Natural Language-Driven Global Mapping of Martian Landforms

2026-01-22

AI Summary

This work addresses the semantic gap between pixel-based planetary surface imagery and the natural language used by scientists, which hinders large-scale, open-ended exploration of Martian landforms. To bridge this divide, the authors propose MarScope, a novel framework that leverages vision–language joint embedding models to align orbital images with textual descriptions in a shared semantic space, enabling arbitrary natural language queries without predefined labels. Trained on over 200,000 human-annotated image–text pairs, MarScope supports efficient, Mars-wide semantic retrieval and mapping, achieving an F1 score of 0.978 with query responses in under five seconds. The framework successfully facilitates both process-oriented and similarity-driven geomorphological analyses, transcending conventional classification paradigms.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Language and Vision
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

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.

Problem

• planetary mapping
• natural language
• semantic gap
• Martian landforms
• geospatial data

Innovation

• vision-language model
• label-free mapping
• planetary geomorphology
• semantic retrieval
• Mars surface analysis