• K.Kavitha Lakshmi
• Dr. M.V.R. Jyothisree
• Dontaraju Rama Srikari
• Mallepally Pravalika
• Bagili Nikhitha

This paper presents a hybrid deep learning-based approach for future traffic prediction aimed at enhancing urban traffic management. With increasing urbanization and vehicular density, efficient traffic forecasting has become critical. The proposed model integrates Long Short-Term Memory (LSTM) networks and Graph Neural Networks (GNNs) to capture temporal and spatial dependencies within traffic data. Historical and real-time data from OpenStreetMap and Google Maps Distance Matrix API are utilized for training. A Flask-based web application offers real-time visualization and predictions. Results demonstrate the model's robustness in predicting traffic flow, thereby supporting data-driven urban planning.

Traffic prediction, deep learning, LSTM, Graph Neural Networks (GNN), spatial-temporal modeling, smart cities.

"Future Traffic Prediction Using Deep Learning: A Hybrid Approach with LSTM and Graph Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.377-381, May-2025, Available :http://www.jetir.org/papers/JETIRGV06055.pdf

"Future Traffic Prediction Using Deep Learning: A Hybrid Approach with LSTM and Graph Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. pp377-381, May-2025, Available at : http://www.jetir.org/papers/JETIRGV06055.pdf