RadioDUN: A Physics-Inspired Deep Unfolding Network for Radio Map Estimation

2025-06-10

AI Summary

Constructing dense radio maps from sparse measurements remains challenging due to insufficient observations and difficulty in incorporating domain-specific physical priors—particularly shadowing effects induced by obstacles. Method: We formulate this task as a physics-constrained sparse signal recovery problem and propose a learnable optimization framework based on deep unfolding networks (DUNs). Our approach introduces a novel Dynamic Reweighting Module (DRM) to explicitly model obstacle-induced shadow fading, incorporates a shadow-aware loss function that embeds propagation physics (e.g., path loss and shadowing) as auxiliary supervision within the unfolding iterations, and jointly leverages compressed sensing priors and wireless channel physics for end-to-end adaptive parameter learning. Results: Extensive experiments on multiple real-world datasets demonstrate significant improvements over state-of-the-art methods in interpolation accuracy and cross-scenario generalization. The code will be made publicly available.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The radio map represents the spatial distribution of spectrum resources within a region, supporting efficient resource allocation and interference mitigation. However, it is difficult to construct a dense radio map as a limited number of samples can be measured in practical scenarios. While existing works have used deep learning to estimate dense radio maps from sparse samples, they are hard to integrate with the physical characteristics of the radio map. To address this challenge, we cast radio map estimation as the sparse signal recovery problem. A physical propagation model is further incorporated to decompose the problem into multiple factor optimization sub-problems, thereby reducing recovery complexity. Inspired by the existing compressive sensing methods, we propose the Radio Deep Unfolding Network (RadioDUN) to unfold the optimization process, achieving adaptive parameter adjusting and prior fitting in a learnable manner. To account for the radio propagation characteristics, we develop a dynamic reweighting module (DRM) to adaptively model the importance of each factor for the radio map. Inspired by the shadowing factor in the physical propagation model, we integrate obstacle-related factors to express the obstacle-induced signal stochastic decay. The shadowing loss is further designed to constrain the factor prediction and act as a supplementary supervised objective, which enhances the performance of RadioDUN. Extensive experiments have been conducted to demonstrate that the proposed method outperforms the state-of-the-art methods. Our code will be made publicly available upon publication.

Problem

• Estimating dense radio maps from sparse samples
• Integrating physical characteristics into radio map estimation
• Reducing recovery complexity via factor optimization decomposition

Innovation

• Physics-inspired deep unfolding network for radio map
• Dynamic reweighting module adaptively models factor importance
• Shadowing loss enhances obstacle-related signal decay prediction