Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{182540,
        author = {Tarun Pandit and Vishnupant Potdar and Nagnath Biradar},
        title = {Air Quality Prediction Using Machine Learning Algorithm in Maharashtra},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {2440-2442},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182540},
        abstract = {Air pollution poses a severe and multifaceted risk to public health, economic productivity, and environmental sustainability, particularly in rapidly urbanizing regions such as Maharashtra, India. This research presents a comprehensive comparison of classical and ensemble machine learning algorithms—for example, Linear Regression, Random Forest, and XGBoost—in forecasting the Air Quality Index (AQI) across three major metropolitan areas: Mumbai, Pune, and Nagpur. The dataset comprises hourly pollutant concentrations (PM2.5, PM10, O3, NO2, CO, SO2) and meteorological variables (temperature, humidity, wind speed, rainfall) collected via Mendeley Data and the CPCB API over a two-year period. Key steps include rigorous data preprocessing, advanced feature engineering—including lag and interaction terms—and systematic hyperparameter tuning with five-fold cross-validation. Model performance is evaluated using RMSE, MAE, and R² metrics. Results indicate that XGBoost consistently yields superior predictive accuracy (R² up to 0.92), while Random Forest offers robust interpretability through feature importance analysis. City-specific findings reveal that PM2.5 and NO2 are the dominant drivers of AQI variation in Mumbai, whereas meteorological factors play a larger role in Pune and Nagpur. These insights can guide targeted mitigation strategies and inform data-driven policy development.},
        keywords = {Air Quality Index, Machine Learning, Maharashtra, XGBoost, Random Forest, Pollution Forecasting, Feature Engineering, Hyperparameter Tuning},
        month = {July},
        }