Loading...
Geothermal AI: an artificial intelligence for early stage geothermal exploration
Moraga, Jaime F.
Moraga, Jaime F.
Citations
Altmetric:
Advisor
Editor
Date
Date Issued
2022
Date Submitted
Collections
Research Projects
Organizational Units
Journal Issue
Embargo Expires
Abstract
Exploration of geothermal resources involves analysis and management of a large number of uncertainties, which makes investment and operations decisions challenging. Remote Sensing (RS), Machine Learning (ML) and Artificial Intelligence (AI) have potential in managing the challenges of geothermal exploration. This thesis presents a methodology that integrates RS, ML and AI to create an initial assessment of geothermal potential, by resorting to known indicators of geothermal areas – namely mineral markers, surface temperature, faults and deformation. The method introduced in this thesis was implemented in two sites (Brady and Desert Peak geothermal sites) that are close to each other but have different characteristics (Brady having clear surface manifestations and Desert Peak being a blind site). Various satellite images and geospatial data were processed for mineral markers, temperature, faults and deformation and then ML methods were implemented to obtain patterns of surface manifestation related to geothermal sites. The resulting Geothermal AI uses these patterns from surface manifestations to predict geothermal potential of each pixel. The Geothermal AI was tested using independent data sets obtaining accuracy of 92-95%. The Geothermal AI was also tested by training on one site and executing it for the other site to predict the geothermal / non-geothermal delineation; in this task, which requires generalization, the Geothermal AI performed quite well in prediction with 72-76% accuracy.
Associated Publications
Rights
Copyright of the original work is retained by the author.