elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Accessibility | Contact | Deutsch
Fontsize: [-] Text [+]

Semantic segmentation of light-toned veins in multimodal ChemCam data

Lomashvili, Ana and Rammelkamp, Kristin and Bhattacharjee, Protim and Gasnault, Olivier and Clave, Elise and Egerland, Christoph H. and Schröder, Susanne and Gabriel, Travis S. J. and Essunfeld, Ari and Le Mouelic, Stephane and Demir, Begüm (2026) Semantic segmentation of light-toned veins in multimodal ChemCam data. Scientific Reports, 16 (1). Nature Publishing Group. doi: 10.1038/s41598-026-47207-0. ISSN 2045-2322.

[img] PDF - Published version
4MB

Official URL: https://www.nature.com/articles/s41598-026-47207-0

Abstract

Since the Mars Science Laboratory landed in 2012, the ChemCam instrument aboard the rover has collected in-situ laser-induced breakdown spectroscopy (LIBS) data and context images along more than 35 km of the Gale Crater traverse, providing valuable observations including diagenetic features such as light-toned veins. These veins are of particular scientific interest because they are interpreted as indicators of past fluid circulation on Mars and provide insights into the evolution of habitability on Mars. Their identification, however, currently relies on manual visual inspection of Remote Micro Imager (RMI) images, a process that is time-consuming and sensitive to differences in human interpretation. To address this issue, in this paper we introduce a novel pixel-level labeled, multimodal dataset of ChemCam observations specifically tailored for vein detection, along with customized U-Net models to integrate both textural (RMI) and chemical (LIBS) modalities. To further ensure trustworthy scientific use, we incorporate the Learn-Then-Test (LTT) framework to provide statistical control of the false discovery rate without requiring model retraining. The experimental results demonstrate that the proposed customized U-Net models trained on the developed dataset, combined with risk-controlled prediction, increases the efficiency of pixel-level vein identification through automation and produces statistically reliable predictions for multimodal ChemCam data.

Item URL in elib:https://elib.dlr.de/223924/
Document Type:Article
Title:Semantic segmentation of light-toned veins in multimodal ChemCam data
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Lomashvili, AnaGerman Aerospace Center (DLR), Institute of Space Research, Berlin, Germany; BIFOLD and TU Berlin, Berlin, Germanyhttps://orcid.org/0009-0005-3157-3316217375990
Rammelkamp, KristinKristin.Rammelkamp (at) dlr.dehttps://orcid.org/0000-0003-4808-0823217375992
Bhattacharjee, Protimprotim.bhattacharjee (at) dlr.deUNSPECIFIEDUNSPECIFIED
Gasnault, OlivierInstitut de Recherche en Astrophysique et Planétologie, Université Toulouse III, Toulouse, Francehttps://orcid.org/0000-0002-6979-9012UNSPECIFIED
Clave, Eliseelise.clave (at) univ-lyon1.frUNSPECIFIEDUNSPECIFIED
Egerland, Christoph H.christoph.egerland (at) dlr.dehttps://orcid.org/0000-0002-1099-6433217375994
Schröder, SusanneSusanne.Schroeder (at) dlr.dehttps://orcid.org/0000-0003-1870-3663UNSPECIFIED
Gabriel, Travis S. J.U.S. Geological Survey, Astrogeology Science Center, Flagstaff, AZ, USAUNSPECIFIEDUNSPECIFIED
Essunfeld, AriLos Alamos National Laboratory, USAUNSPECIFIEDUNSPECIFIED
Le Mouelic, StephaneLaboratoire de Planétologie et Géodynamique, CNRS UMR6112, Université de Nantes, FranceUNSPECIFIEDUNSPECIFIED
Demir, BegümBIFOLD and TU Berlin, Berlin, GermanyUNSPECIFIEDUNSPECIFIED
Date:9 April 2026
Journal or Publication Title:Scientific Reports
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:16
DOI:10.1038/s41598-026-47207-0
Publisher:Nature Publishing Group
ISSN:2045-2322
Status:Published
Keywords:semantic segmentation, Mars, ChemCam, multimodal
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - OptoRob
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Space Research > Remote and In-situ Spectroscopy
Institute of Space Research > Computational Camera and Sensing Systems
Deposited By: Rammelkamp, Kristin
Deposited On:11 Jun 2026 11:17
Last Modified:13 Aug 2026 10:46

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
OpenAIRE Validator logo electronic library is running on EPrints
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.