HORUS: Peering into Lunar Shadowed Regions with AI

Valentin Bickel*, Ben Moseley** and Ignacio Lopez-Francos***

*ETH Zurich, **University of Oxford and ***NASA Ames Research Center

HORUS (Hyper-effective nOise Removal U-net Software) is a cutting-edge AI tool designed to enhance Lunar Reconnaissance Orbiter (LRO) optical low-light imagery of the Moon's shadowed regions by removing most of the CCD-related and photon noise. For the first time, HORUS enables scientists and engineers to identify intra-shadow geologic features (craters, boulders, etc.) as small as 3 meters across, making this tool uniquely useful for applications such as geologic mapping, landing site selection, hazard recognition, and mission planning, directly supporting the robotic and crewed exploration of the Moon's south pole.