Publication: Forecasting particulate matter (PM10) concentration: A radial basis function neural network approach
No Thumbnail Available
Date
2018
Authors
Abdullah S.
Ismail M.
Ghazali N.A.
Ahmed A.N.
Journal Title
Journal ISSN
Volume Title
Publisher
American Institute of Physics Inc.
Abstract
Particulate matter is a prevalent pollutant that affects human health and the environment. Local authorities need a precise PM10 concentration forecasting model as the information can be used to take precautionary measures and significant actions can be taken to improve air quality status. This study trained and tested the nonlinear model, namely Radial Basis Function (RBF) in an industrial area of Pasir Gudang, Johor. Daily observations of PM10 concentration, meteorological factors (wind speed, ambient temperature, and relative humidity) and gaseous pollutants (SO2, NO2, and CO) from the year 2010-2014 were used in this study. Results showed that RBF model was able to explain 65.2% (R2 = 0.652) and 84.9% (R2 = 0.849) variance in the data during training and testing, respectively. Thus, it is proven that nonlinear model has high ability in virtually representing the complexity and nonlinearity of PM10 in the atmosphere without any prior assumptions. � 2018 Author(s).