RAG for Geoscience: What We Expect, Gaps and Opportunities

TL;DR

This paper proposes Geo-RAG, an advanced retrieval-augmented generation framework tailored for geoscience, emphasizing multi-modal data retrieval, reasoning, verification, and transparency to address current limitations in text-centric workflows.

Contribution

It introduces Geo-RAG, a modular, multi-capability paradigm that enhances geoscience workflows through integrated retrieval, reasoning, generation, and verification processes.

Findings

Supports retrieval of multi-modal Earth data

Enables reasoning under physical constraints

Facilitates verification against models and measurements

Abstract

Retrieval-Augmented Generation (RAG) enhances language models by combining retrieval with generation. However, its current workflow remains largely text-centric, limiting its applicability in geoscience. Many geoscientific tasks are inherently evidence-hungry. Typical examples involve imputing missing observations using analog scenes, retrieving equations and parameters to calibrate models, geolocating field photos based on visual cues, or surfacing historical case studies to support policy analyses. A simple ``retrieve-then-generate'' pipeline is insufficient for these needs. We envision Geo-RAG, a next-generation paradigm that reimagines RAG as a modular retrieve $\rightarrow$ reason $\rightarrow$ generate $\rightarrow$ verify loop. Geo-RAG supports four core capabilities: (i) retrieval of multi-modal Earth data; (ii) reasoning under physical and domain constraints; (iii) generation of science-grade artifacts; and (iv) verification of generated hypotheses against numerical models, ground measurements, and expert assessments. This shift opens new opportunities for more trustworthy and transparent geoscience workflows.