Saved in:
Bibliographic Details
Main Authors: Wang, Yiran, Wang, Shuoyuan, Wei, Zhaoran, Zhao, Jiannan, Yao, Zhonghua, Xie, Zejian, Zhang, Songxin, Huang, Jun, Jing, Bingyi, Wei, Hongxin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.15949
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917217638023168
author Wang, Yiran
Wang, Shuoyuan
Wei, Zhaoran
Zhao, Jiannan
Yao, Zhonghua
Xie, Zejian
Zhang, Songxin
Huang, Jun
Jing, Bingyi
Wei, Hongxin
author_facet Wang, Yiran
Wang, Shuoyuan
Wei, Zhaoran
Zhao, Jiannan
Yao, Zhonghua
Xie, Zejian
Zhang, Songxin
Huang, Jun
Jing, Bingyi
Wei, Hongxin
contents Planetary surfaces are typically analyzed using high-level semantic concepts in natural language, yet vast orbital image archives remain organized at the pixel level. This mismatch limits scalable, open-ended exploration of planetary surfaces. Here we present MarScope, a planetary-scale vision-language framework enabling natural language-driven, label-free mapping of Martian landforms. MarScope aligns planetary images and text in a shared semantic space, trained on over 200,000 curated image-text pairs. This framework transforms global geomorphic mapping on Mars by replacing pre-defined classifications with flexible semantic retrieval, enabling arbitrary user queries across the entire planet in 5 seconds with F1 scores up to 0.978. Applications further show that it extends beyond morphological classification to facilitate process-oriented analysis and similarity-based geomorphological mapping at a planetary scale. MarScope establishes a new paradigm where natural language serves as a direct interface for scientific discovery over massive geospatial datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15949
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Natural Language-Driven Global Mapping of Martian Landforms
Wang, Yiran
Wang, Shuoyuan
Wei, Zhaoran
Zhao, Jiannan
Yao, Zhonghua
Xie, Zejian
Zhang, Songxin
Huang, Jun
Jing, Bingyi
Wei, Hongxin
Artificial Intelligence
Instrumentation and Methods for Astrophysics
Planetary surfaces are typically analyzed using high-level semantic concepts in natural language, yet vast orbital image archives remain organized at the pixel level. This mismatch limits scalable, open-ended exploration of planetary surfaces. Here we present MarScope, a planetary-scale vision-language framework enabling natural language-driven, label-free mapping of Martian landforms. MarScope aligns planetary images and text in a shared semantic space, trained on over 200,000 curated image-text pairs. This framework transforms global geomorphic mapping on Mars by replacing pre-defined classifications with flexible semantic retrieval, enabling arbitrary user queries across the entire planet in 5 seconds with F1 scores up to 0.978. Applications further show that it extends beyond morphological classification to facilitate process-oriented analysis and similarity-based geomorphological mapping at a planetary scale. MarScope establishes a new paradigm where natural language serves as a direct interface for scientific discovery over massive geospatial datasets.
title Natural Language-Driven Global Mapping of Martian Landforms
topic Artificial Intelligence
Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2601.15949