Network-Wide Traffic Volume Estimation from Speed Profiles using a Spatio-Temporal Graph Neural Network with Directed Spatial Attention

TL;DR

This paper introduces HDA-STGNN, a deep learning model that estimates traffic volumes across entire urban networks using speed profiles and static road data, overcoming limitations of sensor-based methods.

Contribution

The work presents a novel spatio-temporal graph neural network that estimates network-wide traffic volumes solely from probe speeds and static attributes, without requiring volume data at inference.

Findings

Model effectively captures complex spatio-temporal dependencies.

Topological information significantly improves estimation accuracy.

Approach enables network-wide traffic volume estimation in sensor-scarce cities.

Abstract

Existing traffic volume estimation methods typically address either forecasting traffic on sensor-equipped roads or spatially imputing missing volumes using nearby sensors. While forecasting models generally disregard unmonitored roads by design, spatial imputation methods explicitly address network-wide estimation; yet this approach relies on volume data at inference time, limiting its applicability in sensor-scarce cities. Unlike traffic volume data, probe vehicle speeds and static road attributes are more broadly accessible and support full coverage of road segments in most urban networks. In this work, we present the Hybrid Directed-Attention Spatio-Temporal Graph Neural Network (HDA-STGNN), an inductive deep learning framework designed to tackle the network-wide volume estimation problem. Our approach leverages speed profiles, static road attributes, and road network topology to predict daily traffic volume profiles across all road segments in the network. To evaluate the effectiveness of our approach, we perform extensive ablation studies that demonstrate the model's capacity to capture complex spatio-temporal dependencies and highlight the value of topological information for accurate network-wide traffic volume estimation without relying on volume data at inference time.