Smarter Geothermal Field Development with an Agentic Artificial Intelligence System

Abstract

Geothermal field development involves complex processes that require multi-disciplinary expertise across domains. Decision-making often demands the integration of geological, geophysical, and reservoir engineering insights, and input from operational teams, drilling engineers, and business units focused on project viability and profitability — all under tight temporal and financial constraints. We present GAIA (Geothermal Analytics and Intelligent Agent), an AI-based system for automation and assistance in geothermal field development. GAIA consists of three core components: GAIA Agent, GAIA Chat, and GAIA DT (Digital Twin), which together constitute an agentic retrieval-augmented generation (RAG) workflow. Specifically, GAIA Agent, powered by a pre-trained large language model (LLM), designs and manages task pipelines by autonomously querying knowledge bases and orchestrating multi-step analyses. GAIA DT encapsulates classical and surrogate physics models, which, combined with built-in domain-specific subroutines and visualization tools, enable predictive modeling of geothermal systems. Lastly, GAIA Chat serves as a web-based interface for users, featuring a ChatGPT-like layout with additional functionalities such as interactive visualizations, parameter controls, and in-context document retrieval. To ensure GAIA’s specialized capability for handling complex geothermal-related tasks, we curated a test set comprising various geothermal-related use cases, and we rigorously and continuously evaluate the system’s performance. GAIA is designed to support a wide range of stakeholders, including operators, researchers, and regulators, by providing actionable insights and tailored analytical workflows suited to their specific needs. With its innovative agentic RAG approach, we envision GAIA as a pioneering step toward intelligent geothermal field development, capable of assisting human experts in decision-making, accelerating project workflows, and ultimately enabling automation of the development process.