PNNL

Abstract

Geothermal energy is an essential renewable resource to generate flexible electricity. The geothermal resource assessments conducted by the U.S. Geological Survey showed that southwestern basins in the U.S. have the enormous geothermal potential for meeting the domestic electricity demand. Within these southwestern basins, the play fairway analysis (PFA) funded by the U.S. Department of Energy's (DOE) Geothermal Technologies Office identified that The Tularosa Basin in New Mexico has significant geothermal potential. This short paper presents a machine learning (ML) methodology for curating and analyzing the PFA data from the DOE's geothermal data repository. The proposed approach to find prospective geothermal locations in Tularosa Basin is based on non-negative matrix factorization with custom $k$-means clustering, an unsupervised ML method. This methodology is available in our open-source ML framework, GeoThermalCloud (GTC) \url{https://github.com/SmartTensors/GeoThermalCloud.jl}. Using this GTC framework, we discover prospective geothermal locations and find key parameters defining these prospects. Our ML analysis found that these prospects are consistent with the existing Tularosa basin's PFA studies. This analysis instills confidence in our GTC framework to accelerate geothermal exploration and resource development, which is generally time-consuming.