Neural Computing and Applications

, Volume 26, Issue 8, pp 1789–1797 | Cite as

Prediction of particular matter concentrations by developed feed-forward neural network with rolling mechanism and gray model

  • Minglei Fu
  • Weiwen Wang
  • Zichun Le
  • Mahdi Safaei Khorram
Original Article


Particular matter (PM) due to its side effects on human health like increase the risk of lung cancer and vision impairment has been one of the major concerns for air quality. These particles are now considered as one of the high priorities issues by health organizations in China. In this study, daily PM2.5 and PM10 concentrations data from November 2013 to January 2014 in Hangzhou, Shanghai and Nanjing (three important cities in Yangtze River delta of China) were used to introduce more suitable method to forecast air PM2.5 and PM10 concentrations. Feed-forward neural networks (FFNN) have been introduced as a possible forecasting model for complex air quality prediction. However, due to its deficiency to assess the possible correlation between different input variables, an enhanced FFNN with rolling mechanism (RM) and accumulated generating operation (AGO) of gray model (RM-GM-FFNN) was developed. RM and AGO were used to address the trends of input samples of FFNN and detract the randomness of the input data of FFNN, respectively. Both FFNN and RM-GM-FFNN were tested for prediction of the daily PM2.5 and PM10 concentrations with meteorological parameters and historical PM concentration during the given time. The numerical results showed that in all cases, the coefficient of determination (R 2) and the index of agreement of RM-GM-FFNN increased, while the root-mean-square error (RMSE) and mean absolute error of RM-GM-FFNN decreased. In addition, the mean bias error was more close to zero when compared with that of FFNN, indicating that RM-GM-FFNN performed a better accuracy.


Feed-forward neural network Gray model Particular matter concentration Rolling mechanism 



This work was financially supported by the public industrial technology research project of Zhejiang province, China (No. 2013C31075).


