Open Access

ARTICLE

COVID19: Forecasting Air Quality Index and Particulate Matter (PM2.5)

R. Mangayarkarasi¹, C. Vanmathi^1,*, Mohammad Zubair Khan², Abdulfattah Noorwali³, Rachit Jain⁴, Priyansh Agarwal⁴

1 School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, 632007, India
2 Department of Computer Science, College of Computer Science and Engineering, Taibah University, 41477, Saudi Arabia
3 Department of Electrical Engineering, Umm Al Qura University, Makkah, 21955, Saudi Arabia
4 School of Computer Science and Engineering and Engineering, Vellore Institute of Technology, Vellore, 632007, India

* Corresponding Author: C. Vanmathi. Email:

(This article belongs to the Special Issue: Machine Learning-based Intelligent Systems: Theories, Algorithms, and Applications)

Computers, Materials & Continua 2021, 67(3), 3363-3380. https://doi.org/10.32604/cmc.2021.014991

Received 31 October 2020; Accepted 06 January 2021; Issue published 01 March 2021

Abstract

Urbanization affects the quality of the air, which has drastically degraded in the past decades. Air quality level is determined by measures of several air pollutant concentrations. To create awareness among people, an automation system that forecasts the quality is needed. The COVID-19 pandemic and the restrictions it has imposed on anthropogenic activities have resulted in a drop in air pollution in various cities in India. The overall air quality index (AQI) at any particular time is given as the maximum band for any pollutant. PM2.5 is a fine particulate matter of a size less than 2.5 micrometers, the inhalation of which causes adverse effects in people suffering from acute respiratory syndrome and other cardiovascular diseases. PM2.5 is a crucial factor in deciding the overall AQI. The proposed forecasting model is designed to predict the annual PM2.5 and AQI. The forecasting models are designed using Seasonal Autoregressive Integrated Moving Average and Facebook’s Prophet Library through optimal hyperparameters for better prediction. An AQI category classification model is also presented using classical machine learning techniques. The experimental results confirm the substantial improvement in air quality and greater reduction in PM2.5 due to the lockdown imposed during the COVID-19 crisis.

---

Keywords

---

Citations