Predictive Model for Air Pollutants Concentration Using Machine Learning

Author(s)	Devanshu Pote, Mr. Piyoosh Awthare, Prerna Hiradkar, Manthan Shinde
Country	India
Abstract	The Air Quality Index (AQI) is widely used by government agencies to communicate air pollution severity to the public and is derived from pollutants such as sulphur dioxide, nitrogen dioxide, ozone, PM₁₀ and PM₂.₅. Although several AQI calculation methods have been proposed, no universally applicable approach exists. In this work, standard classification and regression techniques are enhanced by incorporating temporal correlations among sub-models. Historical and meteorological data are utilized to predict pollutant concentrations and forecast AQI over short-term and long-term horizons. The system is trained and evaluated using air pollution data from 2019 to 2024 covering ten Indian cities. Regression-based machine learning models and R-ARIMA time-series forecasting with moving average smoothing are employed to generate daily and monthly AQI predictions. The results demonstrate reliable forecasting performance and support effective air quality monitoring and planning.
Keywords	Air Quality Index, Machine Learning, Time Series Forecasting, Environmental Analytics, ARIMA
Published In	Volume 7, Issue 2, March-April 2026
Published On	2026-04-24
DOI	https://doi.org/10.63363/aijfr.2026.v07i02.5181

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research