arXiv cs.AI· Yuxin Zhou, Huai Zhang, S. Mostafa Mousavi·· 1 天前AI 评分31
GraphRAG 首次直接用于原始地震目录：自动构建知识图谱并支持查询
Automatic Knowledge Graph Construction and Query for Earthquake Catalogs
AI 导读
研究首次将 GraphRAG 直接应用于三份原始表格地震目录（水库邻区震群、2019 Ridgecrest 构造序列、2021 Maduo Mw7.4 余震序列），无需人工结构化即可自动构建结构完整、可查询的知识图谱。
正文 · 原文
Abstract:In recent years, the number of events in earthquake catalogs has significantly increased due to the utilization of more effective deep learning based detectors and phase pickers but answering open ended questions such as what characterizes this sequence? remains constrained by rigid spatiotemporal windowing and subjective expert interpretation. We present the first systematic application of graph based retrieval augmented generation GraphRAG directly to raw, tabular catalog records across three independently featured catalogs, a reservoir adjacent swarm, the 2019 Ridgecrest tectonic sequence, and the 2021 Maduo Mw7.4 aftershock sequence. Without the need for manual data structuring, the pipeline builds structurally complete, queryable knowledge graphs for all three. Rigorous evaluation individually verified against catalog derived ground truth and a rule based reference graph exposes failure modes, and four seismology informed prompt fixes eliminate all targeted fabrications while sharply improving mechanism reasoning. A vector RAG baseline demonstrates the graph layers distinctive value, catalog wide summarization and temporal stage comparison. In addition, we have identified two main pitfalls that need attention. GraphRAG thus offers a practical, transferable, near zero cost query interface for earthquake catalogs, where careful prompting ensures the results are consistently accurate and trustworthy.
| Subjects: | Geophysics (physics.geo-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.24984 [physics.geo-ph] |
| (or arXiv:2607.24984v2 [physics.geo-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2607.24984 arXiv-issued DOI via DataCite |
Submission history
From: Yuxin Zhou [view email]
[v1]
Mon, 27 Jul 2026 18:39:05 UTC (13,508 KB)
[v2]
Wed, 11 Nov 2026 21:40:50 UTC (3,492 KB)
来源：arXiv cs.AI · arxiv.org