Prediction method of atmospheric air quality trend along the Yellow Sea coast during the frequent green tide period

Abstract

The present invention discloses a method for predicting the trend of atmospheric air quality along the coast of the Yellow Sea during the frequent period of the Yellow Sea green tide, which relates to the technical field of air quality prediction, and includes the following steps: clarifying the research area of ​​the Yellow Sea green tide, and collecting ocean data related to the frequent period of the Yellow Sea green tide and historical data of atmospheric air quality; by comparing the ocean and atmospheric data during the period when the green tide occurs and the period when the green tide does not occur, analyzing the correlation between the ocean data and the historical data of atmospheric air quality. The present invention constructs and applies an air quality impact model, accurately predicts the atmospheric air quality along the coast of the Yellow Sea based on historical data and real-time monitoring information, comprehensively considers multiple factors such as meteorological conditions and marine environment, thereby improving the accuracy and reliability of the prediction, which not only helps us to understand the air quality status in a timely manner, but also provides a scientific basis for formulating targeted prevention and control measures, and effectively responds to air pollution problems.

Description

Technical Field

[0001] The invention relates to the technical field of air quality prediction, and in particular to a method for predicting atmospheric air quality trends along the Yellow Sea coast during a period of frequent green tides in the Yellow Sea. Background Art

[0002] The Yellow Sea green tide refers to a marine ecological phenomenon formed by the massive reproduction of algae such as Enteromorpha and their aggregation on the sea surface. The prediction and prevention of the Yellow Sea green tide is particularly important. There is a certain correlation between the occurrence of the Yellow Sea green tide and the atmospheric air quality. On the one hand, the occurrence of the green tide may be affected by meteorological factors such as atmospheric circulation, wind direction and wind speed. Changes in these factors will affect the flow of seawater and the distribution of algae. On the other hand, during the green tide, a large number of algae gather on the sea surface, which may affect the carbon dioxide concentration and oxygen content in the atmosphere through processes such as photosynthesis, thereby affecting the atmospheric air quality. Therefore, the prediction of the Yellow Sea green tide will help to better understand the changing trend of atmospheric air quality.

[0003] In the existing technology, due to the interference of ocean factors during the frequent green tide period, only the atmospheric air quality in a small range along the Yellow Sea coast can be predicted, and it is difficult to comprehensively cover all areas along the Yellow Sea coast. Therefore, how to integrate ocean data to accurately predict the atmospheric air quality during the frequent green tide period in the Yellow Sea, and then accurately reflect the air quality trend in the entire region, is the problem we need to solve. To this end, a method for predicting the atmospheric air quality trend along the Yellow Sea coast during the frequent green tide period in the Yellow Sea is proposed. Summary of the invention

[0004] The present invention aims to provide a method for predicting the atmospheric air quality trend along the Yellow Sea coast during the frequent green tide period in the Yellow Sea, so as to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of the Yellow Sea green tide includes the following steps:

[0007] Step 1: Define the research area of ​​the Yellow Sea green tide, collect relevant ocean data and historical data of atmospheric air quality during the frequent period of the Yellow Sea green tide, and pre-process the data;

[0008] Step 2: By comparing the ocean and atmospheric data during the period when green tides occurred and those during the period when green tides did not occur, the correlation between ocean data and historical atmospheric air quality data was analyzed to explore the specific impact mechanism of green tides on atmospheric air quality.

[0009] Step 3: Based on the pre-processed data and comparative analysis results, an air quality impact model for atmospheric air quality during the frequent green tide period in the Yellow Sea is established to identify and predict the impact of green tide on atmospheric air quality;

[0010] Step 4: Use the adjusted air quality impact model to make actual predictions of atmospheric air quality along the Yellow Sea coast, analyze the prediction results, and identify trends in air quality changes;

[0011] Step 5: Based on the prediction results of the air quality impact model, formulate targeted prevention and control measures and emergency plans.

[0012] A further improvement of the technical solution of the present invention is that in step 1, the process of collecting ocean data and atmospheric air quality historical data is as follows:

[0013] Identify the areas prone to green tide in the Yellow Sea as research areas, and collect ocean data during and without green tides, including ocean currents, wind speed, seawater temperature, salinity, and nutrient data. Collect historical data on atmospheric air quality in the coastal areas of the Yellow Sea during the same period, including air quality index, PM2.5, PM10, SO2, NO2, and CO pollutant concentration data.

