A Pretrained Probabilistic Transformer for City-Scale Traffic Volume Prediction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shen, Shiyu, Pan, Bin, Xue, Guirong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912411298037760
author Shen, Shiyu
Pan, Bin
Xue, Guirong
author_facet Shen, Shiyu
Pan, Bin
Xue, Guirong
contents City-scale traffic volume prediction plays a pivotal role in intelligent transportation systems, yet remains a challenge due to the inherent incompleteness and bias in observational data. Although deep learning-based methods have shown considerable promise, most existing approaches produce deterministic point estimates, thereby neglecting the uncertainty arising from unobserved traffic flows. Furthermore, current models are typically trained in a city-specific manner, which hinders their generalizability and limits scalability across diverse urban contexts. To overcome these limitations, we introduce TrafficPPT, a Pretrained Probabilistic Transformer designed to model traffic volume as a distributional aggregation of trajectories. Our framework fuses heterogeneous data sources-including real-time observations, historical trajectory data, and road network topology-enabling robust and uncertainty-aware traffic inference. TrafficPPT is initially pretrained on large-scale simulated data spanning multiple urban scenarios, and later fine-tuned on target cities to ensure effective domain adaptation. Experiments on real-world datasets show that TrafficPPT consistently surpasses state-of-the-art baselines, particularly under conditions of extreme data sparsity. Code will be open.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02654
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Pretrained Probabilistic Transformer for City-Scale Traffic Volume Prediction
Shen, Shiyu
Pan, Bin
Xue, Guirong
Machine Learning
Artificial Intelligence
City-scale traffic volume prediction plays a pivotal role in intelligent transportation systems, yet remains a challenge due to the inherent incompleteness and bias in observational data. Although deep learning-based methods have shown considerable promise, most existing approaches produce deterministic point estimates, thereby neglecting the uncertainty arising from unobserved traffic flows. Furthermore, current models are typically trained in a city-specific manner, which hinders their generalizability and limits scalability across diverse urban contexts. To overcome these limitations, we introduce TrafficPPT, a Pretrained Probabilistic Transformer designed to model traffic volume as a distributional aggregation of trajectories. Our framework fuses heterogeneous data sources-including real-time observations, historical trajectory data, and road network topology-enabling robust and uncertainty-aware traffic inference. TrafficPPT is initially pretrained on large-scale simulated data spanning multiple urban scenarios, and later fine-tuned on target cities to ensure effective domain adaptation. Experiments on real-world datasets show that TrafficPPT consistently surpasses state-of-the-art baselines, particularly under conditions of extreme data sparsity. Code will be open.
title A Pretrained Probabilistic Transformer for City-Scale Traffic Volume Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.02654