Physics-Informed Deep Recurrent Back-Projection Network for Tunnel Propagation Modeling

2026-01-05

arXiv.org

AI Summary

This study addresses the high computational cost of high-fidelity radio frequency propagation modeling in railway tunnels and the inability of coarse-grid models to preserve critical modal characteristics and geometric details. To overcome these limitations, the authors propose a physics-informed recursive back-projection network (PRBPN) that directly reconstructs high-resolution received signal strength fields from coarse-grid parabolic wave equation (PWE) slices. PRBPN uniquely integrates physics-consistency constraints into a recursive back-projection architecture, leveraging multi-slice temporal information to achieve high-fidelity, data-efficient modeling without requiring pre-upsampling. Experimental results demonstrate that PRBPN closely approximates fine-grid PWE solutions across four tunnel cross-sections and frequency bands, and its robustness under data-scarce conditions is validated using real-world measurements from the Massif Central tunnel in France.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Relational Probabilistic Models
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate and efficient modeling of radio wave propagation in railway tunnels is is critical for ensuring reliable communication-based train control (CBTC) systems. Fine-grid parabolic wave equation (PWE) solvers provide high-fidelity field predictions but are computationally expensive for large-scale tunnels, whereas coarse-grid models lose essential modal and geometric details. To address this challenge, we propose a physics-informed recurrent back-projection propagation network (PRBPN) that reconstructs fine-resolution received-signal-strength (RSS) fields from coarse PWE slices. The network integrates multi-slice temporal fusion with an iterative projection/back-projection mechanism that enforces physical consistency and avoids any pre-upsampling stage, resulting in strong data efficiency and improved generalization. Simulations across four tunnel cross-section geometries and four frequencies show that the proposed PRBPN closely tracks fine-mesh PWE references. Engineering-level validation on the Massif Central tunnel in France further confirms robustness in data-scarce scenarios, trained with only a few paired coarse/fine RSS. These results indicate that the proposed PRBPN can substantially reduce reliance on computationally intensive fine-grid solvers while maintaining high-fidelity tunnel propagation predictions.

Problem

• tunnel propagation modeling
• radio wave propagation
• parabolic wave equation
• computational efficiency
• high-fidelity prediction

Innovation

• Physics-Informed Neural Network
• Recurrent Back-Projection
• Tunnel Propagation Modeling
• Parabolic Wave Equation
• Super-Resolution