Air quality management effect evaluation method based on machine learning algorithm

Abstract

The invention relates to an air quality management effect evaluation method based on a machine learning algorithm. The method comprises the following steps: S1, acquiring a pollutant local source emission intensity indication variable; s2, constructing a pollutant machine learning model, taking the pollutant meteorological standardized concentration as an indication variable of local pollutant emission intensity, and incorporating the indication variable into a machine learning training pollutant regression prediction model; s2, evaluating the contribution of pollutant emission change and meteorological conditions to environmental concentration change, determining a benchmark reference time period of pollutant concentration change of a to-be-evaluated time period, and performing pollutant concentration simulation under different emission and meteorological scenes based on a control variable method by using the pollutant machine learning model constructed in the step S2, the environmental concentration of the pollutant in the discharge intensity of the to-be-evaluated year under the meteorological condition of the benchmark reference year is obtained, the difference value between the predicted environmental concentration and the actual monitoring concentration of the evaluation year is used as contribution, and quantitative evaluation of the pollutant concentration change caused by pollutant emission reduction in the to-be-evaluated year compared with the benchmark year is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of air pollution prevention and control management, and in particular to an air quality management effectiveness evaluation method based on a machine learning algorithm. Background Art

[0002] The evaluation of the effectiveness of air quality management is to answer the question of how much the change in regional or urban air quality is contributed by pollution emission control ("human efforts") and changes in meteorological conditions ("help from the weather"). Traditionally, the evaluation of the effectiveness of air quality management mainly uses the scenario simulation method of the air quality model, such as WRF-CMAQ (The Weather Research and Forecasting Model-Community Multiscale Air Quality Model), which simulates the environmental concentration of air pollutants based on the atmospheric pollution source emission inventory data. This method uses the actual baseline reference year pollution emission inventory data and the meteorological conditions of the actual year to simulate the switch closure simulation experiment, obtain the simulated value of the pollutant concentration under the baseline year emission conditions, and compare the predicted value with the actual value to judge the quality of the simulation results. When the model reaches the expected accuracy, it further uses the pollution source emission inventory data of the target year to be evaluated through scenario simulation to simulate the environmental concentration of pollution emissions in the target evaluation year under the baseline year meteorology. Under the same meteorological conditions, that is, under the meteorological conditions of the base year, the difference between the average annual environmental concentration of pollutants emitted in the assessment year simulated by the model and the average annual observed concentration in the base year is the part of the change in ambient air quality caused by pollution reduction during the assessment period (the contribution of "human efforts"). The contribution of meteorological influence ("the help of nature") can be obtained by subtracting the environmental concentration of pollutants simulated by the model under the meteorological conditions of the base year and the pollution emission inventory of the assessment year from the average annual observed concentration of the assessment target year.

[0003] The air quality model establishes a mathematical model that describes the relationship between pollution source emissions and pollutant concentrations based on the partial differential equations of the atmospheric physical and chemical mechanisms. It can reflect the impact of pollution source emission reduction and weather and meteorological changes on air quality, but the model results are affected by the uncertainty of the initial meteorological field, the imperfection of the chemical mechanism, and the accuracy and timeliness of the pollution emission inventory.

[0004] Given that changes in air quality are affected by both pollution source emissions and meteorological factors, the temporal changes in pollutants are considered to be a function of pollution source strength and meteorological factors. Therefore, a statistical model can be established using meteorological monitoring data and explanatory variables such as pollution source strength and pollutant concentration. The difficulty of this method is that it is difficult to obtain indicator variables that can fully characterize the pollution source strength. In recent years, meteorological standardization technology based on random forest regression algorithm has been widely used. This method establishes a pollutant concentration prediction model based on historical observation data. For any given moment of pollutants, its environmental concentration under different meteorological conditions is predicted, and the average of multiple concentrations is taken, thereby eliminating the disturbance of meteorological factors. The temporal changes in the meteorological standardized concentration of pollutants shield the interference of different meteorological conditions, thereby reflecting the changes in the intensity of local pollution emissions. Summary of the invention

[0005] The present invention aims to utilize meteorologically standardized pollutant time series to characterize the changes in local emission source intensity, incorporate them into statistical models together with meteorological parameters, and predict the environmental concentrations of pollutants in the evaluation period under baseline meteorology or baseline emission intensity through the control variable method. The differences are compared, and the contributions of local pollution emission control ("human efforts") and changes in meteorological conditions ("help from the weather") are evaluated, thus constructing a data-driven air quality management effectiveness evaluation method.

