A Machine Learning Based Search for Lunar Anomalies
2026-08-10 • Machine Learning
Machine Learning
AI summaryⓘ
The authors tested a special computer program called a Beta-Variational Autoencoder that looks at many detailed pictures of the Moon taken since 2009. This program is designed to find unusual or interesting features on the Moon’s surface without being told what to look for. The authors found that it could successfully identify natural features like craters and volcanic pits, as well as human-made objects like spacecraft. Their tests showed the program works well for spotting important spots on the Moon automatically.
Lunar Reconnaissance OrbiterBeta-Variational Autoencoderunsupervised learninganomaly detectionNarrow Angle Cameraimpact cratersIrregular Mare Patchesvolcanic pitslanded spacecraftPlaskett Crater
Authors
Cameron Kelahan, Daniel Angerhausen, Adam Lesnikowski, Valentin T. Bickel
Abstract
The Lunar Reconnaissance Orbiter (LRO) has been collecting high-resolution images (at around 0.5-2 meters per pixel linearly with its Narrow Angle Camera) of the Moon since 2009, amassing a large dataset of images and offering researchers the opportunity to study the surface of the Moon at unprecedented scale. Here, we aim to test the abilities of the Beta-Variational Autoencoder (VAE) created by Lesnikowski et al. (2024), an unsupervised learning model which identifies anomalous features across the Moon's surface, locating not only scientifically useful geologic formations such as rockfall deposits, fresh impact craters, irregular mare patches, or volcanic pits/collapsed lava tubes, but also artificial objects such as landed spacecraft. This investigation further gauged the model's ability to locate anomalous surface features, successfully recovering two places of interest (Plaskett Crater and Paracelsus C Crater) and numerous landed technological assets at a statistically significant rate.