Advertisement

Investigating wintertime air pollution in Hangzhou, China

  • 21 Accesses

Abstract

Hangzhou, one of the most prosperous cities in China, suffered from severe air quality degradation in wintertime, and the ambient atmospheric particulate matter (PM) has become the most public-concerning air pollutant. In this work, a case study in wintry Hangzhou is made, for analysis of air pollutants and prediction of PM2.5/PM10 using two machine learning models, recurrent neural network (RNN) and random forest. The results signify that statistic-based and inventory-free machine learning is competently alternative to the inventory-predicted atmospheric models. Variable importance (VI) indicates that CO was the predominant factor for both PM2.5 and PM10. Dew-point deficit played an essential role in shaping gaseous air pollutants. Water vapor pressure and hydrostatic energy had trivial impact on atmospheric pollutants. RNN and random forest both show high accuracy in predicting PM2.5 and PM10. The inter-annual consistence of PM’s components is confirmed. A method to pinpoint whether the high episodes of PM were spawned by long-range transport or increase of gaseous pollutants (SO2, NO2, and CO) is proposed. Additionally, the possible chemical bond between CO and PM needs to be further investigated.

This is a preview of subscription content, log in to check access.

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 99

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. Abbas I, Badran G, Verdin A, Ledoux F, Roumié M, Courcot D, Garçon G (2018) Polycyclic aromatic hydrocarbon derivatives in airborne particulate matter: sources, analysis and toxicity. Environ Chem Lett 16(2):439–475. https://doi.org/10.1007/s10311-017-0697-0

  2. Alimissis A, Philippopoulos K, Tzanis C, Deligiorgi D (2018) Spatial estimation of urban air pollution with the use of artificial neural network models. Atmos Environ 191:205–213. https://doi.org/10.1016/j.atmosenv.2018.07.058

  3. Boichu M, Favez O, Riffault V, Petit JE, Zhang Y, Brogniez C, Sciare J, Chiapello I, Clarisse L, Zhang S, Pujol-Söhne N, Tison E, Delbarre H, Goloub P (2019) Large-scale particulate air pollution and chemical fingerprint of volcanic sulfate aerosols from the 2014–2015 Holuhraun flood lava eruption of Bárðarbunga volcano (Iceland). Atmos Chem Phys 19:14253–14287. https://doi.org/10.5194/acp-19-14253-2019

  4. Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324

  5. Dong F, Zhang S, Long R, Zhang X, Sun Z (2019) Determinants of haze pollution: an analysis from the perspective of spatiotemporal heterogeneity. J Clean Prod 222:768–783. https://doi.org/10.1016/j.jclepro.2019.03.105

  6. Du Y, Li Z, Du J, Li N, Ya B (2019) Public environmental appeal and innovation of heavy-polluting enterprises. J Clean Prod 222:1009–1022. https://doi.org/10.1016/j.jclepro.2019.03.035

  7. Feng R, Zheng H (2019) Evidence for regional heterogeneous atmospheric particulate matter distribution in China: implications for air pollution control. Environ Chem Lett 17(4):1839–1847. https://doi.org/10.1007/s10311-019-00890-0

  8. Feng R, Wang Q, Huang C, Liang J, Luo K, Fan J, Cen K (2019a) Investigation on air pollution control strategy in Hangzhou for post-G20/pre-Asian-games period (2018–2020). Atmospheric Pollution Research 10(1):197–208. https://doi.org/10.1016/j.apr.2018.07.006

  9. Feng R, Zheng H, Zhang A, Huang C, Gao H, Ma Y (2019b) Unveiling tropospheric ozone by the traditional atmospheric model and machine learning, and their comparison: a case study in Hangzhou, China. Environ Pollut 252:366–378. https://doi.org/10.1016/j.envpol.2019.05.101

  10. Feng R, Luo K, Fan J. (2019c). Decoding tropospheric ozone in Hangzhou, China: from precursors to sources. Asia-Pacific Journal of Atmospheric Sciences In press https://doi.org/10.1007/s13143-019-00124-x, 1, 11

  11. Guo S, Hu M, Zamora M, Peng J, Shang D, Zheng J, Du Z, Wu Z, Shao M, Zeng L, Malina M, Zhang R (2014) Elucidating severe urban haze formation in China. Proc Natl Acad Sci U S A 111(49):17373–17378. https://doi.org/10.1073/pnas.1419604111

  12. Hyde P, Mahalov A (2020) Contribution of bioaerosols to airborne particulate matter. J Air Waste Manage Assoc 70(1):71–77. https://doi.org/10.1080/10962247.2019.1629360

  13. Kamińska J (2018) The use of random forests in modelling short-term air pollution effects based on traffic and meteorological conditions: a case study in Wrocław. J Environ Manag 217:164–174. https://doi.org/10.1016/j.jenvman.2018.03.094

  14. Li J, Liao H, Hu J, Li N (2019) Severe particulate pollution days in China during 2013–2018 and the associated typical weather patterns in Beijing-Tianjin-Hebei and the Yangtze River Delta regions. Environ Pollut 248:74–81. https://doi.org/10.1016/j.envpol.2019.01.124

