Neural Computing and Applications

, Volume 31, Issue 12, pp 8217–8227 | Cite as

Research on prediction of environmental aerosol and PM2.5 based on artificial neural network

  • Xianghong WangEmail author
  • Baozhen Wang
Machine Learning - Applications & Techniques in Cyber Intelligence


With the increasing severity of air pollution, PM2.5 in aerosols, as the most important air pollutant, has adversely affected people’s normal production, life and work, and has caused harm to people’s health. Scientific and effective prediction of PM2.5 can enable people to take precautions in advance to avoid or reduce harm to the human body. Therefore, the prediction of PM2.5 concentration has become a topic of great practical significance. This paper selects the air quality data released in real time, obtains the historical monitoring data of air environmental pollutants, and normalizes the data, then divides the sample data, and divides it into training data set and test data set in appropriate proportion. Design the optimal network structure based on BP neural network. An improved neural network is proposed, and the neural network is optimized using genetic algorithms. The preprocessed data are input into the network for training and testing. The fitting and prediction results were statistically and comparatively analyzed. The data results show that the neural network optimized by genetic algorithm has better performance in PM2.5 mass concentration prediction, which improves the accuracy of prediction results and reduces the error rate.


Aerosol PM2.5 Neural network Prediction 



The research work was supported by Chongqing Municipal Commission of social and livelihood projects (Grant No. cstc2015shmszx20010).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Yang X (2013) Atmospheric particulate matter PM2.5 and its sources. Front Sci 7(2):12–17Google Scholar
  2. 2.
    Yang X, Wei P, Feng L (2013) Atmospheric particulate matter PM2.5 and its controlling countermeasures and measures. Front Sci 7(3):20–29Google Scholar
  3. 3.
    Tsai FC, Smith KR, Vichit-Vadakan N et al (2000) Indoor/outdoor PM10 and PM2.5 in Bangkok, Thailand. J Expo Anal Environ Epidemiol 10(1):15–26CrossRefGoogle Scholar
  4. 4.
    Sahu SK, Kota SH (2017) Significance of PM2.5 air quality at the Indian capital. Aerosol Air Qual Res 17(2):588–597CrossRefGoogle Scholar
  5. 5.
    Xing YF, Xu YH, Shi MH et al (2016) The impact of PM2.5 on the human respiratory system. J Thorac Dis 8(1):E69Google Scholar
  6. 6.
    Cao C, Jiang W, Wang B et al (2014) Inhalable microorganisms in Beijing’s PM2.5 and PM10 pollutants during a severe smog event. Environ Sci Technol 48(3):1499–1507CrossRefGoogle Scholar
  7. 7.
    Hu D, Jiang J (2013) A study of smog issues and PM2.5 pollutant control strategies in China. J Environ Prot 04(07):746–752CrossRefGoogle Scholar
  8. 8.
    Lee H, Coull BA, Bell ML et al (2012) Use of satellite-based aerosol optical depth and spatial clustering for PM2.5 prediction and concentration trends in the New England region, U.S. In: AGU fall meeting. AGU fall meeting abstracts, 2012Google Scholar
  9. 9.
    Biancofiore F, Busilacchio M, Verdecchia M et al (2017) Recursive neural network model for analysis and forecast of PM10 and PM2.5. Atmos Pollut Res 8(4):652–659CrossRefGoogle Scholar
  10. 10.
    Liu H, Wang XM, Pang JM et al (2013) Feasibility and difficulties of China’s new air quality standard compliance: PRD case of PM2.5 and ozone from 2010 to 2025. Atmos Chem Phys 13(23):12013–12027CrossRefGoogle Scholar
  11. 11.
    Mchenry JN, Vukovich JM, Hsu NC (2015) Development and implementation of a remote-sensing and in situ data-assimilating version of CMAQ for operational PM2.5 forecasting. Part 1: MODIS aerosol optical depth (AOD) data-assimilation design and testing. J Air Waste Manag Assoc 65(12):1395–1412CrossRefGoogle Scholar
