A knowledge graph and large language model integration framework for intelligent oil and gas geological exploration

Abstract

The digitization process in oil and gas exploration and production necessitates intelligent approaches to integrating various types of geological, geophysical, engineering, and production information. The current information systems generally lack a unified approach to knowledge representation, semantic interoperability, and reasoning capability to perform complex operations in the domain of E&P. This study presents a novel framework for an intelligent approach to oil and gas geological exploration using knowledge graphs and large language models (LLMs). The proposed architecture utilizes both the structured representation and reasoning power of knowledge graphs as well as the semantic comprehension and task planning capabilities of LLMs. A seven-layer architecture is proposed, which includes hierarchical storage, computing resource management, sampling management and model training, data management, service interface integration, industrial agents, and virtual expert groups. The main components of integration, as well as the workflow for implementation, are described to aid in geological knowledge management, target assessment, risk detection during drilling operations, and reservoir development. The proposed framework offers an actionable path to transform traditional oil and gas information systems into intelligence systems based on knowledge and reasoning rather than data-centric systems.