Physics-Informed Teacher-Student Ensemble Learning for Traffic State Estimation with a Varying Speed Limit Scenario

2026-05-11

AI Summary

This study addresses the challenge of effectively capturing the dynamic heterogeneity of traffic under variable speed limit (VSL) scenarios, which existing physics-informed deep learning methods struggle to model accurately. To overcome this limitation, the authors propose a novel framework that integrates a teacher–student ensemble with physics-informed learning. In this approach, teacher models embed physical constraints derived from traffic flow conservation laws locally, while a student model—implemented as a multilayer perceptron—identifies traffic states and adaptively selects the optimal teacher for state estimation. This work represents the first integration of a teacher–student mechanism into physics-informed learning, significantly enhancing the robustness and accuracy of traffic state estimation under VSL control. Experimental results demonstrate that the proposed method achieves substantially lower relative L2 error compared to mainstream baselines, confirming its effectiveness.

Abstract

Physics-informed deep learning (PIDL) neural networks have shown their capability as a useful instrument for transportation practitioners in utilizing the underlying relationship between the state variables for traffic state estimation (TSE). Another efficient traffic management approach is implementing varying speed limits (VSLs) on transportation corridors to control traffic and mitigate congestion. However, the existing training architecture of PIDL in the literature cannot accommodate the changing traffic characteristics on a freeway with VSL. To tackle this challenge, we propose a novel framework integrating teacher-student ensemble training with PIDL neural networks for TSE under VSL scenarios. The physics of flow conservation law is encoded locally in the teacher models by PIDL, and the student model uses a multi-layer perceptron classifier (MLP) to identify traffic characteristics and selects the ensemble member of PIDL neural networks for TSE. This integrated framework provides a natural solution for capturing the heterogeneity of VSL and accurately addressing the TSE problem. The case study results validate the proposed ensemble approach, demonstrating its superior performance in TSE compared to other popular baseline methods, as indicated by relative L2 error.

Problem

• traffic state estimation
• varying speed limits
• physics-informed deep learning
• traffic heterogeneity

Innovation

• Physics-Informed Deep Learning
• Teacher-Student Ensemble
• Traffic State Estimation
• Variable Speed Limits
• Flow Conservation Law