[0006] To achieve the above object, the present invention provides an air quality management effectiveness evaluation method based on a machine learning algorithm, comprising the following steps:

[0007] S1, obtain the indicator variables of local source emission intensity of pollutants, including:

[0008] S101: Prepare the model training data set, collect and select the hourly monitored SO in the target area within two years. 2 、NO 2 ,CO,O 3 , PM10, PM2.5 concentration time series data and environmental meteorological parameters, and time trend variable data, where the time trend variables are used to characterize pollution emissions or atmospheric physical and chemical processes with periodic changes;

[0009] S102, training a prediction model, for a selected air pollutant, using a regression algorithm to predict the pollutant concentration (C t ) and environmental meteorological parameters (M i ) and time trend variables (T j ) was used to model the pollutant concentrations predicted by the model and the actual monitored concentrations. The correlation coefficient and root mean square error were calculated to evaluate the model fitting effect.

[0010] where ∈ t is the model residual term. For any time t, the model (f t ) The predicted pollutant concentration is C t , then:

[0011] C t =f t (M i,t , T j，t )+∈ t ,

[0012] i∈(T, RH, BLH,...,I); j∈(hour, day,..., Unix time),

[0013] Where i represents the meteorological parameter to be modeled; j represents the time trend variable;

[0014] S103, meteorological standardization processing, the interference of meteorological conditions that change with time series on pollutant concentration is standardized to the average meteorological conditions, and the trained random forest pollutant prediction model f is used to predict the concentration of pollutants under N randomly selected historical meteorological conditions for the pollutants at time t, and the algebraic mean (C t，norm ), that is, the meteorological standardized concentration of pollutants at time t is:

[0015]

[0016] In the formula, k is the kth sample of the selected fixed N groups of historical meteorological data, is the pollutant concentration predicted by the model under the kth historical meteorological data of the selected fixed N groups;

[0017] S2, build a pollutant machine learning model, take the pollutant meteorological standardized concentration as the indicator variable of local pollution emission intensity, and incorporate it into the machine learning training pollutant regression prediction model, including:

[0018] S201, prepare the model training data set, the target area hourly monitored SO 2 、NO 2 ,CO,O 3 , PM10, PM2.5 six air pollutant concentration time series data and environmental meteorological parameters, time trend variable data;

[0019] S202, training the prediction model, using regression algorithm to compare the pollutant concentration and environmental meteorological parameters (M i ) and meteorological normalized concentration (C t，norm ) to model, ∈ tis the model residual term. A pollutant prediction model is retrained with all hourly data sets for two full natural years. For any time t, the model (f′ t ) The predicted pollutant concentration is C′ t :

[0020] C′ t =f′ t (M i，t , C t，norm )+∈ t ,

[0021] i∈(T, RH, BLH, ..., I), i represents the modeled meteorological parameters listed;

[0022] S3, evaluate the contribution of changes in pollution emissions and meteorological conditions to changes in environmental concentrations, determine the baseline reference period for changes in pollutant concentrations in the proposed evaluation period, use the pollutant machine learning model constructed in step S2, simulate pollutant concentrations under different emission and meteorological scenarios based on the control variable method, and obtain the environmental concentration of pollutants under the meteorological conditions of the baseline reference year at the emission intensity in the year to be evaluated. Take the difference between the predicted environmental concentration and the actual monitored concentration in the evaluation year as the contribution, and obtain a quantitative assessment of the change in pollutant concentration caused by pollution reduction in the proposed evaluation year compared to the baseline year.

[0023] Preferably, the environmental meteorological parameters include ground temperature, relative humidity, wind speed, wind direction, air pressure, radiation intensity, mixing layer height, total cloud cover, precipitation, trajectory category and trajectory length.

[0024] Preferably, the time trend variables include a timestamp, a lunar day, a solar day, a day of the week, and a daily hour sequence.

[0025] Preferably, the regression algorithm is a random forest algorithm, a neural network algorithm, a gradient regression tree algorithm or an extreme gradient boosting tree algorithm.

