Current Volume 9
Rapid urban expansion in Indian cities has significantly improved infrastructure and accessibility, but it has also intensified environmental challenges such as air pollution and traffic congestion. Existing systems often provide fragmented real-time data without predictive capabilities, limiting their usefulness for proactive decision-making.In this work, we design and develop CitySense, an AI-based smart city dashboard that integrates air quality monitoring and traffic analysis into a unified framework. The system utilizes real-time data from APIs such as OpenAQ, WeatherAPI, and Google Maps, and applies machine learning models including ARIMA, Prophet, and LSTM to forecast AQI levels and traffic patterns. Experimental observations across cities such as Delhi, Mumbai, and Amritsar indicate that LSTM achieves higher prediction accuracy compared to traditional models. The system also highlights a strong relationship between traffic density and air pollution levels. The results are presented through an interactive visualization dashboard, enabling users to understand trends, predict future conditions, and receive alerts.The proposed system aims to move beyond passive monitoring by enabling proactive decision-making for citizens, urban planners, and researchers, thereby contributing to the development of smarter and more sustainable cities.
Smart City, AQI Prediction, Traffic Forecasting, Machine Learning, LSTM, ARIMA, Data Visualization
IRE Journals:
Prof. Archana Pakhare, Tulja Raut, Aaruni Sinha "CitySense – AI-based Smart City Dashboard for AQI & Traffic Monitoring" Iconic Research And Engineering Journals Volume 9 Issue 10 2026 Page 3857-3861 https://doi.org/10.64388/IREV9I10-1717151
IEEE:
Prof. Archana Pakhare, Tulja Raut, Aaruni Sinha
"CitySense – AI-based Smart City Dashboard for AQI & Traffic Monitoring" Iconic Research And Engineering Journals, 9(10) https://doi.org/10.64388/IREV9I10-1717151