Traffic condition forecasting is fundamental for Intelligent Transportation Systems. Besides accuracy, many services require an estimate of uncertainty for each prediction. Uncertainty quantification must consider the inherent randomness in traffic dynamics, the so-called aleatoric uncertainty, and the additional distrust caused by data shortage, the so-called epistemic uncertainty. They together depict how predictable macroscopic traffic is. This study uses deep ensembles of graph neural networks to estimate both types of uncertainty in network-level speed forecasting. Experimental results given by the used model reveal that, although rare congestion patterns arise randomly, the short-term predictability of traffic states is mainly restricted by the irreducible stochasticity in traffic dynamics. The predicted future state bifurcates into congested or free-flowing cases. This study suggests that the potential for improving prediction models through expanding speed and flow data is limited while diversifying data types is crucial.
How predictable are macroscopic traffic states: a perspective of uncertainty quantification
TRANSPORTMETRICA B
G. Li et al.
2024-12-31
24 pages
Article (Journal)
Electronic Resource
English
5G E2E Network Slicing Predictable Traffic Generator
IEEE | 2023
|Predictable and Delay Tolerant Traffic Management System
European Patent Office | 2022
|Predictable and delay tolerant traffic management system
European Patent Office | 2023
|PREDICTABLE UNCERTAINTY ABOUT TERMINAL OPERATIONS IN THE SEA
British Library Online Contents | 2010
|