  12. 12.
    Li X, Peng L, Yao X et al (2017) Long short-term memory neural network for air pollutant concentration predictions: method development and evaluation. Environ Pollut 231(Pt 1):997–1004Google Scholar
  13. 13.
    Song L, Pang S, Longley I et al (2014) Spatio-temporal PM2.5 prediction by spatial data aided incremental support vector regression. In: International joint conference on neural networks. IEEE, pp 623–630Google Scholar
  14. 14.
    Tan KC, Lim HS, Jafri MZM (2016) Prediction of column ozone concentrations using multiple regression analysis and principal component analysis techniques: a case study in peninsular Malaysia[J]. Atmos Pollut Res 7(3):533–546CrossRefGoogle Scholar
  15. 15.
    Ghazali NA, Ramli NA, Yahaya AS et al (2010) Transformation of nitrogen dioxide into ozone and prediction of ozone concentrations using multiple linear regression techniques. Environ Monit Assess 165(1–4):475–489CrossRefGoogle Scholar
  16. 16.
    Donnelly A, Misstear B, Broderick B (2015) Real time air quality forecasting using integrated parametric and non-parametric regression techniques. Atmos Environ 103(103):53–65CrossRefGoogle Scholar
  17. 17.
    Mishra D, Goyal P (2015) Development of artificial intelligence based NO 2, forecasting models at Taj Mahal, Agra. Atmos Pollut Res 6(1):99–106CrossRefGoogle Scholar
  18. 18.
    He J, Ye Y, Na L et al (2013) Numerical model-based relationship between meteorological conditions and air quality and its implication for urban air quality management. Int J Environ Pollut 53(3–4):265–286CrossRefGoogle Scholar
  19. 19.
    Fang M, Zhu G, Zheng X et al (2011) Study on air fine particles pollution prediction of main traffic route using artificial neural network. In: International conference on computer distributed control and intelligent environmental monitoring. IEEE Computer Society, pp 1346–1349Google Scholar
  20. 20.
    Zheng H, Shang X (2013) Study on prediction of atmospheric PM2.5 based on RBF neural network. In: Fourth international conference on digital manufacturing and automation. IEEE, pp 1287–1289Google Scholar
  21. 21.
    Yang Y, Yan-Li FU (2015) The prediction of mass concentration of PM2.5 based on T-S fuzzy neural network. J Shaanxi Univ Sci Technol 33(6):162–166Google Scholar
  22. 22.
    Tian-Cheng MA, Liu DM, Xue-Jie LI et al (2014) Improved particle swarm optimization based fuzzy neural network for PM_(2.5) concentration prediction. Comput Eng Des 35(9):3258–3262Google Scholar
  23. 23.
    Hu Z, Li W, Qiao J (2016) Prediction of PM2.5 based on Elman neural network with chaos theory. In: Control conference. IEEE, pp 3573–3578Google Scholar
  24. 24.
    Zhu H, Lu X (2016) The prediction of PM2.5 value based on ARMA and improved BP neural network model. In: International conference on intelligent NETWORKING and collaborative systems. IEEE, pp 515–517Google Scholar
  25. 25.
    Zhou S, Li W, Qiao J (2017) Prediction of PM2.5 concentration based on recurrent fuzzy neural network. In: Control Conference. IEEE, pp 3920–3924Google Scholar
  26. 26.
    Papadopoulos H, Haralambous H (2011) Reliable prediction intervals with regression neural networks. Neural Netw 24(8):842–851CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Chongqing Multiple-Source Technology Engineering Research Center for Ecological Environment MonitoringYangtze Normal UniversityChongqingChina
  2. 2.Green Intelligence Environmental SchoolYangtze Normal UniversityChongqingChina
  3. 3.Collaborative Innovation Center for Green Development in Wuling Mountain AreasYangtze Normal UniversityChongqingChina

Personalised recommendations