ICASSP 2027 GC

The Lunar Radio Map Dataset

The dataset will be made publicly available soon. The download links, the challenge documentation and the baseline code will be posted here — please check back, or register to be notified.

Dataset download: link coming soon.
Challenge documentation and detailed instructions: coming soon.
Baseline code (RadioUNet) with data loaders, training and inference: coming soon.

The dataset includes diverse lunar radio maps generated over synthetic topographic models. Initially, we will provide a dataset that participants will use to develop their data-driven models, later releasing the test dataset (without the ground truth) to select the top-performing teams.

The challenge dataset comprises 66,000 PL radio maps generated over synthetic lunar terrains using Sionna-RT. Due to the limited amount of high-resolution lunar Digital Terrain Models (DTMs), we utilized a procedural pipeline to synthesize 256 × 256 meter landscapes at 1 m/px resolution. These were statistically validated against actual lunar DTMs to ensure realistic crater distributions and surface ages. Electromagnetic properties of lunar regolith were applied to ensure accurate propagation modeling across two frequency bands (415 MHz and 5.775 GHz, hereafter referred to as 5.8 GHz). The dataset is split 85/15 into a provided training dataset and a withheld testing dataset for evaluation, structured as follows:

Simulation Details

Simulations modeled line-of-sight paths, specular reflection, diffuse (Lambertian) scattering, and refraction. Diffraction was explicitly disabled due to the exponential computational complexity of applying models like UTD to continuous, high-resolution terrain micro-edges. To mitigate ray-tracing null pixels, we applied Monte Carlo averaging. Remaining gaps were resolved using bilinear interpolation (415 MHz) or a static fill (5.8 GHz). For all simulations, the TX height is set at 3 m above the local terrain contour. The RX is measured as an isotropic probe sampled on a mesh surface exactly 1 m above the terrain contour, which is then linearly interpolated onto a regular 256 × 256 grid. We trace the ray path up to a maximum depth of 100 interactions, simulating 4 × 10⁹ rays per transmitter. The TX parameters were set as a single isotropic antenna element with vertical polarization.

Specifically, the dataset includes:

• The target PL RMs saved as .npy files. Each image pixel value represents the positive pathloss of the wireless signal, measured in dB, at the corresponding lunar geometry location.
• Each PL RM is associated with input physical features, including a continuous height map image representing the topological elevation of the lunar terrain and a one-hot encoded spatial map indicating the exact coordinate location of the transmitter, both also saved as .npy files.

Guidelines for Participants

1. Download the presented dataset and the provided example code, e.g., the data loaders and modules of the presented baseline methods.
2. Develop data-driven PL inference methods using the presented dataset. The participants can make use of the input images to extract additional features. The authors are encouraged to use data augmentation techniques, and a default augmentation pipeline will be provided with the dataset.
3. The participating teams submit their radio map estimates along with their trained models and the test code that runs the evaluation of the model on the test set. Participants have the flexibility to submit either a single unified model that predicts both frequency bands (e.g., using a boolean image flag as a condition, as demonstrated in RadioLunaDiff) or two distinct models trained separately for the 415 MHz and 5.8 GHz tasks.

References

[1] J. Hoydis, S. Cammerer, F. Ait Aoudia, M. Nimier-David, L. Maggi, G. Marcus, A. Vem, and A. Keller, “Sionna,” 2022.

[2] P. Torrado, A. Pearson, J. Klein, A. Moscibroda, and J. Smith, “RadioLunaDiff: Estimation of wireless network signal strength in lunar terrain,” in ICASSP 2026 — 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026, pp. 21231–21235.

[3] R. Levie, Ç. Yapar, G. Kutyniok, and G. Caire, “RadioUNet: Fast radio map estimation with convolutional neural networks,” IEEE Transactions on Wireless Communications, vol. 20, no. 6, pp. 4001–4015, 2021.