[0026] Preferably, the environmental meteorological parameters include a variety of easily accessible meteorological observation data or meteorological reanalysis data, and the variables used to characterize the emission source intensity are any air-related data related to pollution emission activities.

[0027] Preferably, assessing the contribution of changes in pollution emissions and meteorological conditions to changes in ambient concentrations includes:

[0028] The second year or the second month is taken as the evaluation year (eval), and the first year or the first month is taken as the reference year (base). The model f′ constructed in step S2 is used to predict the environmental concentration f′ (M) of the pollutant under the meteorological conditions of the first year or the first month of the reference year and the emission intensity of the second year or the second month. base , C norm，eval), then the difference between the ambient concentration predicted by the model and the actual monitored concentration in the first year or the first month is the contribution ΔC to the change in pollution emission intensity. emi for:

[0029] ΔC emi =[C eval -C base ]-[C eval -f′(M base , C norm，eval )]

[0030] =f′(M base , C norm，eval )-C base

[0031] The meteorological data of the second year or the second month are replaced with the meteorological data of the first year or the first month, and the model f′ constructed in step S2 is used to predict the environmental concentration f′ (M) of the pollutant under the meteorological conditions of the first year or the first month and the emission intensity of the second year or the second month. base , C norm，eval ), then the difference between the ambient concentration predicted by the model and the actual monitored concentration in the second year or the second month is the contribution of the meteorological condition change ΔC met for:

[0032] ΔC met =C eval -f′(M base , C norm，eval )

[0033] In the formula, C base is the average annual environmental observation concentration of pollutants in the base year, C eval To assess the annual average environmental monitoring concentrations of annual pollutants.

[0034] Based on the above technical solution, the advantages of the present invention are:

[0035] Compared with the traditional air quality model assessment method that relies on the data of pollution source emission inventory and has high technical difficulty in operation, the technical method constructed by the present invention has a simple principle, convenient operation and easy implementation. It only requires historical monitoring data of environmental meteorological parameters and air pollutants. It can provide a simple technical method for objectively evaluating the effectiveness of localized air quality management on a time scale of hours, and further provide support technology for decision-making required for the evaluation of environmental air quality standards and the effectiveness of urban and regional air quality management measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0037] Figure 1 A schematic diagram of the steps of the air quality management effectiveness evaluation method of the present invention;

[0038] Figure 2 Schematic diagram of steps to obtain indicator variables of local source emission intensity of pollutants;

[0039] Figure 3 The figures are the changes in PM2.5 concentration and the control effectiveness evaluation results between 2015 and 2023 according to the embodiments of the present invention. DETAILED DESCRIPTION

[0040] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments.

[0041] The present invention provides an air quality management effectiveness evaluation method based on a machine learning algorithm, taking the evaluation of the changes in air pollutant concentrations caused by pollution reduction and meteorological factors in two natural years as an example, which mainly includes the following three steps: Figure 1 As shown, the following steps are included:

[0042] S1, obtain the indicator variable of the emission intensity of the local source of pollutants. The present invention is based on the principle of back-calculating the emission intensity of air pollutants based on the monitored concentration. The air pollutant concentration information includes the pollution emission intensity information and meteorological information. By "stripping" the meteorological information from the change of air pollutant concentration through meteorological standardization technology, the change information of pollution emission intensity can be obtained.

[0043] Specifically, if Figure 2 As shown, including:

[0044] S101: Prepare the model training data set, collect and select the hourly monitored SO in the target area within two years. 2 、NO 2 ,CO,O 3 , PM10, PM2.5 concentration time series data and environmental meteorological parameters, as well as time trend variable data. The time trend variables are used to characterize pollution emissions or atmospheric physical and chemical processes with periodic changes.

