发表机构
University of Chinese Academy of Sciences; College of Earth and Planetary Sciences; Harvard University（中国科学院大学; 地球与行星科学学院; 哈佛大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对地震目录中开放性问题解答受限的情况，应用GraphRAG直接处理原始表格记录，构建可查询知识图谱，经评估改进并识别陷阱，提供实用查询接口，确保结果准确可靠。
AI 中文摘要
近年来，由于采用了更有效的基于深度学习的探测器和震相拾取器，地震目录中的事件数量显著增加。但回答诸如该序列有何特征等开放性问题，仍受严格时空窗和主观专家解释的限制。我们首次将基于图的检索增强生成（GraphRAG）系统地直接应用于三个具有独立特征的原始表格目录记录，即水库相邻地震群、2019年里奇克莱斯特构造序列和2021年玛多Mw7.4余震序列。该管道无需手动构建数据结构，就能为所有三个目录构建结构完整、可查询的知识图谱。通过与目录衍生的地面真值和基于规则的参考图进行严格评估，揭示了失败模式，四个基于地震学的提示修复消除了所有目标造假，同时显著改善了机制推理。向量RAG基线展示了图层的独特价值、目录范围的总结和时间阶段比较。此外，我们还识别了两个需要注意的主要陷阱。GraphRAG为地震目录提供了一个实用、可转移、近乎零成本的查询接口，精心的提示可确保结果始终准确可靠。
英文摘要
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.
