Physics-informed Machine Learning for Calibrating Macroscopic Traffic Flow Models
This addresses the need for accurate traffic model calibration for traffic management, though it is incremental as it builds on existing autoencoder and physics-informed methods.
The paper tackles the problem of calibrating macroscopic traffic flow models by proposing a physics-informed machine learning approach that combines deep autoencoders with traffic flow models, achieving performance comparable to or better than traditional optimization-based methods, as verified in a case study on I-210 E in California.
Well-calibrated traffic flow models are fundamental to understanding traffic phenomena and designing control strategies. Traditional calibration has been developed base 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 of optimization-based methods. To this end, we combine the classical deep autoencoder, an unsupervised machine learning model consisting of one encoder and one decoder, with traffic flow models. Our approach informs the decoder of the physical traffic flow models and thus induces the encoder to yield reasonable traffic parameters given flow and speed measurements. We also introduce the denoising autoencoder into our method so that it can handles not only with normal data but also with corrupted data with missing values. We verified our approach with a case study of I-210 E in California.