[0045] Specifically, based on the six pollutants (SO 2 、NO 2 ,CO,O 3, PM10, PM2.5) concentration data, as well as synchronized environmental meteorological parameters and time trend variables. Environmental meteorological parameters include ground temperature, relative humidity, wind speed, wind direction, air pressure, radiation intensity, mixing layer height, total cloud cover, precipitation, trajectory category and trajectory length. Time trend variables are used to characterize pollution emissions or atmospheric physical and chemical processes with periodic changes. For example, the number of days in the Gregorian calendar, the number of days of the week, and the hourly time series of each day are used to indicate pollution source emission activities with seasonal, weekly-daily and daily change patterns within the annual time scale. The long-term interdecadal pollution emission change trend is indicated by a linearly increasing variable hour by hour, such as Unix time (timestamp, that is, the accumulated seconds from midnight on January 1, 1970, Greenwich Mean Time). During the evaluation process, the evaluation period can use a full year of data or a month of hourly average data. In principle, the evaluation period has the same time span as the benchmark period and the amount of data is as small as possible to meet the training requirements of the machine learning model.

[0046] S102, training a prediction model, for a selected air pollutant, using a regression algorithm to predict the pollutant concentration (C t ) and environmental meteorological parameters (M i ) and time trend variables (T j ) was used to build a pollutant prediction model using the entire hourly data set for two full natural years. The consistency and difference between the pollutant concentrations predicted by the model and the actual monitored concentrations were compared, and the correlation coefficient and root mean square error were calculated to evaluate the model fitting effect.

[0047] where ∈ t is the model residual term. For any time t, the model (f t ) The predicted pollutant concentration is C t , then:

[0048] C t =f t (M i,t , T j，t )+∈ t ,

[0049] i∈(T, RH, BLH,...,I); j∈(hour, day,..., Unix time),

[0050] Where i represents the meteorological parameter to be modeled; j represents the time trend variable.

[0051] S103, meteorological standardization. After the pollutant prediction model is trained, meteorological standardization is performed to standardize the interference of meteorological conditions that change with time series on pollutant concentrations to the average meteorological conditions to eliminate the disturbance of meteorological conditions that reflects the change in pollution emission intensity. Using the trained random forest pollutant prediction model f, for the pollutants at time t, the concentration of pollutants under N randomly selected historical meteorological conditions is predicted, and the algebraic mean (C t，norm ). The N randomly selected groups of meteorological data are extracted from the historical environmental meteorological data in the original training data set. According to the law of large numbers and the central limit theorem, when N is large enough, the meteorological disturbance in the pollutant concentration at that moment will tend to 0. In theory, the change in the meteorological standardized concentration of pollutants in time series can reflect the change in the intensity of pollution emissions.

[0052] The existing technology usually extracts 300-1000 groups of random meteorological samples. The larger the meteorological samples, the longer the calculation time. In order to meet the timeliness requirement, the disturbance of meteorology in time series can be eliminated with the smallest possible historical meteorological samples. The present invention proposes to use the trained pollutant random forest model to predict the environmental concentration of pollutants at time t under a fixed set of historical meteorological conditions (non-random), such as 24 groups of hourly meteorological conditions fixed on a certain historical day, and take the algebraic mean as the representation of emission intensity.

[0053] The present invention normalizes the interference of meteorological conditions that change with time series on pollutant concentration to the average meteorological conditions, and uses the trained random forest pollutant prediction model f to predict the concentration of pollutants at time t under N randomly selected historical meteorological conditions, and takes the algebraic mean (C t，norm ), that is, the meteorological standardized concentration of pollutants at time t is:

[0054]

[0055] In the formula, k is the kth sample of the selected fixed N groups of historical meteorological data, It is the pollutant concentration predicted by the model under the kth historical meteorological data of the selected fixed N groups.

[0056] S2, build a pollutant machine learning model, take the pollutant meteorological standardized concentration as the indicator variable of local pollution emission intensity, and incorporate it into the machine learning training pollutant regression prediction model, including:

[0057] S201, prepare the model training data set, the target area hourly monitored SO 2 、NO 2 ,CO,O 3, PM10, PM2.5 concentration time series data and environmental meteorological parameters, time trend variable data. The time trend variable (T j ) is replaced by the meteorological standardized concentration, i.e., C t，norm .

