From Metadata to Embeddings: Enabling Agentic AI for Subsurface Intelligence

This article presents a practical framework for AI-assisted subsurface data access based on explicit data representations, agent-based workflows, and efficient information retrieval. We demonstrate large-scale conversion of SEG-Y archives into self-describing MDIO v1 datasets and present a case study on agent-driven reconstruction of seismic metadata from legacy text headers. A second case study evaluates embedding-based retrieval across acquisition and processing reports, showing that vector quantisation and graph-based indexing enable low-latency, relevance-driven search. These capabilities are integrated into an interactive, multi-agent system that supports natural-language analysis and coordinated access to structured and unstructured subsurface information.