[0014] Preprocess the collected ocean data and historical data of atmospheric air quality, where the preprocessing operations include data cleaning, data format conversion and standardization steps. Through data cleaning, outliers in the ocean data and air quality data are checked and deleted. For missing data points, linear interpolation, neighbor value filling or time series analysis are used to fill them. Through data format conversion and standardization, all collected data have a unified format and unit for subsequent analysis. For data of different scales, standardization is performed to eliminate the impact of dimensional differences on the analysis results;

[0015] The pre-processed ocean data and air quality data are integrated to form a complete data set, and the data are visualized using chart tools to facilitate analysis and understanding of data trends and patterns.

[0016] A further improvement of the technical solution of the present invention is that in step 2, the correlation analysis process of the ocean data and the historical data of atmospheric air quality is as follows:

[0017] Analyze the changing trends of ocean data and atmospheric air quality data during and without green tides, and compare them with the changes in atmospheric pollutant concentrations;

[0018] Based on the comparison results, regression analysis method was used to take ocean data as independent variables and atmospheric pollutant concentration as dependent variables to conduct regression analysis to determine the correlation between ocean data and atmospheric pollutant concentration. If the regression result is significantly different from 0, it indicates that the corresponding ocean parameters have a significant impact on the atmospheric pollutant concentration.

[0019] Based on the results of correlation analysis, the specific impact mechanism of the release of bioaerosols and volatile organic compounds (VOCs) brought by green tide on atmospheric air quality was further analyzed.

[0020] A further improvement of the technical solution of the present invention is that the expression of the regression analysis is:

[0021] ;

[0022] Among them, C is the concentration of pollutants in the atmosphere, T is the seawater temperature, which is between -2°C and 30°C, and is at a higher value during the period of frequent green tides, and S is the seawater salinity, which is between 25 and 40, and the growth and metabolic activities of green tides will cause slight changes. is the nutrient concentration, which decreases with the growth of the green tide and is between 0.1 and 10 mg / L. U is the ocean current speed, which affects the drift path of the green tide and is between 0 and 3 m / s. D is the wind force, which affects the aggregation degree of the green tide and is between 0 and 20 m / s. , , , , , is the regression coefficient, obtained by data fitting, It is an index parameter related to wind force, which represents the influence of wind force on pollutant concentration. is the error term, which is assumed to be normally distributed. is the logarithmic effect of seawater temperature on pollutant concentration, is the linear effect of seawater salinity on pollutant concentration, is the effect of the square root of nutrient concentration on pollutant concentration, is the effect of the inverse of the ocean current speed on the pollutant concentration, is the effect of exponential attenuation of wind speed on pollutant concentration.

[0023] A further improvement of the technical solution of the present invention is that in step 3, the process of establishing the air quality impact model is:

[0024] The pre-processed ocean data (ocean current velocity, direction, wind force and direction, seawater temperature, salinity, nutrient concentration) and atmospheric air quality data (including conventional pollutant concentrations and monitoring data of bioaerosols and volatile organic compounds (VOCs) brought by green tides) are integrated in chronological order to ensure the time synchronization of the data, and characteristic variables of the changes in ocean data parameters and atmospheric pollutant concentrations during the green tide are extracted from the integrated data. The characteristic variables include ocean current velocity, direction, wind force and direction, seawater temperature, salinity, nutrient concentration, and the release of bioaerosols and volatile organic compounds (VOCs) brought by green tides.

[0025] Based on the extracted characteristic variables and historical data, the ARIMA model of time series analysis method is used to capture the dynamic dependency of time series data. According to the results of time series analysis, the extracted characteristic variables are used as the input of the model, and the concentration of atmospheric pollutants is used as the output of the model to construct an air quality impact model of atmospheric air quality during the frequent green tide period in the Yellow Sea.

[0026] The trained air quality impact model is combined with the extracted characteristic variables to calculate the air quality impact index and make trend predictions on the atmospheric air quality during the frequent green tide period in the Yellow Sea.

[0027] Compare the prediction results during the period when green tide occurs and during the period when green tide does not occur, analyze the specific impact of green tide on atmospheric air quality in the prediction results, and then identify the degree and scope of the impact of green tide on air quality.

[0028] A further improvement of the technical solution of the present invention is that the calculation process of the air quality impact index is:

[0029] Collect actual pollutant concentration data and corresponding predicted pollutant concentration data during the frequent green tide periods in the Yellow Sea, and collect volatile organic compound concentration data and bioaerosol concentration data at each time point;

[0030] The baseline values ​​are calculated based on the historical data of pollutant concentrations, and the maximum and minimum concentrations of volatile organic compounds and bioaerosols are extracted from the historical data of atmospheric air quality;

[0031] For each time point i, the standardized prediction error is calculated by combining the actual pollutant concentration data, the predicted pollutant concentration data and the benchmark value, and the minimum value of the standardized prediction error is found among all time points;

[0032] For each time point i, the VOC impact factor and bioaerosol impact factor are calculated;

[0033] For each time point i, the contribution value of the air quality impact index is calculated by combining the calculation results of the standardized prediction error, the minimum standardized prediction error, the volatile organic compound impact factor and the bioaerosol impact factor, and the contribution values ​​of the air quality impact index of all time points are added up and divided by the number of time points N to obtain the final air quality impact index TPC.

