Long-Horizon Traffic Forecasting via Incident-Aware Conformal Spatio-Temporal Transformers

TL;DR

This paper introduces an incident-aware spatio-temporal transformer model with adaptive conformal prediction for accurate, calibrated long-horizon traffic forecasting that accounts for stochastic network conditions and localized disruptions.

Contribution

It proposes a novel dynamic graph construction method using incident severity signals and a CV strategy for modeling travel time variability, enhancing long-term traffic prediction accuracy.

Findings

Improved long-horizon forecast accuracy over baselines.

Calibrated prediction intervals achieved.

Dynamic graph modeling captures localized disruptions.

Abstract

Reliable multi-horizon traffic forecasting is challenging because network conditions are stochastic, incident disruptions are intermittent, and effective spatial dependencies vary across time-of-day patterns. This study is conducted on the Ohio Department of Transportation (ODOT) traffic count data and corresponding ODOT crash records. This work utilizes a Spatio-Temporal Transformer (STT) model with Adaptive Conformal Prediction (ACP) to produce multi-horizon forecasts with calibrated uncertainty. We propose a piecewise Coefficient of Variation (CV) strategy that models hour-to-hour traveltime variability using a log-normal distribution, enabling the construction of a per-hour dynamic adjacency matrix. We further perturb edge weights using incident-related severity signals derived from the ODOT crash dataset that comprises incident clearance time, weather conditions, speed violations, work zones, and roadway functional class, to capture localized disruptions and peak/off-peak transitions. This dynamic graph construction replaces a fixed-CV assumption and better represents changing traffic conditions within the forecast window. For validation, we generate extended trips via multi-hour loop runs on the Columbus, Ohio, network in SUMO simulations and apply a Monte Carlo simulation to obtain travel-time distributions for a Vehicle Under Test (VUT). Experiments demonstrate improved long-horizon accuracy and well-calibrated prediction intervals compared to other baseline methods.