Global mapping of fragmented rocks on the Moon with a neural network: Implications for the failure mode of rocks on airless surfaces
It has been recently recognized that the surface of sub-km asteroids in contact with the space environment is not fine-grained regolith but consists of centimeter to meter-scale rocks. Here we aim to understand how the rocky morphology of minor bodies react to the well known space erosion agents on the Moon. We deploy a neural network and map a total of ~130,000 fragmented boulders scattered across the lunar surface and visually identify a dozen different desintegration morphologies corresponding to different failure modes. We find that several fragmented boulder morphologies are equivalent to morphologies observed on asteroid Bennu, suggesting that these morphologies on the Moon and on asteroids are likely not diagnostic of their formation mechanism. Our findings suggest that the boulder fragmentation process is characterized by an internal weakening period with limited morphological signs of damage at rock scale until a sudden highly efficient impact shattering event occurs. In addition, we identify new morphologies such as breccia boulders with an advection-like erosion style. We publicly release the produced fractured boulder catalog along with this paper.
Code (0)
등록된 구현이 없습니다.
Tasks
DiagnosticSimilar Papers 제목 키워드 기반
Using MRNet to Predict Lunar Rock Categories Detected by Chang'e 5 Probe
China's Chang'e 5 mission has been a remarkable success, with the chang'e 5 lander traveling on the Oceanus Procellarum to collect images of the lunar surface. Over the past half century, people have brought back some lu…
Breccia and basalt classification of thin sections of Apollo rocks with deep learning
Human exploration of the moon is expected to resume in the next decade, following the last such activities in the Apollo programme time. One of the major objectives of returning to the Moon is to continue retrieving geol…
Contrastive LearningTransfer LearningMoonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing
Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, radar, gravity, and elemental composition. Yet these datasets remain fragm…
POLAR-Sim: Augmenting NASA's POLAR Dataset for Data-Driven Lunar Perception and Rover Simulation
NASA's POLAR dataset contains approximately 2,600 pairs of high dynamic range stereo photos captured across 13 varied terrain scenarios, including areas with sparse or dense rock distributions, craters, and rocks of diff…
Autonomous NavigationSemantic SegmentationTask 2Insights into Lunar Mineralogy: An Unsupervised Approach for Clustering of the Moon Mineral Mapper (M3) spectral data
This paper presents a novel method for mapping spectral features of the Moon using machine learning-based clustering of hyperspectral data from the Moon Mineral Mapper (M3) imaging spectrometer. The method uses a convolu…