A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)

Chemosphere. 2023 Mar:317:137788. doi: 10.1016/j.chemosphere.2023.137788. Epub 2023 Jan 12.

Abstract

Presence of particulate matters with aerodynamic diameter of less than 2.5 μm (PM2.5) in the atmosphere is fast increasing in Malaysia due to industrialization and urbanization. Prolonged exposure of PM2.5 can cause serious health effects to human. This research is aimed to identify the most reliable model to predict the PM2.5 pollution using multi-layered feedforward-backpropagation neural network (FBNN). Air quality and meteorological data were collected from Department of Environment (DOE) Malaysia. Six different training algorithms consisting of thirteen various training functions were trained and compared. FBNN model with the highest coefficient correlation (R2) and lowest root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) were selected as the best performing model. Levenberg Marquardt (trainlm) is the best performing algorithms compared to other algorithms with R2 value of 0.9834 and the lowest error values for RMSE (2.3981), MAE (1.7843) and MAPE (0.1063).

Keywords: Air pollution; Artificial neural network; Feedforward-backpropagation; PM(2.5); Prediction; Training algorithms.

MeSH terms

  • Air Pollutants* / analysis
  • Air Pollution* / analysis
  • Algorithms
  • Environmental Pollution
  • Humans
  • Neural Networks, Computer
  • Particulate Matter / analysis

Substances

  • Particulate Matter
  • Air Pollutants