Development of PM10 pollutant forecasting model at different geographical areas through phase space reconstruction approach

Nor Zila Abd Hamid

Abstract

This study focused on development of PM10 pollutant forecasting model at different geographical areas namely background (Jerantut, Pahang), industrial (Bukit Rambai, Malacca) and urban (Klang, Selangor) through phase space reconstruction approach. Firstly, PM10 pollutant is reconstructed into a multi-dimensional phase space. Then, the reconstruct phase space is used to forecast future PM10 pollutant. Comparison with traditional approach of autoregressive linear through mean absolute error and root mean squared error showed that phase space reconstruction approach is better. Furthermore, values of correlation coefficient showed that PM10 pollutant is forecasted well through phase space reconstruction approach. In conclusion, development of PM10 pollutant forecasting models at different geographical areas are success. These findings are expected to help stakeholders in having a better PM10 pollutant management.

References

Abarbanel, H. D. I. (1996). Analysis of Observed Chaotic Data. New York: Springer- Verlag, Inc.

Abdullah, S., Ismail, M., & Fong, S. Y. (2017). Multiple Linear Regression (MLR) Models for Long Term PM10 Concentration Forecasting during Different Monsoon Seasons. Journal of Sustainability Science and Management, 12(1), 60–69.

Adenan, N. H., & Noorani, M. S. M. (2014). Nonlinear Prediction of River Flow in Different Watershed Acreage. KSCE Journal of Civil Engineering, 18(7), 2268–2274.

Adenan, N. H., & Noorani, M. S. M. (2015). Predicting Time Series Data at Floodplain Area Using Chaos Approach. Sains Malaysiana, in Malay, 44(3), 463–471.

DOE. (2018). Main Sources of Air Pollution in Malaysia. Retrieved from www.doe.gov.my

Gu, Y., Lin, H., Liu, T., Xiao, J., Zeng, W., Li, Z., (2017). The Interaction between Ambient PM10 and NO2 on Mortality in Guangzhou, China. International Journal of Environmental Research and Public Health, 14(1381).

Hamid, N. Z. A., Adenan, N. H., & Noorani, M. S. M. (2017). Forecasting and Analyzing High O3 Time Series in Educational Area through an Improved Chaotic Approach. In AIP Conference Proceedings (Vol. 1870, pp. 1–8).

Hamid, N. Z. A., & Noorani, M. S. M. (2017). New Improved Chaotic Approach Model Application on Forecasting Ozone Concentration Time Series. Sains Malaysiana, 46(8), 1333–1339.

Jayawardena, A. W. (1997). Runoff Forecasting Using a Local Approximation Method. IAHS, 239, 167–171.

Jie, Y. (2017). Air Pollution Associated with Sumatran Forest Fires and Mortality on the Malay Peninsula. Polish Journal of Environmental Studies, 26(1), 163–171.

Kamarehie, B., Ghaderpoori, M., Jafari, A., Karami, M., Mohammadi, A., Azarshab, K., et al. (2017). Estimation of Health Effects (Morbidity and Mortality) attributed to PM10 and PM2.5 Exposure Using an Air Quality Model in Bukan City. Environmental Health Engineering and Management Journal, 4(3), 137–142.

Sprott, J. C. (2003). Chaos and Time-Series Analysis. Oxford University Press.

Ul-saufie, A. Z., Yahya, A. S., Ramli, N. A., & Hamid, H. A. (2011). Comparison between Multiple Linear Regression and Feed Forward Back Propagation Neural Network Models for Predicting PM10 Concentration Level Based on Gaseous and Meteorological Parameters. International Journal of Applied Science and Technology, 1(4), 42–49.

World Health Organization. (2017). World Health Statistics 2017: Monitoring Health for the Sustainable Development Goals. World Health Organization.