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

• URL: http://arxiv.org/abs/2603.16857v1
• Date: Tue, 17 Mar 2026 17:58:01 GMT
• Title: Long-Horizon Traffic Forecasting via Incident-Aware Conformal Spatio-Temporal Transformers
• Abstract summary: This study is conducted on the Ohio Department of Transportation (ODOT) traffic count data and corresponding ODOT crash records.<n>This work utilizes a Spatio-Temporal Transformer (STT) model with Adaptive Conformal Prediction (ACP) to produce multi-horizon forecasts with uncertainty.<n>Experiments demonstrate improved long-horizon accuracy and well-calibrated prediction intervals compared to other baseline methods.
• Score: 0.23453441553817037
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• A Multi-View Coupled Tensor Decomposition for Lightweight Online Adaptive Traffic Prediction [9.202409218074294]
  This paper proposes a Multi-View Coupled Decomposition (MVCTD) model for online traffic prediction from imperfect multi-view observations.<n>Experiments on real-world traffic datasets demonstrate that MVCTD achieves accurate forecasts with favorable runtime under severe missingness.
  arXiv  Detail & Related papers  (2026-08-26T08:09:00Z)
• Travel Time and Weather-Aware Traffic Forecasting in a Conformal Graph Neural Network Framework [0.30586855806896035]
  Traffic flow forecasting is essential for managing congestion, improving safety, and optimizing transportation systems.<n>Better predictions require models capable of accommodating the traffic variability influenced by multiple dynamic and complex interdependent factors.<n>We propose a Graph Neural Network (GNN) framework to address the evolvingity by leveraging adaptive adjacency.
  arXiv  Detail & Related papers  (2025-09-15T15:25:43Z)
• Learning Traffic Anomalies from Generative Models on Real-Time Observations [49.1574468325115]
  We use the Spatiotemporal Generative Adversarial Network (STGAN) framework to capture complex spatial and temporal dependencies in traffic data.<n>We apply STGAN to real-time, minute-by-minute observations from 42 traffic cameras across Gothenburg, Sweden, collected over several months in 2020.<n>Our results demonstrate that the model effectively detects traffic anomalies with high precision and low false positive rates.
  arXiv  Detail & Related papers  (2025-02-03T14:23:23Z)
• Improving Traffic Flow Predictions with SGCN-LSTM: A Hybrid Model for Spatial and Temporal Dependencies [55.2480439325792]
  This paper introduces the Signal-Enhanced Graph Convolutional Network Long Short Term Memory (SGCN-LSTM) model for predicting traffic speeds across road networks. Experiments on the PEMS-BAY road network traffic dataset demonstrate the SGCN-LSTM model's effectiveness.
  arXiv  Detail & Related papers  (2024-11-01T00:37:00Z)
• Urban Traffic Forecasting with Integrated Travel Time and Data Availability in a Conformal Graph Neural Network Framework [0.6554326244334868]
  State-of-the-art models often struggle to consider the data in the best way possible. We propose a novel framework to incorporate travel times between stations into a weighted adjacency matrix of a Graph Neural Network architecture.
  arXiv  Detail & Related papers  (2024-07-17T01:11:07Z)
• Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equations [20.174094418301245]
  Traffic flow forecasting is a fundamental research issue for transportation planning and management. In recent years, Graph Neural Networks (GNNs) and Recurrent Neural Networks (RNNs) have achieved great success in capturing spatial-temporal correlations for traffic flow forecasting. However, two non-ignorable issues haven't been well solved: 1) The message passing in GNNs is immediate, while in reality the spatial message interactions among neighboring nodes can be delayed.
  arXiv  Detail & Related papers  (2024-02-02T08:55:23Z)
• Test-Time Compensated Representation Learning for Extreme Traffic Forecasting [13.859278899032846]
  congestion and rush hours can result in low correlation in vehicle speeds at various intersections during adjacent time periods. Existing methods generally predict future series based on recent and entirely decomposed training data during the testing phase. We propose a test-time representation learning framework comprising a multi-head spatial spatial transformer model.
  arXiv  Detail & Related papers  (2023-09-16T18:46:34Z)
• Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Network [46.409567044630116]
  We propose an Asynchronous Spatio-tEmporal graph convolutional nEtwoRk (ASeer) tailored for irregular traffic time series forecasting. We first propose an Asynchronous Graph Diffusion Network to capture the spatial dependency between asynchronously measured traffic states regulated by adaptive traffic signals. Then, we propose a Transformable Time-aware Convolution Network, which adapts meta-filters for time-aware convolution on the sequences with inconsistent temporal flow.
  arXiv  Detail & Related papers  (2023-08-31T15:49:21Z)
• CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting [50.23240107430597]
  We design a special Transformer, i.e., Channel Aligned Robust Blend Transformer (CARD for short), that addresses key shortcomings of CI type Transformer in time series forecasting. First, CARD introduces a channel-aligned attention structure that allows it to capture both temporal correlations among signals. Second, in order to efficiently utilize the multi-scale knowledge, we design a token blend module to generate tokens with different resolutions. Third, we introduce a robust loss function for time series forecasting to alleviate the potential overfitting issue.
  arXiv  Detail & Related papers  (2023-05-20T05:16:31Z)
• A Graph Convolutional Network with Signal Phasing Information for Arterial Traffic Prediction [63.470149585093665]
  arterial traffic prediction plays a crucial role in the development of modern intelligent transportation systems. Many existing studies on arterial traffic prediction only consider temporal measurements of flow and occupancy from loop sensors and neglect the rich spatial relationships between upstream and downstream detectors. We fill this gap by enhancing a deep learning approach, Diffusion Convolutional Recurrent Neural Network, with spatial information generated from signal timing plans at targeted intersections.
  arXiv  Detail & Related papers  (2020-12-25T01:40:29Z)
• Spatial-Temporal Transformer Networks for Traffic Flow Forecasting [74.76852538940746]
  We propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) to improve the accuracy of long-term traffic forecasting. Specifically, we present a new variant of graph neural networks, named spatial transformer, by dynamically modeling directed spatial dependencies. The proposed model enables fast and scalable training over a long range spatial-temporal dependencies.
  arXiv  Detail & Related papers  (2020-01-09T10:21:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.