[0034] A further improvement of the technical solution of the present invention is that the expression of the air quality impact index is:

[0035] ;

[0036] ;

[0037] ;

[0038] Among them, TPC is the air quality impact index, N is the number of data points, is the predicted pollutant concentration at the i-th time point, is the actual pollutant concentration at the i-th time point, B is the reference value used to standardize the pollutant concentration, and is the average value of the pollutant concentration. is the minimum value after standardization among all time points, and is the weight coefficient, which is used to adjust the impact on TPC. is the impact factor of volatile organic compounds, is the bioaerosol impact factor, is the concentration of volatile organic compounds (VOCs) at the i-th time point, is the maximum concentration of volatile organic compounds (VOCs) during the monitoring period, is the bioaerosol concentration at the i-th time point, is the minimum concentration of bioaerosol during the monitoring period, is the maximum concentration of bioaerosol during the monitoring period. It should be noted that when TPC approaches 0, the worse the atmospheric air quality is, and the greater the impact of green tide on atmospheric air quality is.

[0039] A further improvement of the technical solution of the present invention is that in step 4, the process of identifying the trend of air quality change is:

[0040] Collect the latest air quality data from monitoring stations along the Yellow Sea coast, pre-process the collected data, and input the pre-processed monitoring data into the constructed air quality impact model, including current and recent air quality data, meteorological conditions, and pollution source emissions;

[0041] Run the air quality impact model, input the latest data, predict the atmospheric air quality along the Yellow Sea coast based on the input data, and output the results of the air quality impact index;

[0042] By comparing the values ​​and changing trends of air quality impact indicators at different time points, the trend of improvement or deterioration of atmospheric air quality along the Yellow Sea coast can be clarified. If the air quality impact indicators continue to rise over a period of time, it means that the air quality is improving; if the air quality impact indicators continue to decline over a period of time, it means that the air quality is deteriorating.

[0043] By observing the changing trends of air quality impact indicators over time, we can identify specific time periods when air quality improves or deteriorates.

[0044] A further improvement of the technical solution of the present invention is that in step 5, the process of formulating prevention and control measures and emergency plans is as follows:

[0045] Based on the output results of the air quality impact model and the trend analysis results of the air quality impact indicators, different emergency warning levels are set in combination with the air quality impact indicators, namely yellow warning level, orange warning level and red warning level, and the corresponding warning threshold is matched for each emergency warning level to identify the risk time period of air quality deterioration and determine the key areas of prevention and control measures and emergency plans. Among them, the emergency warning level increases from yellow to red, and the degree of urgency increases step by step;

[0046] Formulate corresponding prevention and control measures and emergency plans for each emergency warning level, and establish an emergency linkage mechanism. For the yellow warning level, strengthen air quality monitoring and pay close attention to the trend of air quality changes. For the orange warning level, restrict industrial emissions in high-risk areas, strengthen environmental supervision, activate the moderate pollution emergency plan, strengthen emergency response, and ensure that prevention and control measures are effectively implemented. For the red warning level, comprehensively restrict industrial emissions in high-risk areas, take production suspension measures when necessary, activate the severe pollution emergency plan, strengthen emergency linkage, and jointly deal with air pollution problems;

[0047] After implementing prevention and control measures and emergency plans, continuously monitor changes in air quality, collect and analyze monitoring data, evaluate the effectiveness of prevention and control measures and emergency plans, adjust prevention and control measures and emergency plans based on monitoring results and evaluation results, continuously optimize prevention and control strategies and emergency response mechanisms, and improve the ability to deal with air pollution problems.

[0048] A further improvement of the technical solution of the present invention is that: a plurality of emergency warning levels correspond to a plurality of warning thresholds, wherein the warning thresholds include an upper threshold and a lower threshold;

[0049] The multiple emergency warning levels and the multiple warning thresholds satisfy the following relationship:

[0050] Yellow warning level ;

[0051] Orange warning level ;

[0052] Red alert level ;

[0053] Among them, TPC is the air quality impact index. is the lower threshold corresponding to the yellow warning level and the upper threshold corresponding to the orange warning level. It is the lower threshold corresponding to the orange warning level and the upper threshold corresponding to the red warning level.

