Physics-informed deep learning for traffic state estimation based on the traffic flow model and computational graph method

Jinlei Zhang, Shuai Mao, Lixing Yang, Wei Ma, Shukai Li, Ziyou Gao

Abstract: Highlights•We introduce the PIDL method to traffic state estimation, enabling accurate estimation results even with sparse data.•The computational graph method is applied to determine the key parameters of the fundamental diagram of traffic flow.•PIDLʹs versatility is showcased through two different traffic data scenarios: loop detectors and probe vehicles.•The research highlights the significance of integrating the physical models into the deep learning framework.