Peering into lunar permanently shadowed regions with deep learning

Abstract

The lunar permanently shadowed regions (PSRs) are expected to host large quantities of water-ice, which are key for sustainable exploration of the Moon and beyond. In the near future, NASA and other entities plan to send rovers and humans to characterize water-ice within PSRs. However, there exists only limited information about the small-scale geomorphology and distribution of ice within PSRs because the orbital imagery captured to date lacks sufficient resolution and/or signal. In this paper, we develop and validate a new method of post-processing LRO NAC images of PSRs. We show that our method is able to reveal previously unseen geomorphological features such as boulders and craters down to 3 meters in size, whilst not finding evidence for surface frost or near-surface ice. Our post-processed images significantly facilitate the exploration of PSRs by reducing the uncertainty of target selection and traverse/mission planning.

Cryogeomorphic Characterization of Shadowed Regions in the Artemis Exploration Zone

“…The mapped umbral craters have diameters between ∼5 and ∼384 m. In the majority of PSRs the crater size frequency distribution (CSFD, available in the supplementary information) bends/rolls over at crater diameters of ∼9–∼11 m, similar to the observations made by Bickel et al. (2021) in other south polar PSRs. This likely is an artifact of the resolution and denoising performance of HORUS, not caused by a physical process.…”

“…The geologic origin of two of those features (O01b, N01a, ∼175-∼450 m long) remains unclear, although the features appear to follow the local contour lines, that is, might be caused by/related to (slow) mass wasting (e.g., creep processes). We note that the PSRs and surrounding TSRs (transiently shadowed regions) in the studied section of the Artemis exploration zone appear to host fewer lobate features than were identified in other south polar regions (Bickel et al, 2021)-an initial observation that requires further confirmation. The lobate feature in PSR M01e appears to be the surface expression of a potential lobate scarp recently identified by Bernhardt et al (2022) in the sunlit area around PSR M01e.…”

“…We note that there are PSRs of all relative ages that appear to be particularly benign to exploration, featuring entry slope angles as low as ∼1°. We did not find direct evidence for a distal origin of the mapped umbral boulders, but note that the sub‐surface bearing capacity (>∼0.75 m depth) of boulder‐bearing PSRs (boulders >∼3 m) might be reasonably high, assuming that boulders have a distal origin, for example, through mass wasting (Bickel et al., 2021). As boulders smaller than ∼3 m are not resolved by HORUS, there are no implications for depths between the surface and ∼0.75 m, as for example, estimated by Sargeant et al.…”

Review for Examining the Oxidation Process of the Moon Using Generative Adversarial Networks: Focusing on Landscape of Moon

“…Machine learning technology is being used for tasks other than just crater detection. It has been shown that surface ice can be detected by removing noise in high-resolution images in the Permanently Shadowed Regions (PSR), further revealing previously undetectable geological features of craters [74,75]. Figure 4 shows the topographic map of the lunar south pole, including the PSRs (black polygons).…”

“…Figure 4 shows the topographic map of the lunar south pole, including the PSRs (black polygons). The blue polygons are the study points [74]. While researching the Moon, the following problems were identified.…”