[0054] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0055] The present invention provides a method for predicting the trend of atmospheric air quality along the coast of the Yellow Sea during the frequent green tide period in the Yellow Sea. By constructing and applying an air quality impact model, the atmospheric air quality along the coast of the Yellow Sea is accurately predicted based on historical data and real-time monitoring information, and various factors such as meteorological conditions and marine environment are comprehensively considered, thereby improving the accuracy and reliability of the prediction. This not only helps us to understand the air quality status in a timely manner, but also provides a scientific basis for formulating targeted prevention and control measures, and effectively responds to air pollution problems.

[0056] The present invention provides a method for predicting the atmospheric air quality trend along the Yellow Sea coast during the period of frequent green tides in the Yellow Sea. Through the air quality impact model, the specific time period of improvement or deterioration of air quality can be identified, which is crucial for optimizing the allocation of environmental resources and formulating emergency response measures, and helps to improve the efficiency and effectiveness of coping with green tide disasters. It not only improves the accuracy of air quality prediction, but also optimizes the formulation and implementation of prevention and control strategies, and promotes the innovative development of environmental protection technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0058] Figure 1 is a flow chart of the method of the present invention;

[0059] Figure 2 A flow chart for establishing an air quality impact model of the present invention;

[0060] Figure 3 The figure is a calculation flow chart of the air quality impact index of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Embodiment 1, as Figure 1 As shown, the present invention provides a method for predicting the atmospheric air quality trend along the Yellow Sea coast during the frequent green tide period of the Yellow Sea, comprising the following steps:

[0063] Step 1: Define the research area of ​​the Yellow Sea green tide, collect ocean data related to the frequent period of the Yellow Sea green tide and historical data on atmospheric air quality, pre-process the data, define the area prone to green tide in the Yellow Sea as the research area, and collect ocean data during and when the green tide occurs, including ocean currents, wind speed, seawater temperature, salinity, and nutrient data, as well as collect historical data on atmospheric air quality in the coastal areas of the Yellow Sea during the same period, including air quality index, PM2.5, PM10, SO2, NO2, and CO pollutant concentration data. Among them, ocean current and wind speed data are crucial for predicting the drift path of the Enteromorpha green tide, which are obtained through ocean monitoring stations. Seawater temperature, salinity, and nutrient data are helpful for analyzing the environmental factors of the Enteromorpha green tide outbreak, which are collected through ocean water quality monitoring stations. Historical data on atmospheric air quality are obtained from the Green Tide Remote Sensing Monitoring Bulletin of the National Satellite Ocean Application Center. Pre-process the collected ocean data and historical data on atmospheric air quality;

[0064] The preprocessing operations include data cleaning, data format conversion and standardization steps. Through data cleaning, outliers in ocean data and air quality data are checked and deleted. For missing data points, linear interpolation, neighbor value filling or time series analysis are used to fill them. Through data format conversion and standardization, all collected data have a unified format and unit for subsequent analysis. For data of different scales, standardization is performed to eliminate the impact of dimensional differences on the analysis results. The preprocessed ocean data and air quality data are integrated to form a complete data set, and the data are visualized using chart tools to facilitate analysis and understanding of data trends and patterns.

[0065] Step 2: By comparing the ocean and atmospheric data during the period when green tides occur and during the period when they do not occur, the correlation between ocean data and historical atmospheric air quality data is analyzed to explore the specific impact mechanism of green tides on atmospheric air quality. The changing trends of ocean data and atmospheric air quality data during the period when green tides occur and during the period when green tides do not occur are analyzed respectively, and compared with the changes in atmospheric pollutant concentrations. During the period when green tides occur, the velocity and direction of ocean currents change due to the drift and aggregation of green tides. The size and direction of wind force affect the drift path and aggregation degree of green tides. Since green tides mostly occur in summer, the seawater temperature is at its peak in the year, and the seawater temperature is usually high. The salinity changes slightly due to the growth and metabolic activity of green tides. The growth of green tides consumes nutrients in seawater, and the concentration of nutrients decreases.

[0066] During the period when green tides did not occur, ocean parameters were usually in a relatively stable state, without obvious seasonal or event changes. During the period when green tides occurred, the air quality index increased due to the release of bioaerosols and volatile organic compounds (VOCs) brought by green tides. Green tides will increase the concentration of particulate matter in the air, especially biological particulate matter. During the period when green tides did not occur, the air quality index and pollutant concentrations were usually in a relatively stable state. Based on the comparison results, regression analysis was used to take ocean data as independent variables and atmospheric pollutant concentrations as dependent variables to conduct regression analysis to determine the correlation between ocean data and atmospheric pollutant concentrations. If the regression result is significantly not 0, it indicates that the corresponding ocean parameters have a significant impact on the concentration of atmospheric pollutants. According to the results of the correlation analysis, the specific impact mechanism of the release of bioaerosols and volatile organic compounds (VOCs) brought by green tides on atmospheric air quality was further analyzed.

