Day-to-day dynamic origin-destination flow estimation using connected vehicle trajectories and automatic vehicle identification data

Dynamic vehicular origin-destination (OD) flow is a fundamental component of traffic network modeling and its estimation has long been studied. Although ideal observing conditions and behavioral assumptions are often indispensable for estimation, day-to-day traffic recurrences and variations are seldom utilized to improve the estimation performance. In this paper, we propose a new method to recover day-to-day dynamic OD flows using both connected vehicle (CV) trajectories and automatic vehicle identification (AVI) observations. The method involves two modules: the first module provides reliable prior OD flows given limited observations, while the second module seeks the optimal estimates based on the prior OD flows. In the first module, linear projection is extended to consider temporal and spatial variation of the CV penetration rate, and non-negative Tucker decomposition (NTD) is adopted to address the data sparsity issue caused by the low CV penetration rate. In the second module, a self-supervised learning model called the latency-constrained autoencoder (LCAE) is established to search for the optimal OD flows according to the priors with given robust latent features. To avoid local minima and ensure consistency between estimates, a novel algorithm called adaptive sub-sample correction (ASC) is proposed and integrated into the optimization process of LCAE, which can iteratively correct the most inconsistent samples based on the day-to-day traffic flow characteristics. The proposed method is examined on an empirical urban arterial network, a calibrated simulation network, and a synthetic large-scale grid network. Our results indicated that the proposed method requires very few AVI detectors and CV trajectories to achieve competitive estimation performance against two benchmark models. Furthermore, general robustness to several factors with respect to observing conditions and data quality was investigated, and satisfactory scalability was also demonstrated in terms of both estimation accuracy and computational cost.