Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR
The prediction of PM2.5 is important for environmental forecasting and air pollution control. In this study, four machine learning methods, ground-based LiDAR data and meteorological data were used to predict the ground-level PM2.5 concentrations in Beijing. Among the four methods, the random forest...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2021-09-01
|
| Series: | Archives of Environmental Protection |
| Subjects: | |
| Online Access: | https://journals.pan.pl/Content/120756/Archives%203_vol47_2021_pp98_107.pdf |
| _version_ | 1797448478582898688 |
|---|---|
| author | Zhiyuan Fang Hao Yang Cheng Li Liangliang Cheng Ming Zhao Chenbo Xie |
| author_facet | Zhiyuan Fang Hao Yang Cheng Li Liangliang Cheng Ming Zhao Chenbo Xie |
| author_sort | Zhiyuan Fang |
| collection | DOAJ |
| description | The prediction of PM2.5 is important for environmental forecasting and air pollution control. In this study, four machine learning methods, ground-based LiDAR data and meteorological data were used to predict the ground-level PM2.5 concentrations in Beijing. Among the four methods, the random forest (RF) method was the most effective in predicting ground-level PM2.5 concentrations. Compared with BP neural network, support vector machine (SVM), and various linear fitting methods, the accuracy of the RF method was superior by 10%. The method can describe the spatial and temporal variation in PM2.5 concentrations under different meteorological conditions, with low root mean square error (RMSE) and mean square deviation (MD), and the consistency index (IA) reached 99.69%. Under different weather conditions, the hourly variation in PM2.5 concentrations has a good descriptive ability. In this paper, we analyzed the weights of input variables in the RF method, constructed a pollution case to correspond to the relationship between input variables and PM2.5, and analyzed the sources of pollutants via HYSPLIT backward trajectory. This method can study the interaction between PM2.5 and air pollution variables, and provide new ideas for preventing and forecasting air pollution. |
| first_indexed | 2024-03-09T14:11:02Z |
| format | Article |
| id | doaj.art-9e3208ae1d0b417397370e5853c1f8af |
| institution | Directory Open Access Journal |
| issn | 2083-4772 2083-4810 |
| language | English |
| last_indexed | 2024-03-09T14:11:02Z |
| publishDate | 2021-09-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Archives of Environmental Protection |
| spelling | doaj.art-9e3208ae1d0b417397370e5853c1f8af2023-11-29T10:29:18ZengPolish Academy of SciencesArchives of Environmental Protection2083-47722083-48102021-09-0147398107https://doi.org/10.24425/aep.2021.138468Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDARZhiyuan Fang0Hao Yang1Cheng Li2Liangliang Cheng3Ming Zhao4Chenbo Xie5Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics,Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics,Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics,Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics,Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics,Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics,Chinese Academy of Sciences, Hefei 230031, ChinaThe prediction of PM2.5 is important for environmental forecasting and air pollution control. In this study, four machine learning methods, ground-based LiDAR data and meteorological data were used to predict the ground-level PM2.5 concentrations in Beijing. Among the four methods, the random forest (RF) method was the most effective in predicting ground-level PM2.5 concentrations. Compared with BP neural network, support vector machine (SVM), and various linear fitting methods, the accuracy of the RF method was superior by 10%. The method can describe the spatial and temporal variation in PM2.5 concentrations under different meteorological conditions, with low root mean square error (RMSE) and mean square deviation (MD), and the consistency index (IA) reached 99.69%. Under different weather conditions, the hourly variation in PM2.5 concentrations has a good descriptive ability. In this paper, we analyzed the weights of input variables in the RF method, constructed a pollution case to correspond to the relationship between input variables and PM2.5, and analyzed the sources of pollutants via HYSPLIT backward trajectory. This method can study the interaction between PM2.5 and air pollution variables, and provide new ideas for preventing and forecasting air pollution.https://journals.pan.pl/Content/120756/Archives%203_vol47_2021_pp98_107.pdfpm2.5lidarmachine learningair pollution monitoring |
| spellingShingle | Zhiyuan Fang Hao Yang Cheng Li Liangliang Cheng Ming Zhao Chenbo Xie Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR Archives of Environmental Protection pm2.5 lidar machine learning air pollution monitoring |
| title | Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR |
| title_full | Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR |
| title_fullStr | Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR |
| title_full_unstemmed | Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR |
| title_short | Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR |
| title_sort | prediction of pm2 5 hourly concentrations in beijing based on machine learning algorithm and ground based lidar |
| topic | pm2.5 lidar machine learning air pollution monitoring |
| url | https://journals.pan.pl/Content/120756/Archives%203_vol47_2021_pp98_107.pdf |
| work_keys_str_mv | AT zhiyuanfang predictionofpm25hourlyconcentrationsinbeijingbasedonmachinelearningalgorithmandgroundbasedlidar AT haoyang predictionofpm25hourlyconcentrationsinbeijingbasedonmachinelearningalgorithmandgroundbasedlidar AT chengli predictionofpm25hourlyconcentrationsinbeijingbasedonmachinelearningalgorithmandgroundbasedlidar AT liangliangcheng predictionofpm25hourlyconcentrationsinbeijingbasedonmachinelearningalgorithmandgroundbasedlidar AT mingzhao predictionofpm25hourlyconcentrationsinbeijingbasedonmachinelearningalgorithmandgroundbasedlidar AT chenboxie predictionofpm25hourlyconcentrationsinbeijingbasedonmachinelearningalgorithmandgroundbasedlidar |