[0067] Furthermore, the expression of regression analysis is:

[0068] ;

[0069] Among them, C is the concentration of pollutants in the atmosphere (such as PM2.5, PM10, etc.), T is the seawater temperature, which is between -2°C and 30°C, and is at a higher value during the period of frequent green tides. S is the seawater salinity, which is between 25 and 40, and the growth and metabolic activities of green tides will cause slight changes. is the nutrient concentration, which decreases with the growth of the green tide and is between 0.1 and 10 mg / L. U is the ocean current speed, which affects the drift path of the green tide and is between 0 and 3 m / s. D is the wind force, which affects the aggregation degree of the green tide and is between 0 and 20 m / s. , , , , , is the regression coefficient, obtained by data fitting, It is an index parameter related to wind force, which represents the influence of wind force on pollutant concentration. is the error term, assuming a normal distribution, is the logarithmic effect of seawater temperature on pollutant concentration, indicating that there is a nonlinear relationship between temperature and pollutant concentration. is the linear effect of seawater salinity on pollutant concentration, is the effect of the square root of nutrient concentration on pollutant concentration, indicating that there is a nonlinear relationship between nutrient concentration and pollutant concentration. is the effect of the inverse of the ocean current speed on the pollutant concentration, indicating that there is an inverse relationship between ocean current speed and pollutant concentration. The exponential decay effect of wind speed on pollutant concentration indicates that the greater the wind speed, the smaller its effect on pollutant concentration;

[0070] Step 3: Based on the pre-processed data and comparative analysis results, an air quality impact model for atmospheric air quality during the frequent green tide period in the Yellow Sea is established to identify and predict the impact of green tide on atmospheric air quality;

[0071] Step 4: Use the adjusted air quality impact model to make actual predictions of atmospheric air quality along the Yellow Sea coast, analyze the prediction results, and identify trends in air quality changes;

[0072] Step 5: Based on the prediction results of the air quality impact model, formulate targeted prevention and control measures and emergency plans.

[0073] Embodiment 2, as Figure 2 , Figure 3 As shown, based on Example 1, the present invention provides a technical solution: Preferably, in step 3, the process of establishing the air quality impact model is:

[0074] The pre-processed ocean data (ocean current velocity, direction, wind force and direction, seawater temperature, salinity, nutrient concentration) and atmospheric air quality data (including conventional pollutant concentrations and monitoring data of bioaerosols and volatile organic compounds (VOCs) brought by green tides) are integrated in chronological order to ensure the time synchronization of the data, and characteristic variables of changes in ocean data parameters and changes in atmospheric pollutant concentrations during the green tide period are extracted from the integrated data;

[0075] The characteristic variables include ocean current velocity, direction, wind force and direction, seawater temperature, salinity, nutrient concentration, and the release of bioaerosols and volatile organic compounds (VOCs) brought by green tides. Based on the extracted characteristic variables and historical data, the ARIMA model of the time series analysis method is used to capture the dynamic dependency of time series data. According to the results of time series analysis, the extracted characteristic variables are used as the input of the model, and the concentration of atmospheric pollutants is used as the output of the model to construct an air quality impact model of atmospheric air quality during the frequent green tide period in the Yellow Sea. The trained air quality impact model is combined with the extracted characteristic variables to calculate the air quality impact index, and the trend of atmospheric air quality during the frequent green tide period in the Yellow Sea is predicted. The prediction results during the period when green tides occur and those during the period when green tides do not occur are compared, and the specific impact of green tides on atmospheric air quality in the prediction results is analyzed, thereby identifying the degree and scope of the impact of green tides on air quality.

[0076] Furthermore, the calculation process of the air quality impact index is:

[0077] Collect actual pollutant concentration data and corresponding predicted pollutant concentration data during the frequent green tide period in the Yellow Sea, and collect volatile organic compound concentration data and bioaerosol concentration data at each time point, calculate and obtain benchmark values ​​based on historical pollutant concentration data, and extract the maximum and minimum concentrations of volatile organic compounds and the maximum and minimum concentrations of bioaerosols from historical atmospheric air quality data. For each time point i, combine the actual pollutant concentration data, predicted pollutant concentration data and benchmark values ​​to calculate the standardized prediction error, and find the minimum value of the standardized prediction error among all time points;

[0078] For each time point i, the volatile organic compound impact factor and the bioaerosol impact factor are calculated. For each time point i, the contribution value of the air quality impact index is calculated by combining the calculation results of the standardized prediction error, the minimum standardized prediction error, the volatile organic compound impact factor and the bioaerosol impact factor. The contribution values ​​of the air quality impact index at all time points are added up and divided by the number of time points N to obtain the final air quality impact index TPC.

