Inverting the fundamental diagram and forecasting boundary conditions: how machine learning can improve macroscopic models for traffic flow

• Published in: Advances in computational mathematics Vol. 50; no. 6
• Main Authors: Briani, Maya, Cristiani, Emiliano, Onofri, Elia
• Format: Journal Article
• Language: English
• Published: New York Springer Nature B.V 01.12.2024
• Subjects: Boundary conditions; Density; Machine learning; Machinery condition monitoring; Macroscopic models; Neural networks; Roads & highways; Sensors; Traffic congestion; Traffic flow; Traffic models; Vehicles

In this paper, we develop new methods to join machine learning techniques and macroscopic differential models, aimed at estimate and forecast vehicular traffic. This is done to complement respective advantages of data-driven and model-driven approaches. We consider here a dataset with flux and veloc...