[0058] S202, training the prediction model, using regression algorithm to compare the pollutant concentration and environmental meteorological parameters (M i ) and meteorological normalized concentration (C t，norm ) is used to model, ∈t is the model residual term, and a pollutant prediction model is retrained with all hourly data sets for two full natural years. For any time t, the model (f′ t ) The predicted pollutant concentration is C′ t :

[0059] C′ t =f′ t (M i，t , C t，norm )+∈ t ,

[0060] i∈(T, RH, BLH, ..., I), i represents the modeled meteorological parameters listed;

[0061] S3, evaluate the contribution of changes in pollution emissions and meteorological conditions to changes in environmental concentrations, determine the baseline reference period for changes in pollutant concentrations in the proposed evaluation period, use the pollutant machine learning model constructed in step S2, simulate pollutant concentrations under different emission and meteorological scenarios based on the control variable method, and obtain the environmental concentration of pollutants under the meteorological conditions of the baseline reference year at the emission intensity in the year to be evaluated. Take the difference between the predicted environmental concentration and the actual monitored concentration in the evaluation year as the contribution, and obtain a quantitative assessment of the change in pollutant concentration caused by pollution reduction in the proposed evaluation year compared to the baseline year.

[0062] Preferably, assessing the contribution of changes in pollution emissions and meteorological conditions to changes in ambient concentrations includes:

[0063] The second year or the second month is taken as the evaluation year (eval), and the first year or the first month is taken as the reference year (base). The model f′ constructed in step S2 is used to predict the environmental concentration f′ (M) of the pollutant under the meteorological conditions of the first year or the first month of the reference year and the emission intensity of the second year or the second month. base , C norm,eval ), then the difference between the ambient concentration predicted by the model and the actual monitored concentration in the first year or the first month is the contribution ΔC to the change in pollution emission intensity. emi for:

[0064] ΔCemi =[C eval -C base ]-[C eval -f′(M base , C norm,eval )]

[0065] =f′(M base , C norm，eval )-C base

[0066] The meteorological data of the second year or the second month are replaced with the meteorological data of the first year or the first month, and the model f′ constructed in step S2 is used to predict the environmental concentration f′ (M) of the pollutant under the meteorological conditions of the first year or the first month and the emission intensity of the second year or the second month. base , C norm，eval ), then the difference between the ambient concentration predicted by the model and the actual monitored concentration in the second year or the second month is the contribution of the meteorological condition change ΔC met for:

[0067] ΔC met =C eval -f′(M base , C norm,eval )

[0068] In the formula, C base is the average annual environmental observation concentration of pollutants in the base year, C eval To assess the annual average environmental monitoring concentrations of annual pollutants.

[0069] Preferably, the regression algorithm is a random forest algorithm, a neural network algorithm, a gradient regression tree algorithm or an extreme gradient boosting tree algorithm.

[0070] Preferably, the environmental meteorological parameters include a variety of easily accessible meteorological observation data or meteorological reanalysis data, and the variables used to characterize the emission source intensity are any air-related data related to pollution emission activities, including but not limited to motor vehicle flow, key source pollutant emission monitoring data, etc.

[0071] Current statistical modeling has always lacked indicator variables that effectively characterize changes in pollution emission intensity, limiting the application of machine learning algorithms to evaluate the effectiveness of pollution control. This paper uses the meteorological standardized concentration of pollutants as an indicator variable of "emission source intensity" and proposes an air quality management effectiveness evaluation method based on a machine learning algorithm under the control variable method.

[0072] Taking the PM2.5 continuous monitoring data of an air quality monitoring station in Tianjin from 2015 to 2023 as an example, the specific implementation method includes the following steps:

[0073] Step 101, obtain the meteorological standardized concentration of PM2.5. Collect and organize the hourly monitoring concentration data of PM2.5 at the site from 2015 to 2023 and the synchronized environmental meteorological parameters (ground temperature, relative humidity, wind speed, wind direction, air pressure, radiation intensity, mixing layer height, total cloud cover, precipitation, air mass trajectory category and length) and time trend variables (timestamp, number of days in the lunar calendar, number of days in the solar calendar, number of days in the week, and daily hourly time series). The selected environmental meteorological variables may include a variety of easily accessible meteorological observation data or meteorological reanalysis data, and the variables used to characterize the intensity of emission sources may be air-related data related to pollution emission activities, including but not limited to motor vehicle flow, key source pollutant emission monitoring data, etc. After the data collection is completed, the deviation caused by the variation of meteorological covariates in the pollutant concentration time series is adjusted to obtain the meteorological standardized concentration of pollutants as the subsequent "emission intensity" modeling indicator variable.

