Multivariate analysis of monsoon seasonal variation and prediction of particulate matter episode using regression and hybrid models

Abstract

Prediction of Particulate Matter (PM10) episode in advance enables for better preparation to avert and reduce the impact of air pollution ahead of time. This is possible with proper understanding of air pollutants and the parameters that influence its pattern. Hence, this study analyzed daily average PM10, temperature (T), humidity (H), wind speed (WS) and wind direction (WD) data for five years (2006)(2007)(2008)(2009)(2010), from two industrial air quality monitoring stations. This data was used to evaluate the impact of meteorological parameters and PM10 in two peculiar seasons; Southwest Monsoon (SWM) and Northeast Monsoon (NEM) seasons, using Principal Component Analysis (PCA). Subsequently, Lognormal Regression (LR), Multiple Linear Regression (MLR) and Principal Component Regression (PCR) methods were used to forecast next day average PM10 concentration level. The PCA result (seasonal variability) showed that peculiar relationship exist between PM10 pollutants and meteorological parameters. For the prediction models, the three methods gave significant results in terms of performance indicators. However, PCR had better predictability, having a higher coefficient of determination (R 2 ) and better performance indicator results than LR and MLR methods. The outcomes of study signify that PCR models can be effectively used as a suitable format in predicting next day average PM10 concentration levels.

Use of Trajectory Regression Analysis to Understand High-PM10 Episodes: a Case Study in Limeira, Brazil

“…Analysis of air quality monitoring data by statistical tools (Nogarotto & Pozza, 2020) has been largely used to study pollution in specific locations (Ventura et al, 2018;Yao et al, 2021), emission comparisons (Kong et al, 2013), and air quality forecasting (Nazif et al, 2019;Pinto et al, 2018), among others. Wang et al (2015) showed the importance of studies on high concentration episodes to assess health and climate impacts and to support measures for air pollution control.…”