the model's adaptability to changes in pollution levels at different times and in different regions; in summary, this scheme can realize multi-factor nonlinear modeling of the atmospheric environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1It is a flow chart of an atmospheric governance monitoring method according to some embodiments of the present application; Figure 2 is a schematic diagram of a photochemical reaction process according to some embodiments of the present application; Figure 3 is a schematic diagram of a process for determining contamination potential according to some embodiments of the present application; Figure 4 is a schematic diagram of the structure of an atmosphere control monitoring system according to some embodiments of the present application; Figure 5 It is a diagram of the internal structure of a computer device for implementing the air governance monitoring method shown in some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the technical solution in this embodiment, the technical solution in this embodiment will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0019] refer to Figure 1 , which is a flow chart of an air governance monitoring method according to some embodiments of the present application. The air governance monitoring method 100 mainly includes the following steps: In step 101, a plurality of monitoring points are set in the atmospheric environment of different functional zones in the target area, and then the concentration information of different volatile organic compounds at all sampling times at each monitoring point is collected by using an intelligent pollutant sensor.

[0020] It should be noted that the monitoring points described in the present application are sampling points set at different locations in the atmospheric environment of the target area, and can be set according to different functional areas and environmental conditions in the atmospheric environment. The functional areas described in the present application specifically include: urban blocks (densely populated areas with large traffic flow), industrial areas (emitting large amounts of harmful gases), parks (as the natural background concentration of volatile organic compounds in atmospheric monitoring) and mountainous areas (used to analyze the diffusion pattern of volatile organic compounds); the intelligent pollutant sensor is a volatile organic compound gas sensor, and the volatile organic compounds in the present application specifically include formaldehyde, benzene, solvents, coatings and automobile exhaust, etc.; in addition, the concentration information refers to multidimensional data composed of concentration values ​​of different volatile organic compounds at all sampling times at each monitoring point.

[0021] In step 102, the ozone pollution potential of each volatile organic compound in the atmospheric environment is determined according to the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound.

[0022] In some embodiments, the following steps may be used to determine the ozone pollution potential of each volatile organic compound in the atmospheric environment based on the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound: Determine the loss factor for each volatile organic compound in the atmosphere when it undergoes photochemical reactions; Performing loss correction on the concentration information of each volatile organic compound according to the loss factor; The ozone pollution potential of each volatile organic compound in the atmospheric environment is determined according to the calibration result and in combination with the pollution diffusion capacity of each volatile organic compound.

[0023] In some embodiments, determining the loss factor of each volatile organic compound in the atmosphere when a photochemical reaction occurs can be achieved by using the following steps: Obtain the photochemical loss rate of each volatile organic compound in the atmosphere when it undergoes photochemical reaction; The photochemical loss rate of each volatile organic compound is combined with the atmospheric chemistry model to generate the loss factor of each volatile organic compound in the atmosphere when it undergoes photochemical reaction.

[0024] It should be noted that after the volatile organic compounds described in this application are emitted, they will react with nitrogen oxides in the atmosphere to produce photochemical reactions (free radical reactions between volatile organic compounds and nitrogen oxides under the action of sunlight) to generate ozone, thereby causing ozone pollution to the atmospheric environment of the target environment. Figure 2 As shown in FIG. 1 , the figure is a schematic diagram of the photochemical reaction process shown in some embodiments of the present application; therefore, the photochemical loss rate refers to the rate at which the photochemical reaction produced when the volatile organic compounds in the atmospheric environment are consumed when affected by solar radiation. As a preferred embodiment, the photochemical loss rate of each volatile organic compound in the atmosphere when a photochemical reaction occurs can be obtained by an experimental determination method, that is, using a gas chromatography-mass spectrometer to determine the photochemical reaction rates of different volatile organic compounds in a simulated atmospheric environment under conditions of controlled temperature, humidity, and light intensity; for example, by monitoring NO 2 The rate of change under different light conditions, and then the NO was determined according to the change in the rate of change at different experimental time points. 2 The photochemical loss rate can be obtained by other methods in other embodiments, which is not limited here.