[0074] Step 102, replace the time variable contained in the pollutant meteorological standardized modeling data set with the "emission variable", that is, the meteorological standardized concentration of the pollutant. The base year data is selected as a new modeling data set, and a new machine learning random forest modeling is performed to construct the response relationship between emissions, meteorology and pollutant observed concentrations under the base year scenario. The above operations can be implemented in the Python environment through the scikit-learn library machine learning random forest modeling code (it can also be a neural network, lightweight gradient boosting machine (LightGBM), extreme gradient boosting tree (XGBoost) and other regression algorithms), based on the root mean square error (RMSE) and correlation coefficient (R 2 ) to judge the quality of model fitting.

[0075] Step 103, using the machine learning model constructed in step 102 to predict the environmental concentration of pollutant emission intensity under the meteorological conditions of the base year 2015 and other years. The emission intensity of the base reference year is replaced by the meteorological standardized concentration (emission intensity) of the corresponding pollutant in each year to be evaluated, and the remaining modeling variables are retained as the base reference year. This completes the reconstruction of the data set in a virtual scenario where the emission intensity is based on the evaluation year and the meteorological conditions are based on the base reference year. Based on the reconstructed data, the environmental concentration of the pollutant emission intensity in the year to be evaluated under the meteorological conditions of the base reference year is predicted by the machine learning model constructed above. Under the comparable meteorological conditions of the base year, a quantitative assessment of the change in PM2.5 concentration caused by pollution reduction in the proposed evaluation year compared to the base year is achieved, and the contribution of the "sky help" meteorological conditions is also calculated. The final result is as follows Figure 3 shown.

[0076] exist Figure 3In the study, PM2.5 concentration decreased by 26.6 micrograms per cubic meter between 2015 and 2023. Among them, the PM2.5 concentration reduced by 20.3 micrograms per cubic meter due to human efforts, accounting for 76% of the PM2.5 concentration reduction, and the effect of emission reduction and pollution control was remarkable; meteorological factors reduced PM2.5 concentration by 6.3 micrograms per cubic meter, and the contribution of "the help of the sky" to the PM2.5 concentration reduction was 24%. Based on the above method, the quantitative contribution of air quality management effectiveness evaluation was obtained.

[0077] The method of the present invention has a simple principle and fast calculation, which breaks through the shortcomings of traditional air quality models, such as the accuracy and timeliness of pollution source emission inventories, and the difficulty of calculation and operation. The present invention can be directly applied to multiple atmospheric environment management application scenarios such as the effectiveness evaluation of the implementation of ambient air quality standards, emergency evaluation of heavy pollution weather, and air quality assurance evaluation of major national events, and has important application and promotion value.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or some technical features can be replaced by equivalents without departing from the spirit of the technical solution of the present invention, which should be included in the scope of the technical solution for protection of the present invention.

