Analysing ML Models for AQI Prediction using Meteorological Data

Abstract

Air is essential for every living being to survive. The modernization and industrialization have led to the rise of pollutants which affect the quality of air directly. Predicting changes in air pollutant concentrations due to human and nature drivers is critical and challenging, particularly in areas with scant data inputs and high variability of parameters. The air quality index (AQI) is an index for reporting air quality on a daily basis. It is a measure of how air pollution affects one's health within a short time period. The purpose of the AQI is to help people know how the local air quality impacts their health. The Environmental Protection Agency (EPA) calculates the AQI for five major air pollutants, for which national air quality standards have been established to safeguard public health. Every country has its own method of calculating the Air Quality Index and the rules for Air Quality Buckets. According to the Central pollution control board, Ministry of Environment, Forests, and climate change of India, the AQI is divided into 6 buckets with the minimum and maximum AQI being 0 and 500 respectively. The buckets are Good, Satisfactory, Moderate, Poor, Very Poor and Severe.