Traffic state estimation is relevant for real-time traffic control, providing travel information as well as for expost analysis of traffic patterns. While the output is usually the average speed and vehicle flow along street segments, the type of input data and the existing methods to obtain the output are diverse. Recently, physics-informed data-driven approaches started to emerge that enrich the estimation process with information taken from physical models. In traffic, so far, these have been the continuity equation and the fundamental diagram, designed to describe fully the traffic dynamics along links and corridors. In this paper, we propose a simpler and practice-ready physics-informed machine learning approach that informs the estimation through the well-established fundamental diagram in a loss constraint. It is designed for a link-level analysis where traffic homogeneity along the considered link is assumed. We apply the proposed method to full-trajectory drone data from Athens, Greece, demonstrate the applicability of our proposed approach, and point out its potential to future applications, e.g., a filter for control algorithms.     «

Traffic state estimation is relevant for real-time traffic control, providing travel information as well as for expost analysis of traffic patterns. While the output is usually the average speed and vehicle flow along street segments, the type of input data and the existing methods to obtain the output are diverse. Recently, physics-informed data-driven approaches started to emerge that enrich the estimation process with information taken from physical models. In traffic, so far, these have bee...     »