A Global Sub-Kilometer Crater Catalogue of Ceres Derived via Zero-Shot Deep Learning

Overview: Crater size-frequency distributions (CSFDs) on Ceres provide a valuable record of the size-frequency distribution and transport history of Main-Belt projectiles, but crater analysis below kilometer scale has been limited by the impracticality of manual crater mapping. Here we present a new global crater catalogue for Ceres generated with a deep-learning crater detector applied to the Dawn's low altitude mapping orbit images and topographic data in a strict zero-shot setting. The resulting catalogue contains 7,692,427 craters with diameters larger than ~250 m. Validation against a previous manual catalogue shows that our automatic crater counts in equatorial regions are in good agreement with the manual catalogue, with only a ~10% difference. This data are part of a submitted paper entitled "Sub-kilometer-scale Cratering History on Ceres Revealed by an AI-based Crater Detection", under submission on Icarus journal, after acceptance we upload the full reference. If you use the dataset, take into account the previous works: La Grassa, Riccardo, et al. "YOLOLens: A deep learning model based on super-resolution to enhance the crater detection of the planetary surfaces." Remote Sensing 15.5 (2023): 1171, https://doi.org/10.3390/rs15051171. La Grassa, R, et al. "LU5M812TGT: An AI-Powered global database of impact craters ≥0.4 km on the Moon", ISPRS Journal of Photogrammetry and Remote Sensing, 2025, ISSN 0924-2716, https://doi.org/10.1016/j.isprsjprs.2024.11.010. La Grassa, Riccardo, et al. "From the Moon to Mercury: Release of Global Crater Catalogs Using Multimodal Deep Learning for Crater Detection and Morphometric Analysis" Remote Sensing 17.19 (2025): 3287. NEW: We have released a plugin available on the official repositor of QGIS, please check also the documentation and pretrained models -> https://github.com/riccardolagrassa/YOLOLens_QGIS_Plugin