Integration of ANFIS model and forward selection method for air quality forecasting
- 47 Downloads
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.
KeywordsComputational 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.
- Armstrong JS (1999) Forrecasting for environmental decision making. University of Pennsylvania. Retrieved from https://repository.upenn.edu/marketing_papers/1
- 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
- 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
- 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
- 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
- Kutner MH, Nachtsheim CJ, Neter J, Li W (2005) Applied linear statistical models, 5th edn. McGraw-Hill, pp 408–409Google Scholar
- 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
- 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