Claims

1. A method for evaluating the effectiveness of air quality management based on a machine learning algorithm, characterized in that: The steps include: S1, obtain the indicator variables of local source emission intensity of pollutants, including: S101, prepare a model training data set, collect and select the time series data of the concentration of six air pollutants, SO2, NO2, CO, O3, PM10, and PM2.5, and environmental meteorological parameters and time trend variable data monitored hourly in the target area within two years, wherein the time trend variable is used to characterize the pollution emission or atmospheric physical and chemical process with periodic changes; S102, training a prediction model, for a selected air pollutant, using a regression algorithm to predict the pollutant concentration (C t ) and environmental meteorological parameters (M i ) and time trend variables (T j ) was used to model the pollutant concentrations predicted by the model and the actual monitored concentrations. The correlation coefficient and root mean square error were calculated to evaluate the model fitting effect. where ∈ t is the model residual term. For any time t, the model (f t ) The predicted pollutant concentration is C t , then: C t =f t (M i ,t,T j,t )+∈ t , i∈(T,RH,BLH,…,I); j∈(hour,day,…,Unix time), Where i represents the meteorological parameter to be modeled; j represents the time trend variable; S103, meteorological standardization processing, the interference of meteorological conditions that change with time series on pollutant concentration is standardized to the average meteorological conditions, and the trained random forest pollutant prediction model f is used to predict the concentration of pollutants under N randomly selected historical meteorological conditions for the pollutants at time t, and the algebraic mean (C t,norm ), that is, the meteorological standardized concentration of pollutants at time t is: In the formula, k is the kth sample of the selected fixed N groups of historical meteorological data, is the pollutant concentration predicted by the model under the kth historical meteorological data of the selected fixed N groups; S2, build a pollutant machine learning model, take the pollutant meteorological standardized concentration as the indicator variable of local pollution emission intensity, and incorporate it into the machine learning training pollutant regression prediction model, including: S201, prepare the model training data set, including the time series data of the concentration of six air pollutants, SO2, NO2, CO, O3, PM10, and PM2.5, as well as the environmental meteorological parameters and time trend variable data monitored hourly in the target area within two years; S202, training the prediction model, using regression algorithm to compare the pollutant concentration and environmental meteorological parameters (M i ) and meteorological normalized concentration (C t,norm ) to model, ∈ t is the model residual term. A pollutant prediction model is retrained with all hourly data sets for two full natural years. For any time t, the model (f′ t ) The predicted pollutant concentration is C′ t : C′ t =f′ t (M i,t ,C t,norm )+∈ t , i∈(T,RH,BLH,…,I), i represents the modeled meteorological parameters listed; S3, evaluate the contribution of changes in pollution emissions and meteorological conditions to changes in environmental concentrations, determine the baseline reference period for changes in pollutant concentrations in the proposed evaluation period, use the pollutant machine learning model constructed in step S2, simulate pollutant concentrations under different emission and meteorological scenarios based on the control variable method, and obtain the environmental concentration of pollutants under the meteorological conditions of the baseline reference year at the emission intensity in the year to be evaluated. Take the difference between the predicted environmental concentration and the actual monitored concentration in the evaluation year as the contribution, and obtain a quantitative assessment of the change in pollutant concentration caused by pollution reduction in the proposed evaluation year compared to the baseline year.

2. The air quality management effectiveness evaluation method according to claim 1, characterized in that: The environmental meteorological parameters include ground temperature, relative humidity, wind speed, wind direction, air pressure, radiation intensity, mixing layer height, total cloud cover, precipitation, track category and track length.

3. The air quality management effectiveness evaluation method according to claim 1, characterized in that: The time trend variables include a timestamp, a lunar day, a solar day, a day of the week, and a daily hour sequence.

4. The air quality management effectiveness evaluation method according to claim 1, characterized in that: The regression algorithm is a random forest algorithm, a neural network algorithm, a gradient regression tree algorithm or an extreme gradient boosting tree algorithm.

5. The air quality management effectiveness evaluation method according to claim 1, characterized in that: The environmental meteorological parameters include a variety of easily accessible meteorological observation data or meteorological reanalysis data, and the variables used to characterize the emission source intensity are any air-related data related to pollution emission activities.

6. The air quality management effectiveness evaluation method according to claim 1, characterized in that: Assessment of the contribution of changes in pollution emissions and meteorological conditions to changes in ambient concentrations includes: The second year or the second month is taken as the evaluation year (eval), and the first year or the first month is taken as the reference year (base). The model f′ constructed in step S2 is used to predict the environmental concentration f′ (M) of the pollutant under the meteorological conditions of the first year or the first month of the reference year and the emission intensity of the second year or the second month. base ,C norm,eval ), then the difference between the ambient concentration predicted by the model and the actual monitored concentration in the first year or the first month is the contribution ΔC to the change in pollution emission intensity. emi for: ΔC emi =[C eval -C base ]-[C eval -f′(M base ,C norm,eval )] =f′(M base ,C norm,eval )-C base The meteorological data of the second year or the second month are replaced with the meteorological data of the first year or the first month, and the model f′ constructed in step S2 is used to predict the environmental concentration f′ (M) of the pollutant under the meteorological conditions of the first year or the first month and the emission intensity of the second year or the second month. base ,C norm,eval ), then the difference between the ambient concentration predicted by the model and the actual monitored concentration in the second year or the second month is the contribution of the meteorological condition change ΔC met for: ΔC met =C eval -f′(M base ,C norm,eval ) In the formula, C base is the average annual environmental observation concentration of pollutants in the base year, C eval To assess the annual average environmental monitoring concentrations of annual pollutants.

Images