  15. Ma J, Ding Y, Cheng J, Jiang F, Wan Z. (2019). A temporal-spatial interpolation and extrapolation method based on geographic long short-term memory neural network for PM2.5. Journal of Cleaner Production, 237: 117729. https://doi.org/10.1016/j.jclepro.2019.117729

  16. Mehmood K, Chang S, Yu S, Wang L, Li P, Li Z, Liu W, Rosenfeld D, Seinfeld J (2018) Spatial and temporal distributions of air pollutant emissions from open crop straw and biomass burnings in China from 2002 to 2016. Environ Chem Lett 16(1):301–309. https://doi.org/10.1007/s10311-017-0675-6

  17. Pryor SC, Sullivan RC, Schoof JT (2017) Modeling the contributions of global air temperature, synoptic-scale phenomena and soil moisture to near-surface static energy variability using artificial neural networks. Atmos Chem Phys 17:14457–14471. https://doi.org/10.5194/acp-17-14457-2017

  18. Pu S, Shao Z, Yang L, Liu R, Bi J, Ma Z (2019) How much will the Chinese public pay for air pollution mitigation? A nationwide empirical study based on a willingness-to-pay scenario and air purifier costs. J Clean Prod 218:51–60. https://doi.org/10.1016/j.jclepro.2019.01.270

  19. Radojević D, Antanasijević D, Perić-Grujić A, Ristić M, Pocajt V (2019) The significance of periodic parameters for ANN modeling of daily SO2 and NOx concentrations: a case study of Belgrade, Serbia. Atmospheric Pollution Research 10(2):621–628. https://doi.org/10.1016/j.apr.2018.11.004

  20. Razmjoo A, Xanthopoulos P, Zheng Q (2017) Online feature importance ranking based on sensitivity analysis. Expert Syst Appl 85:397–406. https://doi.org/10.1016/j.eswa.2017.05.016

  21. Shi S, Wang H, Bin Z, Guo Z (2019) Characterization of aerosol size distributions and chemical compositions under strong wind and stagnant conditions during haze episodes in Lin’an, China. Air Quality, Atmosphere & Health 12(12):1469–1481. https://doi.org/10.1007/s11869-019-00752-2

  22. Song Y, Wang X, Maher B, Li F, Xu C, Liu X, Sun X, Zhang Z (2016) The spatial-temporal characteristics and health impacts of ambient fine particulate matter in China. J Clean Prod 112:1312–1318. https://doi.org/10.1016/j.jclepro.2015.05.006

  23. Tilt B (2019) China’s air pollution crisis: science and policy perspectives. Environ Sci Pol 92:275–280. https://doi.org/10.1016/j.envsci.2018.11.020

  24. Tomatis M, Moreira M, Xu H, Deng W, He J, Parvez A (2019) Removal of VOCs from waste gases using various thermal oxidizers: a comparative study based on life cycle assessment and cost analysis in China. J Clean Prod 233:808–818. https://doi.org/10.1016/j.jclepro.2019.06.131

  25. Wang Z, Feng J, Fu Q, Gao S, Chen X, Cheng J (2019) Quality control of online monitoring data of air pollutants using artificial neural networks. Air Quality, Atmosphere & Health 12(10):1189–1196. https://doi.org/10.1007/s11869-019-00734-4

  26. Watson G, Telesca D, Reid C, Pfister G, Jerrett M (2019) Machine learning models accurately predict ozone exposure during wildfire events. Environ Pollut 254:112792. https://doi.org/10.1016/j.envpol.2019.06.088

  27. Werner M, Kryza M, Pagowski M, Guzikowski J (2019) Assimilation of PM2.5 ground base observations to two chemical schemes in WRF-Chem – the results for the winter and summer period. Atmos Environ 200:178–189. https://doi.org/10.1016/j.atmosenv.2018.12.016

  28. Wu L, Xu Z (2019) Analyzing the air quality of Beijing, Tianjin, and Shijiazhuang using grey Verhulst model. Air Quality, Atmosphere & Health 12(12):1419–1426. https://doi.org/10.1007/s11869-019-00746-0

  29. Zhang Y, Shuai C, Bian J, Chen X, Wu Y, Shen L (2019) Socioeconomic factors of PM2.5 concentrations in 152 Chinese cities: decomposition analysis using LMDI. J Clean Prod 218:96–107. https://doi.org/10.1016/j.jclepro.2019.01.322

Download references

Acknowledgments

Dr. Rui Feng would like to express gratitude to Professor Wei-xian Wang and Professor Ning-xin Feng of Zhejiang University, who had enlightened his curiosity and passion in science since childhood, for they valued family over money and material things and were the best grandparents ever.

Author information

Correspondence to Rui Feng.

Ethics declarations

Conflict of interest

The author declares that there is no conflict of interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Feng, R. Investigating wintertime air pollution in Hangzhou, China. Air Qual Atmos Health (2020) doi:10.1007/s11869-020-00794-x

Download citation

Keywords

  • Recurrent neural networks
  • Random forest
  • Variable importance