Research Article Open Access

Seasonal ARIMA for Forecasting Air Pollution Index: A Case Study

Muhammad Hisyam Lee1, Nur Haizum Abd. Rahman1, Suhartono 2, Mohd Talib Latif1, Maria Elena Nor1 and Nur Arina Bazilah Kamisan1
  • 1 , Afganistan
  • 2 ,
American Journal of Applied Sciences
Volume 9 No. 4, 2012, 570-578


Submitted On: 4 November 2011 Published On: 14 February 2012

How to Cite: Lee, M. H., Rahman, N. H. A., Suhartono, Latif, M. T., Nor, M. E. & Kamisan, N. A. B. (2012). Seasonal ARIMA for Forecasting Air Pollution Index: A Case Study. American Journal of Applied Sciences, 9(4), 570-578.


Problem statement: Both developed and developing countries are the major reason that affects the world environment quality. In that case, without limit or warning, this pollution may affect human health, agricultural, forest species and ecosystems. Therefore, the aim of this study was to determine the monthly and seasonal variations of Air Pollution Index (API) at all monitoring stations in Johor. Approach: In this study, time series models will be discussed to analyze future air quality and used in modeling and forecasting monthly future air quality in Malaysia. A Box-Jenkins ARIMA approach was applied in order to analyze the API values in Johor. Results: In all this three stations, high values recorded at sekolah menengah pasir gudang dua (CA0001). This situation indicates that the most polluted area in Johor located in Pasir Gudang. This condition appears to be the reason that Pasir Gudang is the most developed area especially in industrial activities. Conclusion: Time series model used in forecasting is an important tool in monitoring and controlling the air quality condition. It is useful to take quick action before the situations worsen in the long run. In that case, better model performance is crucial to achieve good air quality forecasting. Moreover, the pollutants must in consideration in analysis air pollution data.

  • 15 Citations



  • Air Pollution Index (API)
  • time series modeling
  • ARIMA time series
  • air quality forecasting
  • pollution data