Air Quality, Atmosphere & Health

, Volume 12, Issue 1, pp 59–72 | Cite as

Integration of ANFIS model and forward selection method for air quality forecasting

  • Afsaneh Ghasemi
  • Jamil AmanollahiEmail author


In the last decade, air pollution in the city of Kermanshah has become a major concern. In this study, adaptive neuro-fuzzy inference system (ANFIS) was developed to predict five daily air pollutants in the atmosphere of Kermanshah city on the same day and 1 day in advance from 2014 to 2016. The selected pollutants were the particulate matter PM10, sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), and ozone (O3). The temperature, relative humidity, dew point, wind speed, precipitation, pressure, visibility, and the pollutant concentration on the previous day were considered as predictors in the ANFIS model. In order to reduce the computational cost and time, the collinearity tests and forward selection (FS) technique were utilized to remove the redundant input variables and select the different combinations of input variables, respectively. Results showed that input combination for MODEL 2 (six input conditions) and MODEL 3 (five input conditions) performed well between observed and predicted values of CO in the same day forecasting (SDF) and 1 day in advance forecasting (1DAF). For other pollutants such as NO2, SO2, and PM10, the results obtained from MODEL 3 were better compared to the other input subset of the MODELs in the SDF and 1DAF. Developing the ANFIS model for O3 pollutant showed that MODEL 4 with the lowest normalized mean square error (NMSE) can be used to forecast the O3 concentration in both cases. It can be concluded that the integration of the FS method and ANFIS model led to an improvement in air quality forecasting.


Computational cost Air pollutants Redundant input Collinearity Kermanshah city 



We thank Dr. Vahid Nimehchisalem, from the Department of English, Faculty of Modern Languages and Communication, Universiti Putra Malaysia, for editing our manuscript.