[0025] In specific implementation, the loss factor of each volatile organic compound in the atmosphere when a photochemical reaction occurs can be generated by combining the photochemical loss rate of each volatile organic compound with an atmospheric chemical model. The following method can be used, namely: first, the meteorological data in the target area is generated by a weather forecast model in the prior art. Subsequently, the initial concentrations and emission rates of anthropogenic emissions (transportation, industry, energy, etc.), biogenic emissions (vegetation volatile organic compound release), soil nitrogen oxide release, etc. are obtained through a global or regional emission inventory (such as China's multi-resolution emission inventory). Then, the meteorological data is used as a model driver, and the initial concentration and the emission rate are used as model constraints. The photochemical reaction of each volatile organic compound in the target area is simulated by using an atmospheric chemical model technology in the prior art (such as a box model) to generate a critical reaction concentration of each volatile organic compound in the target area. Finally, the ratio of the critical reaction concentration to the photochemical loss rate is used as the loss factor of each volatile organic compound when a photochemical reaction occurs.

[0026] It should be noted that the loss factor described in the present application refers to the relative ability of the corresponding volatile organic compound in the atmosphere to be consumed due to solar radiation during the photochemical reaction. The loss factor can be used to characterize the consumption intensity of the corresponding volatile organic compound in the atmospheric environment. The larger the loss factor, the higher the consumption intensity of the corresponding volatile organic compound in the atmospheric environment, and the smaller the loss factor, the lower the consumption intensity of the corresponding volatile organic compound in the atmospheric environment.

[0027] In some embodiments, performing loss correction on the concentration information of each volatile organic compound according to the loss factor may be implemented by the following steps: Selecting a volatile organic compound as the selected volatile organic compound; determining a concentration attenuation coefficient of the selected volatile organic compound according to a loss factor corresponding to the selected volatile organic compound; Performing loss correction on the concentration information of the selected volatile organic compound according to the concentration attenuation coefficient to obtain a correction result of the concentration information of the selected volatile organic compound; Continue to perform loss correction on the concentration information of the remaining volatile organic compounds to obtain a correction result of the concentration information of the remaining volatile organic compounds.

[0028] In a specific implementation, determining the concentration attenuation coefficient of the selected volatile organic compound according to the loss factor corresponding to the selected volatile organic compound can be achieved in the following manner, namely: first, the loss factor is negative, and then the result is used as the exponent of the natural constant e as the concentration attenuation coefficient of the selected volatile organic compound.

[0029] In specific implementation, the concentration information of the selected volatile organic compound is corrected for loss according to the concentration attenuation coefficient, and the correction result of the concentration information of the selected volatile organic compound can be obtained in the following manner, namely: first, a sampling moment is selected, and then, the concentration value of the selected volatile organic compound at each monitoring point at the sampling moment is obtained, and then all the concentration values ​​are multiplied by the loss factor, and the above steps are repeated to multiply the concentration values ​​of the selected volatile organic compound at each monitoring point at the remaining sampling moments by the loss factor, and finally, all the multiplication results are sorted in the order of the sampling moments as a set formed as the correction result of the concentration information of the selected volatile organic compound.

[0030] It should be noted that the concentration attenuation coefficient described in the present application refers to the concentration attenuation ratio caused by the loss of the corresponding volatile organic compounds in the atmospheric environment during the photochemical reaction process. The concentration attenuation coefficient can reflect the consumption rate of the corresponding volatile organic compounds in the atmospheric environment. The larger the concentration attenuation coefficient, the higher the consumption rate of the corresponding volatile organic compounds in the atmospheric environment, and the smaller the concentration attenuation coefficient, the lower the consumption rate of the corresponding volatile organic compounds in the atmospheric environment. In addition, the process of obtaining the correction result through loss correction in the present application can compensate for the concentration attenuation of volatile organic compounds caused by photochemical reactions, so that the measurement data is more in line with the actual emission conditions.

[0031] Wherein, in some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of a process for determining pollution potential shown in some embodiments of the present application. The pollution potential of ozone of each volatile organic compound in the atmospheric environment can be determined based on the correction result combined with the pollution diffusion capacity of each volatile organic compound, which can be achieved by the following steps: First, in 1021, the pollution diffusion coefficient of each volatile organic compound in the atmospheric environment is obtained; Then, in 1022, a reaction activity factor when each volatile organic compound is converted into ozone is determined by the pollution diffusion coefficient; Finally, in 1023, the ozone pollution potential of each volatile organic compound in the atmospheric environment is determined by using the reactivity factor and the correction result.