  1. 1.
    Cheng Z, Wang S, Jiang J, Fu Q, Chen C, Xu B, Yu J, Fu X, Hao J (2013) Long-term trend of haze pollution and impact of particulate matter in the Yangtze River Delta, China. Environ Pollut 182:101–110. doi: 10.1016/j.envpol.2013.06.043 CrossRefGoogle Scholar
  2. 2.
    Wang T, Jiang F, Deng J, Shen Y, Fu Q, Wang Q, Fu Y, Xu J, Zhang D (2012) Urban air quality and regional haze weather forecast for Yangtze River Delta region. Atmos Environ 58:70–83. doi: 10.1016/j.atmosenv.2012.01.014 CrossRefGoogle Scholar
  3. 3.
    Zhang F, Wang W, Lv J, Krafft T, Xu J (2011) Time-series studies on air pollution and daily outpatient visits for allergic rhinitis in Beijing, China. Sci Total Environ 409:2486–2492. doi: 10.1016/j.scitotenv.2011.04.007 CrossRefGoogle Scholar
  4. 4.
    Pao HT, Fu HC, Tseng CL (2012) Forecasting of CO2 emissions, energy consumption and economic growth in China using an improved grey model. Energy 40:400–409. doi: 10.1016/ CrossRefGoogle Scholar
  5. 5.
    Noori R, Hoshyaripour G, Ashrafi K, Araabi BN (2010) Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration. Atmos Environ 44:476–482. doi: 10.1016/j.atmosenv.2009.11.005 CrossRefGoogle Scholar
  6. 6.
    Antanasijević DZ, Pocajt VV, Povrenović DS, Ristić MD, Perić-Grujić AA (2013) PM10 emission forecasting using artificial neural networks and genetic algorithm input variable optimization. Sci Total Environ 443:511–519. doi: 10.1016/j.scitotenv.2012.10.110 CrossRefGoogle Scholar
  7. 7.
    Perez P (2012) Combined model for PM10 forecasting in a large city. Atmos Environ 60:271–276. doi: 10.1016/j.atmosenv.2012.06.024 CrossRefGoogle Scholar
  8. 8.
    Du J, Rutkowski L, Er MJ (2010) An efficient adaptive fuzzy neural network (EAFNN) approach for short term load forecasting. Intell Autom Soft Co 6113:49–57. doi: 10.1007/978-3-642-13208-7_7 Google Scholar
  9. 9.
    Tuo Z, Wang L (2011) Improved BP neural network’s application in the bank earlywarning. Procedia Eng 23:216–221. doi: 10.1016/j.proeng.2011.11.2492 CrossRefGoogle Scholar
  10. 10.
    Russo A, Raischel F, Lind PG (2013) Air quality prediction using optimal neural networks with stochastic variables. Atmos Environ 79:822–830. doi: 10.1016/j.atmosenv.2013.07.072 CrossRefGoogle Scholar
  11. 11.
    Fernando HJS, Mammarella MC, Grandoni G, Fedele P, Marco RD, Dimitrova R, Hyde P (2012) Forecasting PM10 in metropolitan areas: efficacy of neural networks. Environ Pollut 163:62–67. doi: 10.1016/j.envpol.2011.12.018 CrossRefGoogle Scholar
  12. 12.
    Zhao Z, Wang J, Zhao J, Su Z (2012) Using a grey model optimized by differential evolution algorithm to forecast the per capita annual net income of rural households in China. Omega 40:525–532. doi: 10.1016/ CrossRefGoogle Scholar
  13. 13.
    Kayacan E, Ulutas B, Kaynak O (2010) Grey system theory-based models in time series prediction. Expert Syst Appl 37:1784–1789. doi: 10.1016/j.eswa.2009.07.064 CrossRefGoogle Scholar
  14. 14.
    Grivas G, Chaloulakou A (2006) Artificial neural network models for prediction of PM10 hourly concentrations, in the Greater Area of Athens, Greece. Atmos Environ 40:1216–1229. doi: 10.1016/j.atmosenv.2005.10.036 CrossRefGoogle Scholar
  15. 15.
    Perez P, Reyes J (2006) An integrated neural network model for PM10 forecasting. Atmos Environ 40:2845–2851. doi: 10.1016/j.atmosenv.2006.01.010 CrossRefGoogle Scholar
  16. 16.
    Polat K, Durduran SS (2012) Usage of output-dependent data scaling in modeling and prediction of air pollution daily concentration values (PM10) in the city of Konya. Neural Comput Appl 21:2153–2162. doi: 10.1007/s00521-011-0661-z CrossRefGoogle Scholar
  17. 17.
    Lal B, Tripathy SS (2012) Prediction of dust concentration in open cast coal mine using artificial neural network. Atmos Pollut Res 3:211–218. doi: 10.5094/APR.2012.023 CrossRefGoogle Scholar
  18. 18.
    Cai M, Yin Y, Xie M (2009) Prediction of hourly air pollutant concentrations near urban arterials using artificial neural network approach. Transp Res D 14:32–41. doi: 10.1016/j.trd.2008.10.004 CrossRefGoogle Scholar
  19. 19.
    Zheng H, Shang X (2013) Study on prediction of atmospheric PM2.5 based on RBF neural network. In: 2013 Fourth International Conference on Digital Manufacturing and Automation (ICDMA), Qingdao, pp 1287–1289. doi: 10.1109/ICDMA.2013.306
  20. 20.
    Akay D, Atak M (2007) Grey prediction with rolling mechanism for electricity demand forecasting of Turkey. Energy 32:1670–1675. doi: 10.1016/ CrossRefGoogle Scholar
  21. 21.
    Truong DQ, Ahn KK (2012) An accurate signal estimator using a novel smart adaptive grey model SAGM(1,1). Expert Syst Appl 39:7611–7620. doi: 10.1016/j.eswa.2012.01.002 CrossRefGoogle Scholar
  22. 22.
    Hong S, Jiao L, Ma W (2013) Variation of PM2.5 concentration in Hangzhou, China. Particuology 11:55–62. doi: 10.1016/j.partic.2012.04.008 CrossRefGoogle Scholar
  23. 23.
    Zhou G, Yang F, Geng F, Xu J, Yang X, Tie X (2014) Measuring and modeling aerosol: relationship with haze events in Shanghai, China. Aerosol Air Qual Res 14:783–792. doi: 10.4209/aaqr.2013.01.0019 Google Scholar
  24. 24.
    Kang H, Zhu B, Su J, Wang H, Zhang Q, Wang F (2013) Analysis of a long-lasting haze episode in Nanjing, China. Environ Res 120–121:78–87. doi: 10.1016/j.atmosres.2012.08.004 Google Scholar
  25. 25. Accessed 8 Aug 2014
  26. 26.
  27. 27.
    Díaz-Robles LA, Ortega JC, Fu JS, Reed GD, Chow JC, Watson JG, Moncada-Herrera JA (2008) A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: the case of Temuco, Chile. Atmos Environ 42:8331–8340. doi: 10.1016/j.atmosenv.2008.07.020 CrossRefGoogle Scholar
  28. 28.
    Polat K (2011) A novel data preprocessing method to estimate the air pollution (SO2): neighbor-based feature scaling (NBFS). Neural Comput Appl 21(8):1987–1994. doi: 10.1007/s00521-011-0602-x CrossRefGoogle Scholar
  29. 29.
    Zhou QP, Jiang HY, Wang JZ, Zhou JL (2014) A hybrid model for PM2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network. Sci Total Environ 496(274):274. doi: 10.1016/j.scitoten.2014.07.051 Google Scholar
  30. 30.
    Voukantsis D, Karatzas K, Kukkonen J, Räsänen T, Karppinen A, Kolehmainen M (2011) Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki. Sci Total Environ 409:1266–1276. doi: 10.1016/j.scitotenv.2010.12.039 CrossRefGoogle Scholar
  31. 31.
    Moustris KP, Larissi IK, Nastos PT, Koukouletsos KV, Paliatsos AG (2013) Development and application of artificial neural network modeling in forecasting PM10 levels in a Mediterranean city. Water Air Soil Pollut 224:1634. doi: 10.1007/s11270-013-1634-x CrossRefGoogle Scholar
  32. 32.
    Cheng S, Li L, Chen D, Li J (2012) A neural network based ensemble approach for improving the accuracy of meteorological fields used for regional air quality modeling. J Environ Manage 112:404–414. doi: 10.1016/j.jenvman.2012.08.020 CrossRefGoogle Scholar
  33. 33.
    Cobourn WG (2010) An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations. Atmos Environ 40(3015):3023. doi: 10.1016/j.atmosenv.2010.05.009 Google Scholar

Copyright information

© The Natural Computing Applications Forum 2015

Authors and Affiliations

  • Minglei Fu
    • 1
  • Weiwen Wang
    • 1
  • Zichun Le
    • 1
  • Mahdi Safaei Khorram
    • 2
  1. 1.College of ScienceZhejiang University of TechnologyHangzhouChina
  2. 2.Institute of Pesticide and Environmental ToxicologyZhejiang UniversityHangzhouChina

Personalised recommendations