In this paper, we propose a novel physics-informed deep learning architecture for predicting radio maps over lunar terrain. Our approach integrates a physics-based lunar terrain generator, which produces realistic topography informed by publicly available NASA data, with a ray-tracing engine to create a high-fidelity dataset of radio propagation scenarios. Building on this dataset, we introduce a triplet-UNet architecture, consisting of two standard UNets and a diffusion network, to model complex propagation effects. Experimental results demonstrate that our method outperforms existing deep learning approaches on our terrain dataset across various metrics.
@article{arxiv.2509.14559,
title = {Radiolunadiff: Estimation of wireless network signal strength in lunar terrain},
author = {Paolo Torrado and Anders Pearson and Jason Klein and Alexander Moscibroda and Joshua Smith},
journal= {arXiv preprint arXiv:2509.14559},
year = {2025}
}