[0079] Furthermore, the expression of air quality impact index is:

[0080] ;

[0081] ;

[0082] ;

[0083] Among them, TPC is the air quality impact index, N is the number of data points, is the predicted pollutant concentration at the i-th time point, is the actual pollutant concentration at the i-th time point, B is the reference value used to standardize the pollutant concentration, and is the average value of the pollutant concentration. is the minimum value after standardization among all time points, and is the weight coefficient, which is used to adjust the impact on TPC. is the impact factor of volatile organic compounds, is the bioaerosol impact factor, is the concentration of volatile organic compounds (VOCs) at the i-th time point, is the maximum concentration of volatile organic compounds (VOCs) during the monitoring period, is the bioaerosol concentration at the i-th time point, is the minimum concentration of bioaerosol during the monitoring period, is the maximum concentration of bioaerosol during the monitoring period;

[0084] It should be noted that when TPC approaches 0, the worse the atmospheric air quality is, the greater the impact of green tide on atmospheric air quality is. When the VOCs concentration is close to its maximum value, due to the effect of the exponential function, TPC will be punished to a certain extent. High VOCs concentration means more serious air pollution. When the bioaerosol concentration is close to its minimum value, due to the negative exponential effect of the exponential function, TPC will be improved to a certain extent. Low bioaerosol concentration means better air quality.

[0085] In step 4, the process of identifying the trend of air quality changes is as follows:

[0086] Collect the latest air quality data from monitoring stations along the Yellow Sea coast, pre-process the collected data, input the pre-processed monitoring data into the constructed air quality impact model, including current and recent air quality data, meteorological conditions, and pollution source emissions, run the air quality impact model, input the latest data, predict the atmospheric air quality along the Yellow Sea coast based on the input data, and output the results of the air quality impact index. By comparing the values ​​and changing trends of the air quality impact index at different time points, the changing trend of the improvement or deterioration of the atmospheric air quality along the Yellow Sea coast can be clarified. If the air quality impact index continues to rise over a period of time, it means that the air quality is improving;

[0087] If the air quality impact index continues to decline over a period of time, it means that the air quality is deteriorating. By observing the changing trend of the air quality impact index over time and identifying the specific time periods when the air quality improves or deteriorates, it helps to determine which time periods need special attention and take corresponding measures to deal with air quality problems;

[0088] In step 5, the process of formulating prevention and control measures and emergency plans is as follows:

[0089] Based on the output results of the air quality impact model and the trend analysis results of the air quality impact indicators, different emergency warning levels are set in combination with the air quality impact indicators, namely yellow warning level, orange warning level and red warning level, and the corresponding warning threshold is matched for each emergency warning level to identify the risk time period of air quality deterioration and determine the key areas of prevention and control measures and emergency plans. Among them, the emergency warning level increases from yellow to red, and the corresponding prevention and control measures and emergency plans are formulated for each emergency warning level, and an emergency linkage mechanism is established;

[0090] For the yellow warning level, strengthen air quality monitoring and pay close attention to the changing trend of air quality;

[0091] For the orange alert level, industrial emissions in high-risk areas will be restricted, environmental supervision will be strengthened, the moderate pollution emergency plan will be activated, emergency response will be strengthened, and prevention and control measures will be effectively implemented;

[0092] For the red alert level, industrial emissions in high-risk areas will be fully restricted, and production suspension measures will be taken when necessary. Emergency plans for severe pollution will be activated, emergency linkages will be strengthened, and air pollution problems will be jointly addressed. After implementing prevention and control measures and emergency plans, changes in air quality will be continuously monitored, monitoring data will be collected and analyzed, and the effectiveness of prevention and control measures and emergency plans will be evaluated. According to monitoring results and evaluation situations, prevention and control measures and emergency plans will be adjusted, and prevention and control strategies and emergency response mechanisms will be continuously optimized to improve the ability to address air pollution problems;

[0093] Furthermore, multiple emergency warning levels correspond to multiple warning thresholds, wherein the warning threshold includes an upper threshold and a lower threshold;

[0094] Multiple emergency warning levels and multiple warning thresholds satisfy the following relationship:

[0095] Yellow warning level ;

[0096] Orange warning level ;

[0097] Red alert level ;

[0098] Among them, TPC is the air quality impact index. is the lower threshold corresponding to the yellow warning level and the upper threshold corresponding to the orange warning level. It is the lower threshold corresponding to the orange warning level and the upper threshold corresponding to the red warning level.

