Journal of Transportation Engineering and Its Applications ISSN: 3107-4499 (Online)

Authors: Dr. Sneha Rajan, Mr. Arvind Bhattacharya

Abstract: The exponential growth of urban populations has led to complex transportation challenges, particularly in managing and predicting traffic flow efficiently. Traditional traffic modeling techniques often struggle to handle the dynamic, non-linear, and stochastic nature of urban traffic systems. In recent years, machine learning (ML) has emerged as a transformative tool in transportation engineering, offering data-driven approaches for real-time traffic prediction and congestion mitigation. This paper explores the role of machine learning in traffic flow prediction from a transportation engineering perspective. It analyzes various ML algorithms, discusses implementation challenges, and investigates the scope for integration with smart mobility infrastructure. The paper also identifies future directions for research, aiming to promote sustainable, intelligent transportation systems that can adapt to real-world uncertainties.

Keywords: Machine Learning, Traffic Flow Prediction, Transportation Engineering, Intelligent Transport Systems, Urban Mobility