[0032] It should be noted that the pollution diffusion coefficient described in the present application characterizes the diffusion ability of the corresponding volatile organic compound in the atmospheric environment, and the pollution diffusion coefficient can be used to reflect the propagation range of the corresponding volatile organic compound in the atmospheric environment. The larger the pollution diffusion coefficient, the wider the propagation range of the corresponding volatile organic compound in the atmospheric environment, and the smaller the pollution diffusion coefficient, the smaller the propagation range of the corresponding volatile organic compound in the atmospheric environment. In a preferred embodiment, after obtaining the meteorological data of the target area, the turbulent diffusion coefficient in the target area can be determined by the turbulent diffusion formula in the prior art, and then the turbulent diffusion coefficient and the correction result of the corresponding volatile organic compound are used as input, and the pollution diffusion coefficient of the corresponding volatile organic compound in the atmospheric environment is generated in combination with the atmospheric turbulent diffusion model in the prior art, so as to obtain the pollution diffusion coefficient of each volatile organic compound in the atmospheric environment. In other embodiments, other methods can also be used to determine it, which is not limited here.

[0033] In a specific implementation, determining the reaction activity factor when each volatile organic compound is converted into ozone by using the pollution diffusion coefficient can be achieved in the following manner, namely: first, obtaining the reaction rate constant of the corresponding volatile organic compound, and then using the result of comparing the reaction rate constant with the pollution diffusion coefficient as the reaction activity factor when the corresponding volatile organic compound is converted into ozone, thereby obtaining the reaction activity factor when each volatile organic compound is converted into ozone.

[0034] In specific implementation, determining the ozone pollution potential of each volatile organic compound in the atmospheric environment through the reaction activity factor and the correction result can be achieved in the following manner, namely: first, selecting a volatile organic compound, obtaining the correction result of the concentration information corresponding to the volatile organic compound, determining the average value of the concentration values ​​at each monitoring point at all sampling times in the correction result, and then multiplying the result of the average value by the reflection activity factor as the ozone pollution potential of the volatile organic compound in the atmospheric environment, repeating the above steps to determine the ozone pollution potential of the remaining volatile organic compounds in the atmospheric environment.

[0035] It should be noted that the reactivity factor described in the present application represents the potential reaction ability of the corresponding volatile organic compound to be converted into ozone in the atmospheric environment, and the reactivity factor can be used to reflect the contribution of the corresponding volatile organic compound in the ozone generation process. The larger the reactivity factor, the higher the contribution of the corresponding volatile organic compound in the ozone generation process, and the smaller the reactivity factor, the lower the contribution of the corresponding volatile organic compound in the ozone generation process. In addition, the ozone pollution potential represents the ability of the corresponding volatile organic compound to form ozone through photochemical reaction in the atmospheric environment. The larger the ozone pollution potential, the stronger the ability of the corresponding volatile organic compound to form ozone through photochemical reaction in the atmospheric environment, and the smaller the ozone pollution potential, the weaker the ability of the corresponding volatile organic compound to form ozone through photochemical reaction in the atmospheric environment.

[0036] In step 103, multiple pollution sources in the target area are obtained, and pollution spectrum information of different pollution sources is collected through intelligent spectral sensors. Then, based on a machine learning algorithm and in combination with the pollution spectrum information of different pollution sources, a concentration contribution ratio of different pollution sources in the atmospheric environment when converted into ozone pollution is generated.

[0037] It should be noted that multiple pollution sources in the target area can be obtained based on the ability to cause ozone pollution to the atmospheric environment in the target area. Therefore, as a preferred embodiment, traffic emissions, industrial emissions and agricultural pollution can be used as multiple pollution sources in the target area of ​​this application; in addition, the intelligent spectral sensor in this application is a sensor for real-time detection of spectral information of pollution sources in the atmosphere. In some preferred embodiments, a Fourier transform infrared spectral sensor can be used as the intelligent spectral sensor in this application; wherein the intelligent spectral sensor is arranged at each monitoring point. In addition, the pollution spectral information in this application refers to the spectral absorption, scattering or emission characteristic data of the pollution source within a specific wavelength range, which is used to characterize the distribution pattern of different pollution sources.

