• Gurjas Singh Gandhi
• Dr. Prakash Kene
• Nikita Bachute
• Pranav Gadewar
• Ritwik Rahut

This paper presents Vayu Drishti, a real-time air quality monitoring and forecasting system addressing air pollution tracking through multi-source data integration. The system combines data from Central Pollution Control Board (CPCB) ground stations (40 stations across 16 states), ISRO's INSAT-3D satellite, and NASA's MERRA-2 meteorological data. Our feature engineering framework extracts 69 attributes (33 base + 36 engineered features), capturing pollutant interactions, meteorological influences, and temporal patterns. The Random Forest ensemble model achieves R² = 0.9994 and RMSE = 4.57 with 8.3-second training time. The system provides 24-hour forecasts through XGBoost and LSTM models with 92-96% accuracy via a Streamlit web interface with sub-200ms API response time.

Air quality monitoring, Random Forest, Multi-source integration, Real-time prediction, Machine learning, Satellite data, Environmental informatics, Deep learning

"VAYU DRISHTI: REAL-TIME AIR QUALITY MONITORING WITH MULTI-SOURCE DATA INTEGRATION AND MACHINE LEARNING FORECASTING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.e322-e328, November-2025, Available :http://www.jetir.org/papers/JETIR2511440.pdf

"VAYU DRISHTI: REAL-TIME AIR QUALITY MONITORING WITH MULTI-SOURCE DATA INTEGRATION AND MACHINE LEARNING FORECASTING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppe322-e328, November-2025, Available at : http://www.jetir.org/papers/JETIR2511440.pdf