Graph method improves citywide daily traffic estimation accuracy
Spatio-temporally complementary feature propagation on graphs for longitudinal AADT estimation
Machine Learning
Summary
Estimating how busy city roads are every day is important but hard due to limited traffic sensors. The authors created a new method that combines two data types: traffic sensor data that is detailed over time but sparse across locations, and a traffic model that covers all roads but only at certain times. They use a special graph-based technique that considers how vehicles turn at intersections to better fill in missing data. Tested in Zurich, this method quickly produces accurate daily traffic estimates across the road network with less than 10% error.
What this means in practice
- •For urban transportation planners: Estimate daily traffic volumes across city road networks more accurately using limited sensor and model data combined by the new graph method.
- •For traffic management teams: Use a fast, scalable computation to fill gaps in traffic sensor coverage for better real-time or historical traffic analysis.
Tested on one dataset.
Authors
Linghang Sun, Qishen Zhou, Michail A. Makridis, Anastasios Kouvelas
Abstract
The estimation of Annual Average Daily Traffic (AADT) is vital for transportation planning and infrastructure maintenance, yet obtaining accurate values for an entire urban network across multiple years remains challenging due to the high cost and spatial sparsity of physical sensors. This research proposes a novel spatio-temporally complementary feature propagation framework that leverages the strengths of two distinct data sources: spatially sparse but temporally dense loop detector data, and a spatially complete but temporally sparse macroscopic transportation model. The methodology highlights a feature propagation algorithm on directed graphs, formulated as a Poisson energy minimization considering residues. The standard binary adjacency matrix is replaced with flow ratio matrices to capture real-world vehicle turn ratios at intersections. Validated in the city of Zurich, the algorithm demonstrates high computational efficiency, achieving convergence within minutes. Results indicate that the framework effectively reconciles theoretical models with empirical ground truths, yielding a normalized mean absolute error below $10\%$. This scalable approach provides a feasible solution for spatio-temporal network-wide AADT estimation through combining real-world limited sensor coverage and traffic models.