Retooling Supervised Machine Learning for Data-Driven Hydrothermal Resource Assessments

Explore a 57-minute conference talk by Stan Mordensky, Research Geologist at the US Geological Survey, on applying supervised machine learning techniques to hydrothermal resource assessments. Discover how machine learning approaches can produce resource favorability maps that match or surpass traditional methods relying on expert decisions. Learn about the potential for reducing human bias and improving predictive performance in geothermal resource estimation. Gain insights into the comparison between data-driven machine learning models and previous assessment methods for moderate- and high-temperature geothermal resources in the western United States.

Retooling Supervised Machine Learning for Data-Driven Hydrothermal Resource Assessments