|
Title: |
GeoDAWN to GeoTGo: from Complex Data to Decisions Related to Geothermal Prospectivity |
|
Authors: |
Tracy KLIPHUIS, Ari MARKOWITZ, Rishi YANG, Velimir (Monty) VESSELINOV |
|
Key Words: |
machine learning, data imputation, feature extraction, hidden geothermal resources, geothermal exploration, prospectivity. |
|
Conference: |
Stanford Geothermal Workshop |
|
Year: |
2025 |
|
Session: |
Modeling |
|
Language: |
English |
|
Paper Number: |
Kliphuis |
|
File Size: |
2363 KB |
|
View File: |
|
GeoTGo is a cloud-based application designed to streamline geothermal exploration, monitoring, and resource utilization. The platform leverages advanced data analytics, cloud/high-performance computing, machine learning, and GIS technology to optimize the entire geothermal energy lifecycle—from exploration and site assessment to real-time well monitoring and energy output optimization. Key features include AI-powered geothermal mapping, thermal gradient analysis, and reservoir simulations. The app is also designed to support near-real-time data analytics integrated with remote sensors. GeoTGo will also offer financial analysis tools for energy yield estimation, cost-benefit analysis, and scenario modeling, helping developers and investors evaluate the economic feasibility of geothermal projects. The application will also provide collaboration and project management capabilities through a centralized cloud dashboard, enabling teams to work efficiently on geothermal projects. GeoTGo's environmental monitoring tools will track sustainability metrics and link users with compliance methods with regulations. By leveraging cloud infrastructure and HPC, GeoTGo significantly reduces exploration time, optimizes geothermal resource utilization, and enhances decision-making. The app is targeted at geothermal exploration companies, energy providers, investors, regulators, and research institutions, aiming to promote sustainable energy development and maximize the potential of geothermal resources. Here, we demonstrate how GeoTGO is applied to process the GeoDAWN airborne datasets collected over Nevada. Our ML analyses extracted features (signals) in the data that are potentially important for the evaluation of geothermal prospectivity. We also demonstrated the applicability of our ML techniques to impute and blindly predict missing data.
Press the Back button in your browser, or search again.
Copyright 2025, Stanford Geothermal Program: Readers who download papers from this site should honor the copyright of the original authors and may not copy or distribute the work further without the permission of the original publisher.
Attend the nwxt Stanford Geothermal Workshop,
click here for details.