Moonatlas

Online

Craters

CRATER CANDIDATE

37.405°S 170.441°W · FARSIDE · SOUTHERN HEMISPHERE

Diameter
31.64 km
Confidence
0.95
Diameter rank
Top 0.1%

MOONATLAS derived

Large candidateHeld-out testNASA-IBM LFM · WAC crater detection

The NASA-IBM LFM crater detection model predicts a crater candidate about 31.6 km across with confidence 0.95. It is a model detection, not a reference catalog entry.

Why MOONATLAS selected this

Large candidate

Largest confident detections of the analyzed tiles. Product curation over model outputs, not a scientific ranking.

Dataset split

Held out of training and tuning, so this sample is the kind used to evaluate the model. That is evaluation provenance, not physical importance.

LROC WAC tile M1235352691CE
AI prediction · NASA-IBM LFM1.0×

M1235352691CE · 111 predicted boxes · 149 Robbins (2019) reference boxes

A model detection on one analyzed tile, not a catalogued crater and not a unique physical crater: SomBench tiles overlap, so the same crater can be detected on more than one tile.

Model outputs

CONFIDENCEAI prediction · NASA-IBM LFM
0.952
DIAMETERAI prediction · NASA-IBM LFM
31.64 km
REFERENCE MATCHMOONATLAS derived metric
Yes

Provenance

Model
NASA-IBM Lunar Foundation Model
Task
Crater detection on LROC WAC imagery
Checkpoint
WAC_ni_lfm_ps8_lora_s46.ckpt
Dataset
sombench-wac-crater-detection
Split
Held-out test
Source
M1235352691CE_r752_c240.tif
Processing
science-0.3.1
Data origin
Real model output
Scientific details
Model id
lfm-crater-detection
Model revision
f09ebeae2099
Reference
robbins-2019
Object id
wac-m1235352691ce-r752-c240#35
Catalogued
2026-09-17

Values are model output as produced, or MOONATLAS derived metrics computed from it; reference annotations are shown separately and never mixed into predictions. How MOONATLAS works.