Lightning Talk 1: Physics-Informed Machine Learning for Calibrating Macroscopic Traffic Flow Models
Title: Physics-Informed Machine Learning for Calibrating Macroscopic Traffic Flow Models
Authors: Yu Tang, Li Jin, Kaan Ozbay
Abstract: Well-calibrated traffic flow models are fundamental to understanding traffic phenomena and designing control strategies. Traditional calibration has been developed based on optimization methods. In this paper, we propose a novel physics-informed, learning-based calibration approach that achieves performances comparable to and even better than those...
Keywords: Physics-informed learning; Parameter identification; Traffic flow models
