Learning traffic flows: Graph Neural Networks for Metamodelling Traffic Assignment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912379818737664 |
|---|---|
| author | Lassen, Oskar Bohn Agriesti, Serio Eldafrawi, Mohamed Gammelli, Daniele Cantelmo, Guido Gentile, Guido Pereira, Francisco Camara |
| author_facet | Lassen, Oskar Bohn Agriesti, Serio Eldafrawi, Mohamed Gammelli, Daniele Cantelmo, Guido Gentile, Guido Pereira, Francisco Camara |
| contents | The Traffic Assignment Problem is a fundamental, yet computationally expensive, task in transportation modeling, especially for large-scale networks. Traditional methods require iterative simulations to reach equilibrium, making real-time or large-scale scenario analysis challenging. In this paper, we propose a learning-based approach using Message-Passing Neural Networks as a metamodel to approximate the equilibrium flow of the Stochastic User Equilibrium assignment. Our model is designed to mimic the algorithmic structure used in conventional traffic simulators allowing it to better capture the underlying process rather than just the data. We benchmark it against other conventional deep learning techniques and evaluate the model's robustness by testing its ability to predict traffic flows on input data outside the domain on which it was trained. This approach offers a promising solution for accelerating out-of-distribution scenario assessments, reducing computational costs in large-scale transportation planning, and enabling real-time decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11230 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning traffic flows: Graph Neural Networks for Metamodelling Traffic Assignment Lassen, Oskar Bohn Agriesti, Serio Eldafrawi, Mohamed Gammelli, Daniele Cantelmo, Guido Gentile, Guido Pereira, Francisco Camara Machine Learning The Traffic Assignment Problem is a fundamental, yet computationally expensive, task in transportation modeling, especially for large-scale networks. Traditional methods require iterative simulations to reach equilibrium, making real-time or large-scale scenario analysis challenging. In this paper, we propose a learning-based approach using Message-Passing Neural Networks as a metamodel to approximate the equilibrium flow of the Stochastic User Equilibrium assignment. Our model is designed to mimic the algorithmic structure used in conventional traffic simulators allowing it to better capture the underlying process rather than just the data. We benchmark it against other conventional deep learning techniques and evaluate the model's robustness by testing its ability to predict traffic flows on input data outside the domain on which it was trained. This approach offers a promising solution for accelerating out-of-distribution scenario assessments, reducing computational costs in large-scale transportation planning, and enabling real-time decision-making. |
| title | Learning traffic flows: Graph Neural Networks for Metamodelling Traffic Assignment |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.11230 |