GBCGE student Connor Smith presents new research at the Stanford Geothermal Workshop
March 12, 2021
GBCGE graduate student Connor Smith attended this years’ Stanford Geothermal Workshop (virtual this year) and presented recent efforts in support of the NV geothermal machine learning project. In his paper, Connor and co-authors discuss how supervised and unsupervised learning methods are being used to improve our exploration workflow for hidden geothermal systems in the Great Basin region. Methods include using a supervised filter method, based on permutation analysis, to evaluate every possible feature combination/drop out scenario and rank feature influence based on the performance variance of supervised classification models. Additionally, the paper discusses use of an unsupervised factor analysis based on principal component analysis coupled with a semi-supervised k-means clustering algorithm. The results from these methods offer a promising avenue for identifying favorable sources of predictive information to identify the locations of blind geothermal systems and furthering our understanding of complex geothermal feature and label relationships in the Great Basin region and beyond. To read his paper, visit the IGA conference paper database: https://pangea.stanford.edu/ERE/db/IGAstandard/record_detail.php?id=29605