RAG for Geoscience: What We Expect, Gaps and Opportunities
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915447487594496 |
|---|---|
| author | Yu, Runlong Luo, Shiyuan Ghosh, Rahul Li, Lingyao Xie, Yiqun Jia, Xiaowei |
| author_facet | Yu, Runlong Luo, Shiyuan Ghosh, Rahul Li, Lingyao Xie, Yiqun Jia, Xiaowei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11246 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAG for Geoscience: What We Expect, Gaps and Opportunities Yu, Runlong Luo, Shiyuan Ghosh, Rahul Li, Lingyao Xie, Yiqun Jia, Xiaowei Emerging Technologies Information Retrieval 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. |
| title | RAG for Geoscience: What We Expect, Gaps and Opportunities |
| topic | Emerging Technologies Information Retrieval |
| url | https://arxiv.org/abs/2508.11246 |