[0038] In some embodiments, the following steps may be used to generate the concentration contribution ratio of different pollution sources in the atmospheric environment when they are converted into ozone pollution based on a machine learning algorithm combined with pollution spectrum information of different pollution sources: Determine the characteristic spectrum of each pollution source according to the pollution spectrum information of various pollution sources; The characteristic spectra of various pollution sources are combined with machine learning algorithms to generate the concentration contribution ratio of each pollution source in the atmospheric environment when it is converted into ozone pollution.

[0039] It should be noted that the characteristic spectrum described in the present application refers to a spectral reflection or absorption pattern that is unique to a pollution source, and the characteristic spectrum can be used to reflect the combination of various volatile organic compounds in the pollution source and their relative concentrations. For example, volatile organic compounds in automobile emissions, industrial waste gas, or traffic smog may have different absorption characteristics in different wavelength ranges, namely, characteristic spectrum. Therefore, as a preferred embodiment, determining the characteristic spectrum of each pollution source based on the pollution spectrum information of various pollution sources can be achieved in the following manner, namely, first, selecting a pollution source, obtaining the pollution spectrum information of the pollution source, and then, after the pollution spectrum information is standardized using the prior art, determining the coordination of the standardized result. Variance matrix, then, with the covariance matrix as input, the principal component analysis algorithm in the prior art is used to determine multiple eigenvalues ​​and corresponding eigenvectors of the covariance matrix, and all eigenvalues ​​are sorted in order of numerical value from large to small; in some preferred embodiments, the first three largest eigenvalues ​​can be selected as principal components, and then all principal components and corresponding eigenvectors are formed into a matrix, and the original data (pollution spectrum information) are projected onto these principal components to obtain the reduced-dimensional data, and the reduced-dimensional data is used as the characteristic spectrum of the pollution source, and the above steps are repeated to determine the characteristic spectrum of the remaining pollution sources. In other embodiments, other methods can be used to determine, which are not limited here.

[0040] In a specific implementation, the characteristic spectra of various pollution sources are combined with a machine learning algorithm to generate the concentration contribution ratio of each pollution source in the atmospheric environment when it is converted into ozone pollution. In some embodiments, a box model (MCM, Master Chemical Mechanism) can be used to establish an atmospheric ozone conversion model of the atmospheric environment, and then the atmospheric ozone conversion model is trained by a supervised learning algorithm (such as linear regression, classification algorithm) to calculate the concentration contribution ratio of each pollution source when it is converted into ozone pollution. When the pollution source is converted into ozone pollution, the box model (MCM, Master Chemical Mechanism) Mechanism) is a commonly used mathematical model of chemical reaction mechanism, which contains about 6700 organic substances and about 17000 chemical reactions, and can describe in detail the chemical process of atmospheric gas phase organic substances; by inputting initial conditions (such as characteristic spectra of various pollution sources), the box model can simulate the generation and change of ozone; in specific implementation, the supervised learning algorithm can use the Scikit-Learn tool in the machine learning library of Python software; first, after using the data processing technology in the existing technology (such as normalization, baseline correction, etc.) for the characteristic spectra of all pollution sources, the processing results are composed of the input feature matrix of the Scikit-Learn tool; after the concentration contribution ratio of each pollution source when converted into ozone pollution is used as the target variable of the Scikit-Learn tool, the Python software will output the concentration contribution ratio of each pollution source when converted into ozone pollution according to the input feature matrix.

[0041] It should be noted that the concentration contribution ratio described in the present application is a parameter used to measure the degree of influence of different pollution sources on ozone pollution. The concentration contribution ratio can be used to characterize the degree of influence of the pollution source on ozone pollution. The larger the concentration contribution ratio, the higher the degree of influence of the pollution source on ozone pollution. The smaller the concentration contribution ratio, the lower the degree of influence of the pollution source on ozone pollution. In addition, the present application uses a machine learning algorithm to automatically identify the complex relationship between the characteristics of the pollution source and ozone pollution based on big data, thereby providing a more accurate contribution ratio estimation. Other methods can also be used in other embodiments, which are not limited here.

