Segmentation of lunar crater sub-geomorphology based on an improved U-Net

Impact craters are prominent lunar landforms that record impact conditions and subsequent geological modification. Semantic segmentation of their internal units, including central peaks, floors, walls, and rims, is needed for quantitative geomorphological analysis. Existing automated studies have focused mainly on crater detection or boundary extraction, whereas pixel-level mapping of crater sub-geomorphology remains limited. We developed Crater3-Net, an improved U-Net that uses a digital elevation model (DEM), slope, and plan curvature as three input channels and applies max-unpooling to recover spatial detail. On an independent test set, Crater3-Net achieved a mean intersection over union (mIoU) of 0.787 and a mean pixel accuracy (mPA) of 0.954, the highest values among the four tested configurations. We applied the trained network to lunar craters larger than 10 km and manually refined the resulting vector boundaries, producing a database of 16,412 craters and approximately 34,000 sub-geomorphological units. Within this database, the proportion of craters with mapped central peaks increased with crater diameter and broadly followed the established simple-to-complex transition. The resulting workflow supports large-scale quantitative mapping of lunar crater sub-geomorphology and provides a consistent database for constructing the Digital Moon and studying lunar surface evolution.

Authors

Institutions

Publication Details

Journal
International Journal of Digital Earth
Published
2026-11-18
DOI
https://doi.org/10.1080/17538947.2026.2763219
Primary Topic
Planetary Science and Exploration
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Segmentation of lunar crater sub-geomorphology based on an improved U-Net

Jiayin Deng, 建忠 刘, Weiming Cheng, Yimeng Jiao et al.
International Journal of Digital Earth
Planetary Science and Exploration
article

Segmentation of lunar crater sub-geomorphology based on an improved U-Net

Jiayin Deng, 建忠 刘, Weiming Cheng, Yimeng Jiao, Yutong Zhang
article en

Abstract

Impact craters are prominent lunar landforms that record impact conditions and subsequent geological modification. Semantic segmentation of their internal units, including central peaks, floors, walls, and rims, is needed for quantitative geomorphological analysis. Existing automated studies have focused mainly on crater detection or boundary extraction, whereas pixel-level mapping of crater sub-geomorphology remains limited. We developed Crater3-Net, an improved U-Net that uses a digital elevation model (DEM), slope, and plan curvature as three input channels and applies max-unpooling to recover spatial detail. On an independent test set, Crater3-Net achieved a mean intersection over union (mIoU) of 0.787 and a mean pixel accuracy (mPA) of 0.954, the highest values among the four tested configurations. We applied the trained network to lunar craters larger than 10 km and manually refined the resulting vector boundaries, producing a database of 16,412 craters and approximately 34,000 sub-geomorphological units. Within this database, the proportion of craters with mapped central peaks increased with crater diameter and broadly followed the established simple-to-complex transition. The resulting workflow supports large-scale quantitative mapping of lunar crater sub-geomorphology and provides a consistent database for constructing the Digital Moon and studying lunar surface evolution.

International Journal of Digital EarthVol. 19(2)
Henan University of Science and Technology (CN), Chinese Academy of Sciences (CN), Institute of Geochemistry (CN), Institute of Geographic Sciences and Natural Resources Research (CN), University of Chinese Academy of Sciences (CN)
National Natural Science Foundation of China, China Postdoctoral Science Foundation, Natural Science Foundation of Henan Province
Planetary Science and Exploration
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon