PuSH - Publikationsserver des Helmholtz Zentrums München

Natterer, E.S.* ; Rao, S.R.* ; Tejada Lapuerta, A. ; Engelhardt, R.* ; Horl, S.* ; Bogenberger, K.*

Machine learning surrogates for agent-based models in transportation policy analysis.

Transp. Res. Pt. C-Emerg. Technol. 180:105360 (2025)
Verlagsversion DOI
Open Access Hybrid
Creative Commons Lizenzvertrag
Effective traffic policies are crucial for managing congestion and reducing emissions. Agent-based transportation models (ABMs) offer a detailed analysis of how these policies affect travel behaviour at a granular level. However, computational constraints limit the number of scenarios that can be tested with ABMs and therefore their ability to find optimal policy settings. In this proof-of-concept study, we propose a machine learning (ML)-based surrogate model to efficiently explore this vast solution space. By combining Graph Neural Networks (GNNs) with the attention mechanism from Transformers, the model predicts the effects of traffic policies on the road network at the link level. We implement our approach in a large-scale MATSim simulation of Paris, France, covering over 30,000 road segments and 10,000 simulations, applying a policy involving capacity reduction on main roads. The ML surrogate achieves an overall R2 of 0.91; on primary roads where the policy applies, it reaches an R2 of 0.98. This study shows that the combination of GNNs and Transformer architectures can effectively serve as a surrogate for complex agent-based transportation models with the potential to enable large-scale policy optimization, helping urban planners explore a broader range of interventions more efficiently.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Graph neural networks; Transformers; Agent-based simulations; Optimization-based transportation policies; Surrogate models; Street capacity reduction; Simulation; Implementation; Management; Framework
ISSN (print) / ISBN 0968-090X
e-ISSN 1879-2359
Zeitschrift Transportation Research Part C: Emerging Technologies
Quellenangaben Band: 180, Heft: , Seiten: , Artikelnummer: 105360 Supplement: ,
Verlag Elsevier
Verlagsort The Boulevard, Langford Lane, Kidlington, Oxford Ox5 1gb, England
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Computational Biology (ICB)