[0042] In step 104, the ozone pollution load of each monitoring point is predicted according to the ozone pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, so as to obtain the pollution load degree of each monitoring point at different sampling times; In some embodiments, the ozone pollution load of each monitoring point is predicted based on the pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, and the pollution load degree of each monitoring point at different sampling times can be obtained by the following steps: Select a sampling time as the selected sampling time; Determine the amount of ozone generated at each monitoring point by selecting the concentration values ​​of various volatile organic compounds at each monitoring point at the sampling time and the ozone pollution potential of each volatile organic compound in the atmospheric environment; Determine the pollution load at each monitoring point at the selected sampling time based on all ozone generation and the concentration contribution ratio of the different pollution sources when converted into ozone pollution; Continue to determine the pollution load at each monitoring point during the remaining sampling moments.

[0043] In specific implementation, the ozone generation amount at each monitoring point can be determined by selecting the concentration values ​​of various volatile organic compounds at each monitoring point at the sampling time and the pollution potential of ozone of each volatile organic compound in the atmospheric environment. This can be achieved in the following manner, namely: first, a monitoring point is selected to obtain the concentration values ​​of various volatile organic compounds at the monitoring point, and then the concentration value of each volatile organic compound is multiplied by the pollution potential of ozone of the corresponding volatile organic compound, and then the results corresponding to all pollution degrees are added as the ozone generation amount at the monitoring point, and the above steps are repeated to determine the ozone generation amount at the remaining monitoring points.

[0044] It should be noted that in the present application, different monitoring points have a unique corresponding pollution source as the characteristic pollution source of the corresponding monitoring point. The characteristic pollution source refers to the pollution source that contributes most significantly or representatively to the concentration of volatile organic compounds at the monitoring point. As a preferred embodiment, the characteristic pollution source of the monitoring point can be set by the ratio of the concentration values ​​of various volatile organic compounds. For example, when the ratio of the concentration values ​​of benzene and toluene is large, the volatile organic compounds at the corresponding monitoring point come from solvent emissions, and the characteristic pollution source of the corresponding monitoring point is set to industrial emissions; when the ratio of the concentration values ​​of benzene and toluene is small, the volatile organic compounds at the corresponding monitoring point come from automobile exhaust, and the characteristic pollution source of the corresponding monitoring point is set to Traffic emissions can also be set by other methods in other embodiments, which are not limited here; therefore, in specific implementation, the pollution load degree at each monitoring point in the selected sampling time is determined based on all ozone generation and the concentration contribution ratio of the different pollution sources when converted into ozone pollution. It can be achieved in the following way, namely: first, a monitoring point is selected, and the characteristic pollution source of the monitoring point is set according to the concentration values ​​of various volatile organic compounds at the monitoring point, and then the concentration contribution ratio of the characteristic pollution source is obtained. Finally, the ozone generation at the monitoring point is divided by the concentration contribution ratio of the characteristic pollution source when converted into ozone pollution as the pollution load degree at the monitoring point, and the above steps are repeated to determine the pollution load degrees at the remaining monitoring points.

[0045] It should be noted that the ozone generation amount mentioned in the present application refers to the total amount of ozone converted into ozone by various precursor volatile organic compounds in the atmospheric environment through photochemical reactions at a specific monitoring point, reflecting the ozone generation capacity at the corresponding monitoring point. The larger the ozone generation amount, the stronger the ozone generation capacity at the corresponding monitoring point, and the smaller the ozone generation amount, the weaker the ozone generation capacity at the corresponding monitoring point. In addition, the pollution load degree refers to the ozone pollution pressure level at the monitoring point, and the pollution load degree can be used to characterize the load degree of ozone pollution at the corresponding monitoring point. The larger the pollution load degree, the higher the load degree of ozone pollution at the corresponding monitoring point, and the smaller the pollution load degree, the lower the load degree of ozone pollution at the corresponding monitoring point.

[0046] In step 105, the atmospheric environment of the target area is treated in different zones based on all pollution loads.

