Generalising Travel Time Prediction To Varying Route Choices In Urban Networks

TL;DR

This paper introduces GenTTP, a travel time prediction model that captures varying route choices and generalizes across different demand scenarios in urban networks.

Contribution

It presents a novel framework that differentiates route choices and predicts travel times under varying demand and route distributions.

Findings

Successfully differentiates route choices in travel time prediction

Learns complex spatiotemporal traffic patterns

Generalizes across varying demand and route assignments

Abstract

Previous methods that predict system-wide travel time, predominantly grounded in graph neural networks, remain limited to typical and recurring demand patterns. While they successfully predict future congestion following daily commute, they inherently approximate a single demand realisation and fail to capture varying route choices. In this work, we propose a Generalised Travel Time Predictor (GenTTP) that successfully differentiates route choices and offers accurate flow and travel time predictions. Our framework learns to uncover complex spatiotemporal traffic patterns and microscopic relationships between route choices and the resulting travel times. This addresses a critical gap: the lack of travel time prediction models that generalise across varying route assignments, where the same demand can produce substantially different network-wide outcomes depending on how travellers are distributed over available paths.