构建面向地球科学的多模态增强生成系统，提升科研可信度。
RAG for Geoscience: What We Expect, Gaps and Opportunities
- 设计模块化检索-推理-生成-验证循环架构
- 支持多模态地球数据与物理约束下的科学级生成
- 适合地质、气候等需证据支撑的研究场景
检索增强生成（RAG）通过结合检索与生成提升语言模型能力，但现有流程仍以文本为中心，难以满足地球科学对证据的高需求。许多地质任务如基于相似场景填补缺失观测、检索方程参数校准模型、根据视觉线索定位野外照片，或挖掘历史案例支持政策分析，均需超越简单“检索-生成”流程。本文提出下一代范式Geo-RAG，将RAG重构为模块化的检索→推理→生成→验证闭环。该系统具备四项核心能力：(i) 多模态地球数据检索；(ii) 在物理与领域约束下推理；(iii) 生成科学级成果；(iv) 通过数值模型、实测数据和专家评估验证假设。这一转变推动更可信、透明的地球科学研究工作流发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。