[0047] In some embodiments, the following steps may be used to perform zoning management of the atmospheric environment in the target area based on all pollution loads: The atmospheric environment of the target area at the corresponding sampling time is divided into multiple pollution load areas according to the pollution load degree of all monitoring points at different sampling times; The atmospheric environment of the target area is zoned and managed based on all pollution load areas.

[0048] In specific implementation, the atmospheric environment of the target area at the corresponding sampling moment is divided into multiple pollution load areas by the pollution load degree of all monitoring points at different sampling moments. The following method can be used, namely: first, a sampling moment is selected to obtain the pollution load degree of all monitoring points at the sampling moment. Then, the absolute value of the difference between the pollution load degrees of every two monitoring points is used as the similarity index between the corresponding two monitoring points. Then, all similarity indexes are used as input. Through the K-means clustering algorithm in the prior art, all monitoring points at the sampling moment are divided into multiple point clusters. Then, the area composed of each point cluster in the target area is used as the corresponding pollution load area, so that the atmospheric environment of the target area at the sampling moment is divided into multiple pollution load areas. The above steps are repeated to determine the multiple pollution load areas corresponding to the remaining sampling moments.

[0049] In specific implementation, the zoning management of the atmospheric environment of the target area based on all pollution load areas can be achieved in the following manner, namely: first, a sampling time is selected to obtain all pollution load areas corresponding to the sampling time; then, as a preferred embodiment, based on the spatial distribution information of all pollution load areas at the sampling time, the spatial interpolation algorithm in the geographic information system can be called to estimate the pollution load degree of the area not covered by the monitoring point in the target area, and generate a complete spatial distribution map of the pollution load degree; then, in combination with the geographical information such as the geographical boundaries, administrative divisions, and road distribution of the target area, the boundaries of the pollution load area are adjusted to make it conform to the diffusion characteristics of the actual atmospheric environment, and the adjusted pollution load area is mapped to the geographic information system of the target area; finally, the spatial distribution map of the pollution load degree at the sampling time, the pollution load area division results and the corresponding geographic information are integrated to generate the real-time monitoring information of the atmospheric environment of the target area at the sampling time, and store or visualize it; repeat the above steps to determine the real-time monitoring information of the atmospheric environment of the target area corresponding to the remaining sampling times, and then the atmospheric environment of the target area is zoned and managed through the real-time monitoring information.

[0050] It should be noted that after determining the real-time monitoring information, the present application obtains the real-time monitoring information at each sampling moment (including the spatial distribution map of the pollution load and the results of the pollution load regional division). Then, based on the pollution load regional division results at the corresponding sampling moment, combined with historical monitoring data and pollution evolution trends, the pollution types, volatile organic compound components and main pollution sources of each region are classified and labeled; then, combined with the meteorological data, topographic information and volatile organic compound diffusion model in the geographic information system, the pollution diffusion trend of different pollution load areas is analyzed, and the volatile organic compounds in different wind directions, wind speeds, and wind speeds are predicted. The propagation path under meteorological conditions such as temperature and humidity is determined to determine the key control areas. Subsequently, the corresponding control measures are matched for different pollution load areas according to the control strategy library of different pollution sources, such as adopting exhaust gas treatment optimization plans for industrial emission sources, adopting technologies to reduce volatile organic compound emissions for agricultural emission sources, and implementing traffic restrictions or optimizing traffic flow for traffic pollution sources. Finally, the pollution control plan at the sampling moment is integrated with the geographic information system to form a zoning control plan for the target area, which is visualized or output to the atmospheric environment control system to guide actual control actions, thereby achieving zoning control of the atmospheric environment.

[0051] It should be noted that the pollution load area mentioned in this application refers to a dynamic spatial unit divided according to the environmental characteristics of different functional areas in the target area (such as urban blocks, industrial areas, parks, mountainous areas, etc.) and combined with the similarity of the pollution load degrees of each monitoring point. In addition, the real-time monitoring information represents the spatiotemporal mapping result of the atmospheric pollution status of the target area generated by combining the pollution load area and the geographic information system, which includes the spatial distribution of pollution load degrees, the division of pollution load areas, and the influence of geographical environmental factors, reflecting the overall dynamic characteristics of atmospheric pollution in the target area. This application conducts pollution trend analysis and environmental management decisions on the atmospheric environment of the target area through the real-time monitoring information.

