Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR

• Autorzy: Fang Zhiyuan , Yang Hao , Li Cheng , Cheng Liangliang , Zhao Ming , Xie Chenbo

Identyfikatory

DOI

10.24425/aep.2021.138468

• Języki publikacji: EN

Abstrakty

EN

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.

Słowa kluczowe

EN

PM2.5; LiDAR; machine learning; air pollution monitoring

• Wydawca: Institute of Environmental Engineering, Polish Academy of Sciences
• Czasopismo: Archives of Environmental Protection
• Rocznik: 2021
• Tom: Vol. 47, no. 3
• Strony: 98--107
• Opis fizyczny: Bibliogr. 23 poz., fot., rys., tab., wykr.

Twórcy

autor

Fang Zhiyuan

• Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
• Science Island Branch of Graduate School, University of Science and Technology of China, Hefei 230026, China
• Advanced Laser Technology Laboratory of Anhui Province, Hefei 230037, China

autor

Yang Hao

• Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
• Science Island Branch of Graduate School, University of Science and Technology of China, Hefei 230026, China
• Advanced Laser Technology Laboratory of Anhui Province, Hefei 230037, China

autor

Li Cheng

• Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
• Science Island Branch of Graduate School, University of Science and Technology of China, Hefei 230026, China
• Advanced Laser Technology Laboratory of Anhui Province, Hefei 230037, China

autor

Cheng Liangliang

• Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
• Science Island Branch of Graduate School, University of Science and Technology of China, Hefei 230026, China
• Advanced Laser Technology Laboratory of Anhui Province, Hefei 230037, China

autor

Zhao Ming

• Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
• Science Island Branch of Graduate School, University of Science and Technology of China, Hefei 230026, China

autor

Xie Chenbo

• Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
• Science Island Branch of Graduate School, University of Science and Technology of China, Hefei 230026, China

