The Malaysian Journal of Analytical Sciences Vol 12 No 1 (2008): 257 – 263

 

 

ARIMA AND INTEGRATED ARFIMA MODELS FOR FORECASTING AIR POLLUTION INDEX IN SHAH ALAM, SELANGOR

 

Lim Ying Siew, Lim Ying Chin and Pauline Mah Jin Wee

 

International Education Centre (INTEC), Universiti Teknologi MARA Section 17 Campus,

40200 Shah Alam, Selangor.

 

Abstract

Air  pollution is  one  of  the  major  issues  that has  been affecting  human health, agricultural crops,  forest  species  and ecosystems. Since 1980, Malaysia has had a series of haze episodes and the worst ever was reported in 1997. As a result, the government has established the Malaysia Air Quality Guidelines, the Air Pollution Index (API) and Haze Action Plan, to improve the air quality. The API was introduced as an index system for classifying and reporting the ambient air quality in Malaysia. The API for a given period is calculated based on the sub-index value (sub-API) for all the five air pollutants, namely sulphur dioxide (SO₂), nitrogen dioxide (NO₂), ozone (O₃), carbon monoxide (CO) and particulate matter below 10 micron size (PM₁₀). The forecast of air pollution can be used for air pollution assessment and management. It can serve as information and warning to  the public in cases of high air pollution levels and for policy management of many different chemical compounds. Hence, the objective of this project is to fit and illustrate the use of time series models in forecasting the API in Shah Alam, Selangor. The data used in this study consists of 70 monthly observations of API (from March 1998 to December 2003) published in the Annual Reports of the Department of Environment, Selangor. The time series models that were being considered were the Integrated Autoregressive Moving  Average (ARIMA) and the Integrated Long Memory Model (ARFIMA) models. The lowest MAE, RMSE and MAPE values were used as the model selection criteria. Between these two models considered, the integrated ARFIMA model appears to be the better model as it has the lowest MAPE value. However, the actual  value of May 2003 falls outside the 95% forecast interval, probably due to emissions from mobile sources (i.e., motor vehicles), industrial emissions, burning of solid wastes and forest fires.

 

Keywords: Air Pollution Index (API), Integrated Autoregressive Moving Average (ARIMA), Fractionally Integrated

Autoregressive Moving Average (ARFIMA)

 

References

1.         Awang M. B., Jaafar A. B., Abdullah A. M., Ismail M.B., Hassan M.N., Abdullah R., Johan S. and Noor H. (2000), Air Quality In Malaysia: Impacts, Management Issues And Future Challenges, Respirology, Vol. 5, pp 183-196.

2.         Afroz  R.,  Hassan  M.N.  and  Ibrahim  N.A.  (2003),  Review  Of  Air  Pollution  And  Health  Impacts  In  Malaysia, Environmental Research, Volume 92, Issue 2, pp 71-77.

3.         Nasir M.H., Choo W.Y., Rafia A., Theng L.C., Noor M. M. H (2000), Estimation Of Health Damage Cost For 1997- Haze  Episode  In  Malaysia  Using  the  Ostro  model,  Proceeding  Malaysian  Science  And  Technology  Congress, Confederation Of Scientific And Technological Association In Malaysia,COSTAM, Kuala Lumpur, in Press.

4.         Faridah Mohamad (2002), Impacts Of Exposure To Ambient PM₁₀   On Hospital Outpatient Visits For  Haze-Related Diseases And School Children Lung Function, Masters Thesis. Universiti Putra Malaysia, Malaysia.

5.         Beardsley R., Bromberg P.A., Costa D.A., Devlin R., Dockery D. W., Frampton M. W., Lambert W.,  Samet J. M., Speizer F. E., Utell M.(1997), Smoke Alarm: Haze From Fires Might Promote Bacterial Growth. Science America, pp 24-25.

6.         National Environment Research   Institute,   NERI  (2003),  THOR.

            http://www.dmu.dk/1_viden/2_miljoe- tilstand/3_luft/4_spredningsmodeller/5_thor/default_en.asp.  

            Accessed on 27 April 2004.

7.         Dominici, F., McDermott, A., Hastie, T. J.(2004), Improved Semi-Parametric Time Series Models Of Air Pollution And Mortality. http://www-stat.stanford.edu/~hastie/Papers/dominiciR2.pdf.  Accessed on 27 April 2004.

8.         Awang M.B., Hassan M.N., Noor Alshurdin M.S., Abdullah A.M. (1997), Air pollution in Malaysia, in IMR Quaterly Bulletin, No. 43, pp 26-42.

9.         Annual Report (1998-2003), Department of Environment, Selangor.

10.     Brockwell, P.J. and Davis, R.A. (2002), Introduction To Time Series And Forecasting, 2nd   Edition,  Springer-Verlag, New York.