Title: Air pollution prediction model for estimating and forecasting particulate matter PM_2.5 concentrations using SOSE-RMLP approach

Authors: V. Kanpur Rani; R. Vallikannu

Addresses: Hindustan Institute of Technology and Science, Padur, Kelambakkam, Chennai-603103, India ' Hindustan Institute of Technology and Science, Padur, Kelambakkam, Chennai-603103, India

Abstract: With poor air quality and air pollution issues, several countries around the globe are facing a challenging aspect. The main intention of air pollution modelling is to reliably predict the noxious air contaminants with their levels of concentrations in the forecasting model. There were several traditional methods employed in the prediction of air quality, however due to the existence of huge uncertainties of emission inventory (EI) there is a need for improvements and refinements in the accurate prediction. Hence, an approach to estimate the urban forecasting prediction of air quality that employs a statistical method with optimisation strategy for enhancing the prediction of air pollution is proposed. The proposed work attempts to introduce a new model for air pollution prediction and forecasting model analysis using processes such as preliminary processing using statistical method termed ordinal scaled encoding-based filtering process (SOSE).

Keywords: air pollution; air quality index; air quality prediction; residual multi-layer perceptron; RMLP; ordinal scaled encoding-based filtering process; SOSE; Taiwan Environmental Protection Agency; TEPA; convergent artificial bee colony optimisation; CABC; MAE; RMSE; MAPE.

DOI: 10.1504/IJGW.2023.130128

International Journal of Global Warming, 2023 Vol.29 No.4, pp.289 - 304

Received: 04 May 2022
Received in revised form: 17 Jun 2022
Accepted: 18 Jun 2022
Published online: 05 Apr 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article