Discovering Hidden Geothermal Signatures using Unsupervised Machine Learning
V.V. Vesselinov, et al.
Summary
Discovery of hidden geothermal resources is challenging. It requires the mining of large datasets with diverse data attributes representing subsurface hydrogeological and geothermal conditions. The commonly used play fairway analysis approach typically incorporates subject-matter expertise to analyze regional data to estimate geothermal characteristics and favorability. We demonstrate an alternative approach based on machine learning (ML) to process a geothermal dataset from southwest New Mexico (SWNM). We use unsupervised ML to extract hidden geothermal signatures from the data, and then we use these signatures to estimate geothermal favorability. The results are consistent with an existing comprehensive play fairway analysis, and they provide insights into key parameters defining geothermal favorability in the study area. We also discuss a coupling strategy between a process model (Burns equation) and ML to obtain a better understanding about the geothermal conditions in the study area.