• Mahesh Chhagan Patil
• Snehal Mahesh Katke

Abstract : This research explores air quality classification and forecasting by leveraging multi-source environmental data, aiming to improve the accuracy and timeliness of air quality predictions. By integrating data from various sources such as pollutant levels, meteorological conditions, and traffic patterns, the study utilizes machine learning algorithms to classify air quality into distinct pollution levels and predict future air quality trends. The research compares different machine learning models, including gradient boosting, XGBoost, LightGBM, and CatBoost, to assess their effectiveness in predicting air quality in both urban and rural environments. Model performance comparison showed that XGBoost achieved the highest accuracy (0.9570), followed by GradientBoosting (0.9560), CatBoost (0.9560), and LightGBM (0.9400). The findings aim to provide actionable insights for policymakers, environmental agencies, and the public, facilitating better air quality management and mitigating health risks associated with air pollution.

Multi Source, Quality, Classification, Air Quality,Forecasting.

"Air Quality Classification and Forecasting: Insights from Multi-Source Environmental Data ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.c650-c655, December-2024, Available :http://www.jetir.org/papers/JETIR2412275.pdf

"Air Quality Classification and Forecasting: Insights from Multi-Source Environmental Data ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppc650-c655, December-2024, Available at : http://www.jetir.org/papers/JETIR2412275.pdf