🤖 AI Summary
This study addresses the challenge of automatically detecting scientific or anthropogenic anomalous features in vast collections of high-resolution lunar imagery. It proposes an unsupervised anomaly detection method by introducing Beta-variational autoencoders (Beta-VAE) to large-scale lunar remote sensing data—a first in this domain. The approach requires no labeled training data and simultaneously identifies both natural geological anomalies and artificial objects. Applied to Lunar Reconnaissance Orbiter (LRO) images acquired since 2009, the model successfully locates scientifically significant craters such as Plaskett and Paracelsus C and accurately pinpoints multiple known lander sites with statistical significance. These results demonstrate the method’s effectiveness and generalization capability for anomaly detection in planetary remote sensing.
📝 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.