Prediction of Particulate Matter (PM₁₀) during High Particulate Event in Peninsular Malaysia using Novel Hybrid Model

¹ Faculty of Civil Engineering & Technology, Universiti Malaysia Perlis, Jejawi 02600, Perlis, Malaysia
² Sustainable Environment Research Group (SERG), Centre of Excellence Geopolymer and Green Technology (CEGeoGTech), Universiti Malaysia Perlis, Jejawi 02600, Perlis, Malaysia
³ Faculty of Computer and Mathematical Sciences, Universiti Teknologi Mara (UiTM), Shah Alam 40450, Selangor, Malaysia
⁴ National Institute for Research and Development in Environmental Protection INCDPM, Splaiul Independentei 294, 060031 Bucharest, Romania

^* Corresponding author: norazian@unimap.edu.my

Abstract

High Particulate Events (HPE) contributes to the deterioration of air quality, as the fine particles present can be inhaled, leading to respiratory diseases and other health problem. Knowing the adverse effects of air pollution episodes to human health, it is crucial to create suitable models that can effectively and accurately predict air pollution concentration. This study proposed a hybrid model for forecasting the next day PM₁₀ concentration in peninsular Malaysia namely Shah Alam, Nilai, Bukit Rambai and Larkin. Hourly air pollutant concentration (PM₁₀, NO_x, NO₂, SO₂, CO, O₃) and meteorological parameters (RH, T, WS) during the HPE events in 1997, 2005, 2013 and 2015 were used. Support Vector Machine (SVM) and Quantile Regression (QR) was combined to construct a hybrid models (SVM-QR) to reduce the number of input variables. Performance indicators such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) and Index of Agreement (d₂) were used to evaluate the performance of the predictive models. SVM-QR model resulted good performance in all areas. SVM-3 was selected as the best model at Bukit Rambai (MAE=5.72, RMSE=9.71) and Shah Alam (MAE=11.89, RMSE=22.66), while SVM-1 as the best model at Larkin and Nilai with the value (MAE=7.22, RMSE=13.38) and (MAE=6.88, RMSE=11.84), respectively. This strategy was proven to help reducing the complexity of the model and enhance the predictive capacity of the model.