  1. Ahmadi Doabi S, Afyuni M, Karami M (2017) Multivariate statistical analysis of heavy metals contamination in atmospheric dust of Kermanshah province, western Iran, during the spring and summer2013. J Geochem Explor 180:61–70CrossRefGoogle Scholar
  2. Amanollahi J, Kaboodvandpour S, Abdullah AM, Ramli MF (2011) Accuracy assessment of moderate resolution image spectroradiometer products before and during dust storms. Int J Environ Sci Technol 8(2):373–380CrossRefGoogle Scholar
  3. Antanasijevic DZ, Pocajt VV, Povrenovic DS, Ristic MD, Peric-Grujic AA (2013) PM10 emission forecasting using artificial neural networks and genetic algorithm input variable optimization. Sci Total Environ 443(15):511–519CrossRefGoogle Scholar
  4. Armstrong JS (1999) Forrecasting for environmental decision making. University of Pennsylvania. Retrieved from
  5. Ashmore MR (2005) Assessing the future global impacts of ozone on vegetation. Plant Cell Environ 28(8):949–964CrossRefGoogle Scholar
  6. Ausati S, Amanollahi J (2016) Assessing the accuracy of ANFIS, EEMD-GRNN, PCR, and MLR models in predicting PM2.5. Atmos Environ 142:465–474CrossRefGoogle Scholar
  7. Bagherian Marzouni M, Alizadeh T, Rezaei Banafsheh M, Khorshiddoust AM, Ghanbari Ghozikali M, Akbaripoor S, Sharifi R, Goudarzi G (2016) A comparison of health impacts assessment for PM10 during two successive years in the ambient air of Kermanshah, Iran. Atmos Pollut Res 7(5):768–774CrossRefGoogle Scholar
  8. Bellini T (2012) Forward search outlier detection in data envelopment analysis. Eur J Oper Res 216(1):200–207CrossRefGoogle Scholar
  9. Bertaccini B, Varriale R (2007) Robust analysis of variance: an approach based on the forward search. Comput Stat Data Anal 51(10):5172–5183CrossRefGoogle Scholar
  10. Biancofiore F, Busilacchio M, Verdecchia M, Tomassetti B, Aruffo E, Bianco S, Di Tommaso S, Colangeli C, Rosatelli G, Di Carlo P (2017) Recursive neural network model for analysis and forecast of PM10 and PM2.5. Atmos Pollut Res 8(4):652–659CrossRefGoogle Scholar
  11. Carnevale C, Finzi G, Pederzoli A, Pisoni E, Thunis P, Turrini E, Volta M (2014) Applying the delta tool to support the air quality directive: evaluation of the TCAM chemical transport model. Air Qual Atmos Health 7(3):335–346CrossRefGoogle Scholar
  12. Cerioli A, Farcomeni A, Riani M (2014) Strong consistency and robustness of the Forward Search estimator of multivariate location and scatter. J Multivar Anal 126:167–183CrossRefGoogle Scholar
  13. Chen R, Yin P, Meng X, Liu C, Wang L, Xu X, Ross JA, Tse LA, Zhao Z, Kan H, Zhou M (2017) Fine particulate air pollution and daily mortality: a nationwide analysis in 272 Chinese cities. Am J Respir Crit Care Med 196(1):73–81CrossRefGoogle Scholar
  14. Dehbi HM, Blangiardo M, Gulliver J, Fecht D, de Hoogh K, Al-Kanaani Z et al (2017) Air pollution and cardiovascular mortality with over 25 years follow-up: a combined analysis of two British cohorts. Environ Int 99:275–281CrossRefGoogle Scholar
  15. Delle Monache L, Perry KD, Cederwall RT (2002) Comparison of aerosol properties within and above the ABL at the ARM program’s SGP site. Proceedings AMS conference on the application of air pollution meteorology, Norfolk, Virginia, pp78–80Google Scholar
  16. Dimakopoulou K, Gyparis A, Katsouyanni K (2017) Using spatio-temporal land use regression models to address spatial variation in air pollution concentrations in time series studies. Air Qual Atmos Health 10(9):1139–1149CrossRefGoogle Scholar
  17. Ewing SA, Christensen JN, Brown ST, Vancuren RA, Cliff SS, Depaolo DJ (2010) Pb isotopes as an indicator of the Asian contribution to particulate air pollution in urban California. Environ Sci Technol 44(23):8911–8916CrossRefGoogle Scholar
  18. Gerosa G, Fusaro L, Monga R, Finco A, Fares S, Manes F, Marzuoli R (2015) A flux-based assessment of above and below ground biomass of Holm oak (Quercus ilex L.) seedlings after one season of exposure to high ozone concentrations. Atmos Environ 113:41–49CrossRefGoogle Scholar
  19. Gorai AK, Mitra G (2017) A comparative study of the feed forward back propagation (FFBP) and layer recurrent (LR) neural network model for forecasting ground level ozone concentration. Air Qual Atmos Health 10(2):213–223CrossRefGoogle Scholar
  20. Goudarzi G, Daryanoosh SM, Godini H, Hopke PK, Sicard P, DeMarco A, Rad HD, Harbizadeh A, Jahedi F, Mohammadi MJ, Savari J, Sadeghi S, Kaabi Z, Omidi Khaniabadi Y (2017) Health risk assessment of exposure to the Middle-Eastern Dust storms in the Iranian megacity of Kermanshah. Public Health 148:109–116CrossRefGoogle Scholar
  21. Goyal MK, Bharti B, Quilty J, Adamowski J, Pandey A (2014) Modeling of daily pan evaporation in subtropical climates using ANN, LS-SVR, fuzzy logic, and ANFIS. Expert Syst Appl 41(11):5267–5276CrossRefGoogle Scholar
  22. Jang JSR, Sun CT, Mizutani E (1997) Neuro-fuzzy and soft computing: a computational, approach to learning and machine Intelligence IEEE T Automat Control 42Google Scholar
  23. Kaboodvandpour S, Amanollahi J, Qhavami S, Mohammadi B (2015) Assessing the accuracy of multiple regressions, ANFIS, and ANN models in predicting dust storm occurrences in Sanandaj, Iran. Nat Hazards 78(2):879–893CrossRefGoogle Scholar
  24. Kanada M, Dong L, Fujita T, Fujii M, Inoue T, Hirano Y, Togawa T, Geng Y (2013) Regional disparity and cost-effective SO2 pollution control in China: a case study in 5 mega-cities. Energy Policy 61:1322–1331CrossRefGoogle Scholar
