The PM 2.5 concentrations dominated the Air Pollutant Index (API) in Malaysia. • There were several reductions on PM 2.5 concentrations during Malaysia Movement Control Order (MCO). • Several red zone areas showed approximately 28.3% reduction of PM 2.5 concentrations. • The Northern Region of Peninsular Malaysia showed the highest average reduction of PM 2.5 concentrations, with 23.7%.

The general air quality of Malaysia since 1970 has deteriorated. Studies have shown that should no effective countermeasures be introduced, the emissions of sulfur dioxide, nitrogen oxides, particulate matter, hydrocarbons and carbon monoxide in the year 2005 would increase by 1.4, 2.12, 1.47 and 2.27 times, respectively, from the 1992 levels.

High level of tropospheric ozone concentration, exceeding allowable level has been frequently reported in Malaysia. This study proposes accurate model based on Machine Learning algorithms to predict Tropospheric ozone concentration in major cities located in Kuala Lumpur and Selangor, Malaysia. The proposed models were developed using three-year of historical data for different parameters as input to predict 24-hour and 12-hour of tropospheric ozone concentration. Different Machine Learning algorithms have been investigated, viz. Linear Regression, Neural Network and Boosted Decision Tree. The results revealed that wind speed, humidity, Nitrogen Oxide, Carbon Monoxide and Nitrogen Dioxide have significant influence on ozone formation. Boosted Decision Tree outperformed Linear regression and Neural Network algorithms for all stations. The performance of the proposed model improved by using 12-hours dataset instead of the 24-hour where R 2 values were equal to 0.91, 0.88 and 0.87 for the three investigated stations. To assess the uncertainties of the Boosted Decision Tree model, 95% prediction uncertainties (95PPU) d-factors were introduced.95PPU showed about 94.4, 93.4, 96.7% and the d-factors were 0.001015, 0.001016 and 0.001124 which relate to S1, S2 and S3, respectively. The obtained results provide a reliable prediction model to mimic actual ozone concentration in different locations in Malaysia.

Malaysia has been facing transboundary haze events every year in which the air contains particulate matter, particularly PM10, which affects human health and the environment. Therefore, it is crucial to develop a PM10 forecasting model for early information and warning alerts to the responsible parties in order for them to mitigate and plan precautionary measures during such events. Therefore, this study aimed to develop and compare the best-fitted model for PM10 prediction from the first hour until the next three hours during transboundary haze events. The air pollution data acquired from the Malaysian Department of Environment spanned from the years 2005 until 2014 (excluding years 2007–2009), which included particulate matter (PM10), ozone (O3), nitrogen oxide (NO), nitrogen dioxide (NO), carbon monoxide (CO), sulfur dioxide (SO2), wind speed (WS), ambient temperature (T), and relative humidity (RH) on an hourly basis. Three different stepwise Multiple Linear Regression (MLR) models for predicting the PM10 concentration were then developed based on three different prediction hours, namely t+1, t+2, and t+3. The PM10, t+1 model was the best MLR model to predict PM10 during transboundary haze events compared to PM10,.t+2 and PM10,t+3 models, having the lowest percentage of total error (28%) and the highest accuracy of 46%. A better prediction and explanation of PM10 concentration will help the authorities in getting early information for preserving the air quality, especially during transboundary haze episodes.

Air quality status on the East Coast of Peninsular Malaysia is dominated by Particulate Matter (PM10) throughout the years. Studies have affirmed that PM10 influence human health and the environment. Therefore, precise forecasting algorithms are urgently needed to determine the PM10 status for mitigation plan and early warning purposes. This study investigates the forecasting performance of a linear (Multiple Linear Regression) and two non-linear models (Multi-Layer Perceptron and Radial Basis Function) utilizing meteorological and gaseous pollutants variables as input parameters from the year 2000–2014 at four sites with different surrounding activities of urban, sub-urban and rural areas. Non-linear model (Radial Basis Function) outperforms the linear model with the error reduced by 78.9% (urban), 32.1% (sub-urban) and 39.8% (rural). Association between PM10 and its contributing factors are complex and non-linear in nature, best captured by an Artificial Neural Network, which generates more accurate PM10 compared to the linear model. The results are robust enough for precise next day forecasting of PM10 concentration on the East Coast of Peninsular Malaysia.