Verifiably grounded machine interpretation of lunar geology
2026-08-10 • Computation and Language
Computation and LanguageMachine Learning
AI summaryⓘ
The authors worked on creating a computer program that can act like a geologist by analyzing different maps and images of the moon to understand its volcanic history. Their program looks at local visual data to describe layers of rock and terrain correctly. However, when the program tries to guess the ages of these layers just from images, it tends to rely on what it has memorized rather than real data. By adding a way for the program to look up scientific information, it can cite accurate age data from published research. This shows that combining visual analysis with access to scientific records is important for automated geology.
planetary geologystratigraphylunar basaltic maremultimodal vision-language architecturetopographic mapsspectral mapsgeologic mapsage datingopen-book retrievalmachine intelligence
Authors
Tom Sander, Kay Wohlfarth, Christian Wöhler
Abstract
Planetary geology relies on historical, interpretive reasoning to reconstruct past events from diverse observations. Here, we present a step toward an automated "machine intelligence geologist" by embedding this distinct methodology of geologic knowledge discovery and inference into a multimodal vision-language architecture. Focusing on the stratigraphy of lunar basaltic mare volcanism, we train a model to generate verifiably grounded geologic interpretations directly from co-registered topographic, spectral, and geologic maps. We demonstrate that while the system successfully balances established geological priors with local visual evidence to accurately describe stratigraphy and terrain, numeric age dating derived solely from vision defaults to memorized priors. Integrating an open-book retrieval mechanism resolves this, enabling the model to faithfully cite published chronologies. Our findings delineate the necessary architecture for automated geologic inference: site evidence must be visually interpreted from local data, while quantitative historical context must be retrieved from the scientific record.