  25. Khan JA, Aelst SV, Zamar RH (2007) Building a robust linear model with forward selection and stepwise procedures. Comput Stat Data Anal 52(1):239–248CrossRefGoogle Scholar
  26. Khaniabadi Y, Goudarzi G, Daryanoosh S, Borgini A, Tittarelli A, De Marco A (2016) Exposure to PM10, NO2, and O3 and impacts on human health. Environ Sci Pollut Res 24(3):2781–2789CrossRefGoogle Scholar
  27. Khedairia S, Tarek Khadir M (2012) Impact of clustered meteorological parameters on air pollutants concentrations in the region of Annaba, Algeria. Atmos Res 113:89–101CrossRefGoogle Scholar
  28. Kutner MH, Nachtsheim CJ, Neter J, Li W (2005) Applied linear statistical models, 5th edn. McGraw-Hill, pp 408–409Google Scholar
  29. Legates DR, McCabe GJ (1999) Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation. Water Resour Res 35(1):233–241CrossRefGoogle Scholar
  30. Li YF, Xie M, Goh TN (2010) Adaptive ridge regression system for software cost estimatingon multi-collinear datasets. J Syst Softw 83(11):2332–2343CrossRefGoogle Scholar
  31. Marino D, Morabito FC, Ricca B (2001) Management of uncertainty in environmental problems: an assessment of technical aspects and policies. In: GilAluja J (ed) Handbook of uncertainty. Kluwer Academic Publisher, New YorkGoogle Scholar
  32. Mohammadi K, Shamshirband S, Petkovic D, Yee PL, Mansor Z (2016) Using ANFIS for selection of more relevant parameters to predict dew point temperature. Appl Therm Eng 96:311–319CrossRefGoogle Scholar
  33. Naderloo L, Alimardani R, Omid M, Sarmadian F, Javadikia P, Torabi MY, Alimardani F (2012) Application of ANFIS to predict crop yield based on different energy inputs. Measurement 45(6):1406–1413CrossRefGoogle Scholar
  34. Noori R, Abdoli MA, Farokhnia A, Abbasi M (2009) RETRACTED: results uncertainty of solid waste generation forecasting by hybrid of wavelet transform-ANFIS and wavelet transform-neural network. Expert Syst Appl 36(6):9991–9999CrossRefGoogle Scholar
  35. Prasad K, Gorai AK, Goyal P (2016) Development of ANFIS models for air quality forecasting and input optimization for reducing the computational coast and time. Atmos Environ 128:246–262CrossRefGoogle Scholar
  36. Sheta A, Faris H, Rodan A, Kovac-Andric E, Al-Zoubi AM (2018) Cycle reservoir with regular jumps for forecasting ozone concentrations: two real cases from the east of Croatia. Air Qual Atmos Health 11(5):559–569CrossRefGoogle Scholar
  37. Soltani F, Kerachian R, Shirangi E (2010) Developing operating rules for reservoirs considering the water quality issues: application of ANFIS-based surrogate models. Expert Syst Appl 37(9):6639–6645CrossRefGoogle Scholar
  38. Struzewska J, Kaminski JW, Jefimow M (2016) Application of model output statistics to the GEM-AQ high resolution air quality forecast. Atmos Res 181:186–199CrossRefGoogle Scholar
  39. Timonen H, Widger N, Jaffe D (2013) Influence of background particulate matter (PM) on urban air quality in the Pacific Northwest. J Environ Manag 129:333–340CrossRefGoogle Scholar
  40. Tsakiri KG, Zurbenko IG (2011) Prediction of ozone concentration using atmospheric variables. Air Qual Atmos Health 4(2):111–120CrossRefGoogle Scholar
  41. Vlachogianni A, Kassomenos P, Karppinen A, Karakitsios S, Kukkonen J (2011) Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki. Sci Total Environ 409(8):1559–1571CrossRefGoogle Scholar
  42. Wang XX, Chen S, Lowe D, Harris CJ (2006) Sparse support vector regression based on orthogonal forward selection for the generalised kernel model. Neurocomputing 70(1–3):462–474CrossRefGoogle Scholar
  43. Wang J, Xu H, Guinot B, Li L, Sai Hang Ho S, Liu S, Li X, Cao J (2017) Concentrations, sources and health effects of parent, oxygenated-and nitrated-polycyclic aromatic hydrocarbons (PAHs) in middle-school air in Xian, China. Atmos Res 192:1–10CrossRefGoogle Scholar
  44. Wendish MS, Mertes MW, Ruggaber A, Nakajima T (1996) Vertical profiles and radiation and the influence of a temperature inversion: measurements and radiative transfer calculations. J Appl Meteorol 35(10):1703–1715CrossRefGoogle Scholar
  45. Willmott CJ (1981) On the validation of models. Phys Geogr 2(2):184–194CrossRefGoogle Scholar
  46. Yilmaz I, Kaynar O (2011) Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils. Expert Syst Appl 38(5):5958–5966CrossRefGoogle Scholar
  47. Yu H, Remer LA, Chin M, Bian H, Tan Q, Yuan T, Zhang Y (2012) Aerosol from overseas rival domestic emissions over North America. Science 337:566–569CrossRefGoogle Scholar
  48. Zhang H, Wang Y, Park TW, Deng Y (2017a) Quantifying the relationship between extreme air pollution events and extreme weather events. Atmos Res 188:64–79CrossRefGoogle Scholar
  49. Zhang Q, Jiang X, Tong D, Davis SJ, Zhao H, Geng G, Feng T, Zheng B, Lu Z, Streets DG, Ni R, Brauer M, van Donkelaar A, Martin RV, Huo H, Liu Z, Pan D, Kan H, Yan Y, Lin J, He K, Guan D (2017b) Transboundary health impacts of transported global air pollution and international trade. Nature 543:705–709CrossRefGoogle Scholar
  50. Zhou Q, Jiang H, Wang J, Zhou J (2014) A hybrid model for PM2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network. Sci Total Environ 496:264–274CrossRefGoogle Scholar

Copyright information

© Springer Nature B.V. 2018

Authors and Affiliations

  1. 1.University of KurdistanSanandajIran

Personalised recommendations