Different Approaches of Multiple Linear Regression (MLR) Model in Predicting Ozone (O3) Concentration in Industrial Area

• Published in: International Journal of Integrated Engineering
• Main Author: Napi N.N.L.M.; Abdullah S.; Mansor A.A.; Ghazali N.A.; Ahmed A.N.; Dom N.C.; Ismail M.
• Format: Article
• Language: English
• Published: Penerbit UTHM 2023
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85152670270&doi=10.30880%2fijie.2023.15.01.010&partnerID=40&md5=c8852861b94efa67c188866ac16469e3

Meteorological conditions and other gaseous pollutants generally impacted the development of ozone (O3) in the atmosphere. The purpose of this study was to create the best O3 model for forecasting O3 concentrations in the industrial area and to determine the variables that affect O3 concentrations. Five-year data of meteorological and gaseous pollutants were used to analyze and develop the prediction model. Based on three distinct techniques, three separate multiple linear regression (MLR) prediction models of O3 concentration were developed. MLR3 had the highest correlation coefficient of 0.792 during development as compared to models MLR1 and MLR2. MLR2 was deemed the best O3 prediction model, however, since it had the lowest error values of root mean square error (3.976) and mean absolute error (3.548) when compared to other models. The establishment of an O3 prediction model can offer local governments with early information that could help them reduce and manage air pollution emissions. © 2023 UTHM Publisher. All rights reserved.