[0052] In addition, in another aspect of the present application, in some embodiments, the present application provides an atmospheric governance monitoring system, referring to Figure 4 , which is a schematic diagram of the structure of an air governance monitoring system according to some embodiments of the present application, the air governance monitoring system 200 includes: a collection module 201, a processing module 202 and an execution module 203, which are described as follows: The acquisition module 201 in the present application is mainly used to set multiple monitoring points in the atmospheric environment of different functional zones in the target area, and then collect the concentration information of different volatile organic compounds at all sampling times at each monitoring point through the intelligent pollutant sensor; Processing module 202, in the present application, the processing module 202 is mainly used to determine the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound; In addition, the processing module 202 in the present application is also used to obtain multiple pollution sources in the target area, collect pollution spectrum information of different pollution sources through intelligent spectrum sensors, and then generate the concentration contribution ratio of different pollution sources in the atmospheric environment when converted into ozone pollution based on the machine learning algorithm and the pollution spectrum information of different pollution sources; In addition, the processing module 202 in the present application is also used to predict the ozone pollution load of each monitoring point according to the pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, and obtain the pollution load degree of each monitoring point at different sampling times; Execution module 203, in this application, execution module 203 is mainly used to perform zoning management of the atmospheric environment of the target area based on all pollution loads.

[0053] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned atmospheric governance monitoring method.

[0054] In some embodiments, reference Figure 5 , which is an internal structure diagram of a computer device for implementing an air governance monitoring method according to some embodiments of the present application. The air governance monitoring method in the above embodiment can be Figure 5 The computer device 300 shown in the figure is implemented, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303 and at least one communication interface 304.

[0055] The processor 301 may be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC) or one or more for controlling the execution of the atmospheric governance monitoring method in the present application.

[0056] The communication bus 302 is used to transmit information between the above components.

[0057] The memory 303 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 through the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0058] Among them, the memory 303 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The air governance monitoring method in the above embodiment can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0059] The communication interface 304 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0060] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-core (singleCPU) processor or a multi-core (multiCPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0061] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0062] In addition, the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned atmospheric governance monitoring method is implemented.

[0063] In summary, in the atmospheric governance monitoring method and system disclosed in the embodiment of the present application, multiple monitoring points are set in the atmospheric environment of different functional zones in the target area, and then the concentration information of different volatile organic compounds at all sampling times at each monitoring point is collected through intelligent pollutant sensors; the pollution potential of ozone of each volatile organic compound in the atmospheric environment is determined based on the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound; multiple pollution sources in the target area are obtained, and the pollution spectrum information of different pollution sources is collected through intelligent spectral sensors, and then the concentration contribution ratio of different pollution sources in the atmospheric environment when converted into ozone pollution is generated based on the machine learning algorithm and the pollution spectrum information of different pollution sources; the ozone pollution load of each monitoring point is predicted according to the pollution potential of ozone of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, and the pollution load degree of each monitoring point at different sampling times is obtained; the atmospheric environment of the target area is zoned for governance based on all pollution load degrees; and multi-factor nonlinear modeling of the atmospheric environment can be realized.

[0064] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0065] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for monitoring air pollution control, characterized in that: The steps include: Set up multiple monitoring points in the atmospheric environment of different functional areas in the target area, and then collect the concentration information of different volatile organic compounds at all sampling times at each monitoring point through intelligent pollutant sensors; Determining the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound; Acquire multiple pollution sources in the target area, collect pollution spectrum information of different pollution sources through intelligent spectral sensors, and then generate the concentration contribution ratio of different pollution sources in the atmospheric environment when converted into ozone pollution based on machine learning algorithms and pollution spectrum information of different pollution sources; According to the ozone pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, the ozone pollution load of each monitoring point is predicted to obtain the pollution load degree of each monitoring point at different sampling times; The atmospheric environment in the target area is zoned and managed based on all pollution loads.

