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.

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 PM_{10, t+1} model was the best MLR model to predict PM₁₀ during transboundary haze events compared to PM_10,.t+2 and PM_10,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.

The aim of the measurement of this data is to evaluate the Indoor Air Quality (IAQ) in terms of chemical and physical parameters. Data were collected at three different kindergartens having different surrounding activities (industrial, institutional, residential area). The chemical parameters measured were respirable suspended particulates of PM10, PM2.5, PM1, carbon monoxide and carbon dioxide, and the concentrations are within the acceptable limit. Physical parameters of wind speed are within the standard, while temperature and relative humidity exceeded the acceptable limit. A strong correlation was found between the chemical IAQ parameters with thermal comfort parameters (temperature and relative humidity). The concentration of IAQ pollutants is higher in order of residential > institutional > industrial.

Ground-level ozone is one of the dominant criteria pollutants that contribute to unhealthy days in ambient air measurements throughout Malaysia. In addition to VOCs and NOx, meteorological factors such as insolation and temperature influence the formation of ground-level ozone. For this reason, the relationship between daily maximum temperature and variation of ground-level ozone concentrations using 10 years of data (2000-10, excluding 2008) was scrutinized statistically at two stations representing urban and industrial areas in Terengganu State, Malaysia. We found that there is a positive linear correlation between maximum daily temperature and maximum daily ozone concentration with correlation coefficients of 0.684 and 0.605 for urban and industrial areas, respectively. Nevertheless, the long-term variation of daily maximum temperature and daily maximum ozone concentration for these two stations shows that the levels were higher in the industrial rather than the urban area. The results indicate that surrounding activities and temperature play vital roles in influencing ground-level ozone concentrations in Terengganu. Furthermore, ozone concentrations are highest for air masses characterized by dry, warm conditions during the southwest monsoon and are usually associated with the generation of haze episodes in the Malaysian Peninsula.