Learning to Learn the Macroscopic Fundamental Diagram using Physics-Informed and meta Machine Learning techniques

2025-08-19

AI Summary

To address the challenge of macroscopic fundamental diagram (MFD) modeling under sparse traffic detector coverage, this paper proposes the first MFD modeling framework integrating meta-learning with physics-informed neural networks (PINNs). The method embeds physical constraints—such as traffic flow conservation—into a multi-task PINN and enables rapid adaptation to low-data cities via cross-city meta-training. Its key innovation lies in the first application of meta-learning to MFD modeling, thereby jointly ensuring physical interpretability and data efficiency. Experiments on representative urban road networks demonstrate that the proposed approach reduces average mean squared error (MSE) in flow prediction by 17,500–36,000 compared to baselines, significantly outperforming conventional transfer learning and nonparametric models (e.g., FitFun). These results validate the method’s strong generalization capability, cross-city transferability, and practical deployment potential.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

The Macroscopic Fundamental Diagram is a popular tool used to describe traffic dynamics in an aggregated way, with applications ranging from traffic control to incident analysis. However, estimating the MFD for a given network requires large numbers of loop detectors, which is not always available in practice. This article proposes a framework harnessing meta-learning, a subcategory of machine learning that trains models to understand and adapt to new tasks on their own, to alleviate the data scarcity challenge. The developed model is trained and tested by leveraging data from multiple cities and exploiting it to model the MFD of other cities with different shares of detectors and topological structures. The proposed meta-learning framework is applied to an ad-hoc Multi-Task Physics-Informed Neural Network, specifically designed to estimate the MFD. Results show an average MSE improvement in flow prediction ranging between ~ 17500 and 36000 (depending on the subset of loop detectors tested). The meta-learning framework thus successfully generalizes across diverse urban settings and improves performance on cities with limited data, demonstrating the potential of using meta-learning when a limited number of detectors is available. Finally, the proposed framework is validated against traditional transfer learning approaches and tested with FitFun, a non-parametric model from the literature, to prove its transferability.

Problem

• Estimating Macroscopic Fundamental Diagrams with limited loop detector data
• Generalizing traffic flow models across cities with varying detector availability
• Improving prediction accuracy using meta-learning and physics-informed neural networks

Innovation

• Meta-learning for traffic dynamics estimation
• Physics-Informed Neural Network for MFD prediction
• Cross-city generalization with limited detectors