Paper Detail

LunarFM: A Shared Multimodal Representation of the Moon's Surface

Marc Girona-Mata, Jakob Gawlikowski, Sumit Goski, Gautier Bardi de Fourtou, Valentin T. Bickel, Ben Moseley, Abigail Calzada-Diaz, Sylvester Kaczmarek, Raúl Ramos-Pollán

arxiv Score 5.3

Published 2026-07-24 · First seen 2026-07-27

General AI

Abstract

The renewed global focus on lunar exploration, driven by the prospect of in-situ resource utilization and a sustained human presence on the Moon, has created growing demand for accurate, large-scale characterization of the lunar surface. Although vast quantities of orbital remote-sensing data have been collected, scientific analysis and resource mapping remain fragmented by heterogeneous multiinstrument observations, sparse labels, and bespoke task-specific modelling workflows. Here we introduce LunarFM, a multimodal foundation model that learns a general representation of the lunar surface from diverse orbital measurements. LunarFM assimilates observations from six instruments across three lunar missions, mapping 18 input channels to a shared embedding space. We demonstrate that this embedding space supports a diverse range of downstream applications, including similarity search, few-shot resource mapping, mineral abundance regression, and geological unit classification, enabling efficient scientific investigation and resource-oriented analysis. We provide a machine-learning-ready dataset of co-registered multimodal observations spanning latitudes from 70°S to 70°N, a pretrained multimodal masked autoencoder, and a companion embedding dataset providing a joint 768-dimensional representation of lunar surface properties. All code and data are available at https://lunarfm.trillium.tech/

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{gironamata2026lunarfm,
  title = {LunarFM: A Shared Multimodal Representation of the Moon's Surface},
  author = {Marc Girona-Mata and Jakob Gawlikowski and Sumit Goski and Gautier Bardi de Fourtou and Valentin T. Bickel and Ben Moseley and Abigail Calzada-Diaz and Sylvester Kaczmarek and Raúl Ramos-Pollán},
  year = {2026},
  abstract = {The renewed global focus on lunar exploration, driven by the prospect of in-situ resource utilization and a sustained human presence on the Moon, has created growing demand for accurate, large-scale characterization of the lunar surface. Although vast quantities of orbital remote-sensing data have been collected, scientific analysis and resource mapping remain fragmented by heterogeneous multiinstrument observations, sparse labels, and bespoke task-specific modelling workflows. Here we introduce},
  url = {https://arxiv.org/abs/2607.22408},
  keywords = {cs.LG},
  eprint = {2607.22408},
  archiveprefix = {arXiv},
}

Metadata

{}