The development of an AI-based tool for tracer selection and test design in geothermal energy applications

Vucinic, Luka ORCID: https://orcid.org/0000-0002-9370-3308, Vucinic, Maria Isabel Freitas da Silva, O’Connell, David, Mezali, Hakim, de Volder, Sofie, Poulain, Amael, Ajia, Fatima, Coxon, Catherine, Gill, Laurence and Savic, Dragan (2025) The development of an AI-based tool for tracer selection and test design in geothermal energy applications. In: AGU Annual Meeting 2025, 2025-12-15 - 2025-12-19, New Orleans.

Full text not available from this repository. (Request a copy)

Abstract

Geothermal energy is a clean, renewable, and sustainable energy resource with growing potential for future energy production. Artificial tracer tests were originally developed for hydrological and hydrogeological investigations, particularly in karst environments, and have since found widespread use across a range of applications. These techniques are now increasingly applied to geothermal energy systems where they provide valuable information on interwell connectivity, reservoir volume, heat transfer surface area, and thermal drawdown. The success of a tracer test depends on selecting appropriate tracers and designing a robust test protocol that ensures detection and meaningful interpretation. We present the concept of an AI-based tool, underpinned by a Large Language Model (LLM) framework, to support the planning and design of tracer tests in geothermal environments. This tool will integrate a structured database of tracer properties and behaviours with geothermal reservoir attributes and historical tracer test outcomes. Its primary function will be to assist in selecting appropriate tracer compounds or combinations based on test objectives and site-specific conditions. Additionally, the tool will offer guidance on estimating tracer injection quantities and provide recommendations for test design to maximise detection and minimise uncertainty. While development of the tool is ongoing, the proposed framework demonstrates strong potential to enhance the efficiency and reproducibility of artificial tracer test planning in geothermal energy investigations. It can contribute to the broader adoption of geothermal technologies by supporting more effective geothermal resource characterisation. Once completed, the tool will offer a flexible and adaptive decision-support system that integrates domain expertise with data-driven insights. In the future, this tool could be further expanded to support tracer test data analysis and interpretation, although implementing this will be a more complex challenge.

Item Type:	Conference or Workshop Item (Other)
Faculty \ School:	Faculty of Science > School of Environmental Sciences
Depositing User:	LivePure Connector
Date Deposited:	18 Aug 2026 12:27
Last Modified:	18 Aug 2026 12:27
URI:	https://ueaeprints.uea.ac.uk/id/eprint/104214
DOI:

Actions (login required)

View Item