Bibliografia

• 1. Belle, J. & Liu, Y. (2016). Evaluation of Aqua MODIS Collection 6 AOD Parameters for Air Quality Research over the Continental United States. Remote Sensing, 8(10), pp. 815-820.
• 2. Berdnik, V.V. & Loiko, V.A. (2016). Neural networks for aerosol particles characterization. Journal of Quantitative Spectroscopy & Radiative Transfer, 184.
• 3. Bishop, C.M., (1995). Neural Networks for Pattern Recognition. Agricultural Engineering International the Cigr Journal of Scientific Research & Development Manuscript Pm, 12(5), pp. 1235-1242.
• 4. Breiman & Leo, (1996). Bagging Predictors. Machine Learning, 24(2), pp. 123-140.
• 5. Butt, E.W., Turnock, S.T., Rigby, R., Reddington, C.L., Yoshioka, M., Johnson, J.S., Regayre, L.A., Pringle, K.J., Mann, G.W. & Spracklen, D.V. (2017). Global and regional trends in particulate air pollution and attributable health burden over the past 50 years. Environmental Research Letters. 10 (12), DOI: 10.1088/1748-9326/aa87be.
• 6. Chan, P.W. (2009). Comparison of aerosol optical depth (AOD) derived from ground-based LIDAR and MODIS. Open Atmospheric Science Journal, 3(1), pp. 131-137.
• 7. Chu, Y., Liu, Y., Li, X., Liu, Z., Lu, H., Lu, Y., Mao, Z., Chen, X., Li, N., Ren, M., Liu, F., Tian, L., Zhu, Z. & Xiang, H. (2016). A Review on Predicting Ground PM2.5 Concentration Using Satellite Aerosol Optical Depth. Atmosphere, 7(10), p. 129. DOI: 10.3390/atmos7100129.
• 8. Fernald, F.G. (1984). Analysis of atmospheric lidar observations: some comments. Applied optics, 5, pp. 652-653.
• 9. Gui, K., Che, H., Chen, Q., An, L., Zeng, Z., Guo, Z., Zheng, Y., Wang, H., Wang, Y., Yu, J. & Zhang, X. (2016)., Aerosol Optical Properties Based on Ground and Satellite Retrievals during a Serious Haze Episode in December 2015 over Beijing. Atmosphere, 7(5), pp. 70, DOI: 10.3390/atmos7050070.
• 10. Hu, S, Wang, Z., Xu, Q., Zhou, J. & Hu. H. (2006). Study on Lidar Measurement of Atmospheric Aerosol Optical Thickness. Journal of Quantum Electronics, 3, p. 307-310. (in Chinese)
• 11. Hutchison, K.D., Faruqui, S.J. & Smi, S. (2008). The Improving correlations between MODIS aerosol optical thickness and ground-based PM2.5 observations through 3D spatial analyses. Atmosphere Environment, 3(42), pp. 530-554, DOI: 10.1016/j.atmosenv.2007.09.050.
• 12. Jones, R.M. (2008). Experimental evaluation of a Markov model of contaminant transport in indoor environments with application to tuberculosis transmission in commercial passenger aircraft. Dissertations & Theses - Gradworks, 2008.
• 13. Kaufman, Y.J., Tanré, D. & Boucher, O. (2002). A satellite view of aerosols in the climate system. Nature, 419(6903), pp. 215-23.
• 14. Li, X. & Zhang, X. (2019). Predicting ground-level PM 2.5 concentrations in the Beijing-Tianjin-Hebei region: A hybrid remote sensing and machine learning approach. Environmental Pollution, 249, pp. 735-749, DOI: 10.1016/j.envpol.2019.03.068.
• 15. Bing,-C.L., Binaykia, A., Chang, P-C., Tiwari, M.K. & Tsao, C-C. (2017). Urban air quality forecasting based on multi-dimensional collaborative Support Vector Regression (SVR): A case study of Beijing-Tianjin-Shijiazhuang. Plos One, 12(7), pp. e0179763, DOI: 10.1371/journal.pone.0179763.
• 16. Mao, X., Shen, T. & Feng, X. (2017). Prediction of hourly ground-level PM2.5 concentrations 3 days in advance using neural networks with satellite data in eastern China. Atmospheric Pollution Research, 6(8), pp. 1005-1015. S1309104217300296.
• 17. Nabavi, S.O.(2018). Prediction of aerosol optical depth in West Asia using deterministic models and machine learning algorithms. Aeolian Research, 35C: p. 69-84.
• 18. Stein, A.F. (2016). NOAA’s HYSPLIT atmospheric transport and dispersion modeling system. Bulletin of the American Meteorological Society, p. 150504130527006, DOI: 10.1016/j.apr.2017.04.002.
• 19. Toth, T.D., Campbell, J.R., Reid, J.S., Tackett, J.L., Vaughan, M.A., Zhang, J. & Marquis, J.W. (2018). Minimum aerosol layer detection sensitivities and their subsequent impacts on aerosol optical thickness retrievals in CALIPSO level 2 data products. Atmospheric Measurement Techniques, 11, p. 499-514, DOI: 10.5194/amt-11-499-2018.
• 20. Yan, D., Lei, Y., Shi, Y., Zhu, Q., Li, L.& Zhang, Z. (2018). Evolution of the spatiotemporal pattern of PM2.5 concentrations in China - a 2 case study from the Beijing-Tianjin-Hebei region. Atmosphere Environment. 183, pp. 225-233, DOI: 10.1016/j.atmosenv.2018.03.041.
• 21. Yang, G., Lee, H. & Lee, G. (2020). A Hybrid Deep Learning Model to Forecast Particulate Matter Concentration Levels in Seoul, South Korea. Atmosphere, 11(4): pp. 348, DOI: 10.3390/atmos11040348.
• 22. Wang, Y., Chen, L., Li, S., Wang, X., Yu, C., Si, Y. & Zhang, Z. (2017). Interference of Heavy Aerosol Loading on the VIIRS Aerosol Optical Depth (AOD) Retrieval Algorithm. Remote Sensing, 2017. 9(4): p. 397, DOI: 10.3390/rs9040397.
• 23. Chen, Z., Zhang, J., Zhang, T., Liu, W. & Liu, J. (2015). Haze observations by simultaneous lidar and WPS in Beijing before and during APEC, 2014. Science China (Chemistry), 2015. 09(v.58): p. 33-40, DOI: 10.1007/s11426-015-5467-x