2. The method according to claim 1, characterized in that Determining the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound specifically includes: Determine the loss factor for each volatile organic compound in the atmosphere when it undergoes photochemical reactions; Performing loss correction on the concentration information of each volatile organic compound according to the loss factor; The ozone pollution potential of each volatile organic compound in the atmospheric environment is determined according to the calibration result and in combination with the pollution diffusion capacity of each volatile organic compound.

3. The method according to claim 2, characterized in that Performing loss correction on the concentration information of each volatile organic compound according to the loss factor specifically includes: Selecting a volatile organic compound as the selected volatile organic compound; determining a concentration attenuation coefficient of the selected volatile organic compound according to a loss factor corresponding to the selected volatile organic compound; Performing loss correction on the concentration information of the selected volatile organic compound according to the concentration attenuation coefficient to obtain a correction result of the concentration information of the selected volatile organic compound; Continue to perform loss correction on the concentration information of the remaining volatile organic compounds to obtain a correction result of the concentration information of the remaining volatile organic compounds.

4. The method according to claim 2, characterized in that Determining the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the correction result and the pollution diffusion capacity of each volatile organic compound specifically includes: Obtaining the pollution diffusion coefficient of each volatile organic compound in the atmospheric environment; Determining the reaction activity factor when each volatile organic compound is converted into ozone by the pollution diffusion coefficient; The ozone pollution potential of each volatile organic compound in the atmospheric environment is determined by the reactivity factor and the correction result.

5. The method according to claim 1, characterized in that Based on the machine learning algorithm, the pollution spectrum information of different pollution sources is combined to generate the concentration contribution ratio of different pollution sources in the atmospheric environment when converted into ozone pollution. Specifically, it includes: Determine the characteristic spectrum of each pollution source according to the pollution spectrum information of various pollution sources; The characteristic spectra of various pollution sources are combined with machine learning algorithms to generate the concentration contribution ratio of each pollution source in the atmospheric environment when it is converted into ozone pollution.

6. The method according to claim 1, characterized in that The ozone pollution load of each monitoring point is predicted according to the pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when they are converted into ozone pollution, and the pollution load degree of each monitoring point at different sampling times is obtained, which specifically includes: Select a sampling time as the selected sampling time; Determine the amount of ozone generated at each monitoring point by selecting the concentration values ​​of various volatile organic compounds at each monitoring point at the sampling time and the ozone pollution potential of each volatile organic compound in the atmospheric environment; Determine the pollution load at each monitoring point at the selected sampling time based on all ozone generation and the concentration contribution ratio of the different pollution sources when converted into ozone pollution; Continue to determine the pollution load at each monitoring point during the remaining sampling moments.

7. The method according to claim 1, characterized in that Based on all pollution loads, the atmospheric environment of the target area is zoned and managed, including: The atmospheric environment of the target area at the corresponding sampling time is divided into multiple pollution load areas according to the pollution load degree of all monitoring points at different sampling times; The atmospheric environment of the target area is zoned and managed based on all pollution load areas.

8. An air governance monitoring system, characterized in that: include: The acquisition module is used to set multiple monitoring points in the atmospheric environment of different functional areas of the target area, and then collect the concentration information of different volatile organic compounds at all sampling times at each monitoring point through intelligent pollutant sensors; A processing module, used for determining the ozone pollution potential of each volatile organic compound in the atmospheric environment according to the concentration information of each volatile organic compound combined with the pollution diffusion capacity of the corresponding volatile organic compound; The processing module is also used to obtain multiple pollution sources in the target area, collect pollution spectrum information of different pollution sources through intelligent spectrum sensors, and then generate concentration contribution ratios of different pollution sources in the atmospheric environment when converted into ozone pollution based on machine learning algorithms and pollution spectrum information of different pollution sources; The processing module is further used to predict the ozone pollution load of each monitoring point according to the ozone pollution potential of each volatile organic compound in the atmospheric environment and the concentration contribution ratio of the different pollution sources when converted into ozone pollution, so as to obtain the pollution load degree of each monitoring point at different sampling times; The execution module is used to perform zoning management of the atmospheric environment in the target area based on all pollution loads.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the atmospheric governance monitoring method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the atmospheric governance monitoring method according to any one of claims 1 to 7 are implemented.

Images