Network-Wide Traffic Flow Estimation Across Multiple Cities with Global Open Multi-Source Data: A Large-Scale Case Study in Europe and North America
Zijian Hu, Zhenjie Zheng, Monica Menendez, Wei Ma
TL;DR
This work tackles network-wide traffic flow estimation across multiple cities by leveraging Global Open Multi-Source (GOMS) data and map images to unify heterogeneous inputs. It introduces an attention-based graph neural network with novel Triple Cross-Attention and Dense Connection blocks to fuse GOMS maps (OSM, sensor distribution, and population density) with observed traffic data, enabling accurate cross-city NTFE. Large-scale evaluation across 15 European and North American cities demonstrates stable performance improvements over baselines and validates the importance of comprehensive GOMS data and architectural components. The results suggest that GOMS maps can address the accuracy-generalization trade-off, offering a scalable path toward universal, multi-city traffic estimation and informed urban transportation planning.
Abstract
Network-wide traffic flow, which captures dynamic traffic volume on each link of a general network, is fundamental to smart mobility applications. However, the observed traffic flow from sensors is usually limited across the entire network due to the associated high installation and maintenance costs. To address this issue, existing research uses various supplementary data sources to compensate for insufficient sensor coverage and estimate the unobserved traffic flow. Although these studies have shown promising results, the inconsistent availability and quality of supplementary data across cities make their methods typically face a trade-off challenge between accuracy and generality. In this research, we first time advocate using the Global Open Multi-Source (GOMS) data within an advanced deep learning framework to break the trade-off. The GOMS data primarily encompass geographical and demographic information, including road topology, building footprints, and population density, which can be consistently collected across cities. More importantly, these GOMS data are either causes or consequences of transportation activities, thereby creating opportunities for accurate network-wide flow estimation. Furthermore, we use map images to represent GOMS data, instead of traditional tabular formats, to capture richer and more comprehensive geographical and demographic information. To address multi-source data fusion, we develop an attention-based graph neural network that effectively extracts and synthesizes information from GOMS maps while simultaneously capturing spatiotemporal traffic dynamics from observed traffic data. A large-scale case study across 15 cities in Europe and North America was conducted. The results demonstrate stable and satisfactory estimation accuracy across these cities, which suggests that the trade-off challenge can be successfully addressed using our approach.