Machine Learning Surrogates for Optimizing Transportation Policies with Agent-Based Models

TL;DR

This paper introduces Graph Neural Networks as efficient surrogates for large-scale agent-based traffic simulations, enabling faster evaluation of transportation policies with high accuracy in a Paris case study.

Contribution

It presents a novel application of GNNs to approximate agent-based models for urban traffic, reducing computational costs and improving policy analysis.

Findings

GNN accurately predicts traffic flow changes due to capacity reduction policies.

High performance on roads directly affected and with higher traffic volumes.

Effective surrogate model for large-scale urban traffic simulations.

Abstract

Rapid urbanization and growing urban populations worldwide present significant challenges for cities, including increased traffic congestion and air pollution. Effective strategies are needed to manage traffic volumes and reduce emissions. In practice, traditional traffic flow simulations are used to test those strategies. However, high computational intensity usually limits their applicability in investigating a magnitude of different scenarios to evaluate best policies. This paper presents a first approach of using Graph Neural Networks (GNN) as surrogates for large-scale agent-based simulation models. In a case study using the MATSim model of Paris, the GNN effectively learned the impacts of capacity reduction policies on citywide traffic flow. Performance analysis across various road types and scenarios revealed that the GNN could accurately capture policy-induced effects on edge-based traffic volumes, particularly on roads directly affected by the policies and those with higher traffic volumes.