Exploratory analysis of machine learning techniques in the Nevada geothermal play fairway analysis. (June 2023)

• Record Type: Journal Article
• Authors: Smith, Connor M.; Faulds, James E.; Brown, Stephen; Coolbaugh, Mark; DeAngelo, Jacob; Glen, Jonathan M.; Burns, Erick R.; Siler, Drew L.; Treitel, Sven; Mlawsky, Eli; Fehler, Michael; Gu, Chen; Ayling, Bridget F.
• Is Part Of: Geothermics. Volume 111(2023)
• Publication Date: 2023-06
• Subjects: Hydrogeology -- Periodicals; Geothermal resources -- Periodicals; Énergie géothermique -- Périodiques; GEOTHERMAL ENGINEERING; GEOTHERMAL ENERGY; GEOTHERMAL EXPLORATION; Geothermal resources; Hydrogeology; Periodicals; Electronic journals; 621.44
• DOI: 10.1016/j.geothermics.2023.102693
• Languages: English
• ISSNs: 0375-6505

Abstract

Highlights: Machine learning techniques and new data developments are introduced to the nevada play fairway analysis to explore data driven geothermal favorability modeling. Data developments include new training data, introducing new feature maps, and translating certain categorical features to continuous numerical representations. Machine learning methods in the form of 1) supervised bayesian probabilistic neural, and 2) unsupervised principal component analysis paired with k-means clustering, constrain previously unrecognized feature controls on geothermal favorability, many of which are spatially organized within the extent of cluster groups and the major structural-hydrologic domains of the study area. Abstract: Play fairway analysis (PFA) is commonly used to generate geothermal potential maps and guide exploration studies, with a particular focus on locating and characterizing blind geothermal systems. This study evaluates the application of machine learning techniques to PFA in the Great Basin region of Nevada. Following the evaluation of various techniques, we identified two approaches to PFA that produced promising results, 1) supervised Bayesian probabilistic neural networks to generate geothermal potential maps with confidence intervals, and 2) unsupervised principal component analysis paired with k-means clustering to generate both cluster maps to help identify spatial patterns, as well as new combined feature inputs. We applied these techniques to perform a comparative analysis between two principal sets of geological and geophysical features related to permeability and heat and a set of positive (known geothermal resources) and negative training sites (known drill sites with unsuitable geothermal conditions). We found that these methods constrain previously unrecognized feature controls on geothermal favorability, many of which are spatially organized within the extent of cluster groups and the major structural-hydrologic domains of the study area. Furthermore, we utilized exploratory unsupervised modeling to highlight spatial relationships between input data and predictive output results of our supervised modeling. Finally, we demonstrate how our models compare to the previous Nevada PFA and how the rapid insights these machine learning techniques offer may support future assessments of both known and undiscovered blind geothermal systems in the Great Basin region of Nevada and beyond.