Automatic Knowledge Graph Construction and Query for Earthquake Catalogs

2026-07-27

AI Summary

Traditional seismic catalog analysis is constrained by fixed spatiotemporal windows and subjective interpretation, limiting its ability to automatically address open-ended questions. This work presents the first application of GraphRAG to raw tabular earthquake catalogs, constructing a queryable knowledge graph without requiring manual structuring. We introduce a seismology-informed prompt repair strategy that effectively mitigates hallucination and enhances mechanistic reasoning. Evaluated against vector-based RAG, rule-based knowledge graphs, and domain-specific prompt engineering, our approach successfully generates fully automated summaries and phase-wise evolutionary comparisons across three real earthquake sequences. The results demonstrate superior accuracy, practical utility, and the advantage of zero-cost deployment.

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.

Problem

• earthquake catalogs
• open-ended questions
• spatiotemporal windowing
• expert interpretation
• knowledge graph

Innovation

• GraphRAG
• knowledge graph
• earthquake catalog
• retrieval-augmented generation
• seismic sequence analysis