[0099] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting atmospheric air quality trends along the Yellow Sea coast during the frequent period of the Yellow Sea green tide, characterized in that: The following steps are involved: Step 1: Define the research area of ​​the Yellow Sea green tide and collect relevant oceanographic data and historical data on atmospheric air quality during the frequent green tide periods in the Yellow Sea; Step 2: Analyze the correlation between ocean data and historical atmospheric air quality data by comparing ocean and atmospheric data during periods when green tides occur and periods when green tides do not occur; Step 3: Based on the pre-processed data and comparative analysis results, an air quality impact model for atmospheric air quality during the frequent green tide period in the Yellow Sea is established to identify and predict the impact of the green tide on atmospheric air quality. In step 3, the process of establishing the air quality impact model is as follows: The pre-processed ocean data and atmospheric air quality data are integrated in chronological order, and characteristic variables of the changes in ocean data parameters and atmospheric pollutant concentrations during the green tide period are extracted from the integrated data. The characteristic variables include ocean current velocity, direction, wind force and direction, seawater temperature, salinity, nutrient concentration, and the release of bioaerosols and volatile organic compounds caused by the green tide. Based on the extracted characteristic variables and historical data, the ARIMA model of time series analysis method is used to capture the dynamic dependency of time series data. According to the results of time series analysis, the extracted characteristic variables are used as the input of the model, and the concentration of atmospheric pollutants is used as the output of the model to construct an air quality impact model of atmospheric air quality during the frequent green tide period in the Yellow Sea. The trained air quality impact model is combined with the extracted characteristic variables to calculate the air quality impact index and make trend predictions on the atmospheric air quality during the frequent green tide period in the Yellow Sea. Compare the forecast results during the period when green tide occurs and during the period when green tide does not occur, analyze the specific impact of green tide on atmospheric air quality in the forecast results, and then identify the degree and scope of the impact of green tide on air quality; Step 4: Use the adjusted air quality impact model to make actual predictions of atmospheric air quality along the Yellow Sea coast, analyze the prediction results, and identify the trend of air quality changes; Step 5: Based on the prediction results of the air quality impact model, formulate targeted prevention and control measures and emergency plans.

2. The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of the Yellow Sea green tide according to claim 1, characterized in that: In step 1, the process of collecting ocean data and atmospheric air quality historical data is as follows: Identify the areas prone to green tide in the Yellow Sea as research areas, and collect ocean data during and without green tides, including ocean currents, wind speed, seawater temperature, salinity, and nutrient data. Collect historical data on atmospheric air quality in the coastal areas of the Yellow Sea during the same period, including air quality index, PM2.5, PM10, SO2, NO2, and CO pollutant concentration data. Preprocessing the collected ocean data and historical data of atmospheric air quality, where the preprocessing operations include data cleaning, data format conversion and standardization steps; The preprocessed ocean data and air quality data are integrated to form a complete data set, and the data are visualized using chart tools.

3. The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of green tide in the Yellow Sea according to claim 2, characterized in that: In step 2, the correlation analysis process between ocean data and historical data of atmospheric air quality is as follows: Analyze the changing trends of ocean data and atmospheric air quality data during and without green tides, and compare them with the changes in atmospheric pollutant concentrations; Based on the comparison results, regression analysis was performed using the ocean data as the independent variable and the concentration of atmospheric pollutants as the dependent variable to determine the correlation between the ocean data and the concentration of atmospheric pollutants. Based on the results of correlation analysis, the specific impact mechanism of the release of bioaerosols and volatile organic compounds brought by green tide on atmospheric air quality is further analyzed.

4. The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of green tide in the Yellow Sea according to claim 3, characterized in that: The expression of the regression analysis is: Among them, C is the concentration of pollutants in the atmosphere, T is the seawater temperature, S is the seawater salinity, and C nut is the nutrient concentration, U is the current speed, D is the wind force, which affects the degree of green tide aggregation and is between 0 and 20 m / s. β0, β1, β2, β3, β4, and β5 are regression coefficients obtained by data fitting. λ is an exponential parameter related to wind force, ∈ is an error term, β1ln(T) is the logarithmic effect of seawater temperature on pollutant concentration, and β2S is the linear effect of seawater salinity on pollutant concentration. is the effect of the square root of nutrient concentration on pollutant concentration, is the effect of the inverse of the ocean current speed on the pollutant concentration, β5e -λD is the effect of exponential attenuation of wind speed on pollutant concentration.

