Road Traffic Flow Prediction with Visual Analytics

Traffic flow prediction is an important task in the field of transportation engineering and intelligent transportation systems. Accurate traffic flow prediction can help improve traffic management, reduce congestion and pollution, and increase road safety. Mitigation solutions are usually used to soften the impact of this problem in most cities. In particular, the city of Lisbon has taken measures to reduce pollution by closing areas of the city to the most polluting cars—the zero emission zones. However, the city still lacks visual analytics support for traffic decisions in real-time. In this chapter, we propose an approach to traffic flow prediction using machine learning techniques. Specifically, we propose a traffic flow indicator that can indicate road traffic fluidity inside a region of interest for a given time frame. We integrate it into an interactive dashboard supported by a predictive model. The model uses XGBoost to create a short-term time delay estimation for a region-of-interest. We find that our approach is able to achieve high Mean Squared Error (R \(^2\) ) results and low Mean Absolute Error (MAE). Additionally, we perform a user study to assess the quality of traffic flow indicator. The results demonstrate the potential of applying machine learning techniques for traffic flow prediction. They also suggest that our approach could be a useful tool for traffic management and transportation planning.