5. The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of green tide in the Yellow Sea according to claim 4, characterized in that: The calculation process of the air quality impact index is as follows: Collect actual pollutant concentration data and corresponding predicted pollutant concentration data during the frequent green tide periods in the Yellow Sea, and collect volatile organic compound concentration data and bioaerosol concentration data at each time point; The baseline values ​​are calculated based on the historical data of pollutant concentrations, and the maximum and minimum concentrations of volatile organic compounds and bioaerosols are extracted from the historical data of atmospheric air quality; For each time point i, the standardized prediction error is calculated by combining the actual pollutant concentration data, the predicted pollutant concentration data and the benchmark value, and the minimum value of the standardized prediction error is found among all time points; For each time point i, the VOC impact factor and bioaerosol impact factor are calculated; For each time point i, the contribution value of the air quality impact index is calculated by combining the calculation results of the standardized prediction error, the minimum standardized prediction error, the volatile organic compound impact factor and the bioaerosol impact factor, and the contribution values ​​of the air quality impact index of all time points are added up and divided by the number of time points N to obtain the final air quality impact index TPC.

6. The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of the Yellow Sea green tide according to claim 5, characterized in that: The expression of the air quality impact index is: Among them, TPC is the air quality impact index, N is the number of data points, P i is the predicted pollutant concentration at the i-th time point, O i is the actual pollutant concentration at the i-th time point, B is the baseline value, which is the average value of the pollutant concentration, is the minimum value after standardization among all time points, α and γ are weight coefficients, f(V) is the impact factor of volatile organic compounds, f(BA) is the impact factor of bioaerosols, V i is the concentration of volatile organic compounds at the i-th time point, V max is the maximum concentration of volatile organic compounds during the monitoring period, BA i is the bioaerosol concentration at the i-th time point, BA min is the minimum concentration of bioaerosol during the monitoring period, BA max is the maximum concentration of bioaerosol during the monitoring period.

7. The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of the Yellow Sea green tide according to claim 6, characterized in that: In step 4, the process of identifying the air quality change trend is as follows: Collect the latest air quality data from monitoring stations along the Yellow Sea coast, pre-process the collected data, and input the pre-processed monitoring data into the constructed air quality impact model; Run the air quality impact model, input the latest data, predict the atmospheric air quality along the Yellow Sea coast based on the input data, and output the results of the air quality impact index; By comparing the values ​​and changing trends of air quality impact indicators at different time points, the trend of improvement or deterioration of atmospheric air quality along the Yellow Sea coast can be clarified; By observing the changing trends of air quality impact indicators over time, we can identify specific time periods when air quality improves or deteriorates.

8. The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of the Yellow Sea green tide according to claim 7, characterized in that: In step 5, the process of formulating prevention and control measures and emergency plans is as follows: Based on the output results of the air quality impact model and the trend analysis results of the air quality impact indicators, different emergency warning levels are set in combination with the air quality impact indicators, namely yellow warning level, orange warning level and red warning level, and the corresponding warning threshold is matched for each emergency warning level to identify the risk time period of air quality deterioration and determine the key areas of prevention and control measures and emergency plans. Among them, the emergency warning level increases from yellow to red, and the degree of urgency increases step by step; Formulate corresponding prevention and control measures and emergency plans for each emergency warning level, and establish an emergency linkage mechanism; After implementing prevention and control measures and emergency plans, continuously monitor changes in air quality, collect and analyze monitoring data, evaluate the effectiveness of prevention and control measures and emergency plans, and adjust prevention and control measures and emergency plans based on monitoring results and evaluation results.

9. The method for predicting the trend of atmospheric air quality along the Yellow Sea coast during the frequent period of the Yellow Sea green tide according to claim 8, characterized in that: A plurality of emergency warning levels correspond to a plurality of warning thresholds, wherein the warning thresholds include an upper threshold and a lower threshold; The multiple emergency warning levels and the multiple warning thresholds satisfy the following relationship: Yellow warning level TPC ≥ TPC Y ; Orange warning level TPC R ≤TPC <TPC Y ; Red Alert Level 0 <TPC<TPC R ; Among them, TPC is the air quality impact index, TPC Y is the lower threshold corresponding to the yellow warning level and the upper threshold corresponding to the orange warning level, TPC R It is the lower threshold corresponding to the orange warning level and the upper threshold corresponding to the red warning level.

Images