Machine Learning to Identify Geologic Factors Associated with Production in Geothermal Fields: A Case-Study Using 3D Geologic Data from Brady Geothermal Field and NMFk

Abstract

In this paper, we present an analysis using unsupervised machine learning (ML) to identify the key geologic factors that contribute to the geothermal production in Brady geothermal field. Brady is a hydrothermal system in northwestern Nevada that supports both electricity production and direct use of hydrothermal fluids. Transmissive fuid-fow pathways are relatively rare in the subsurface, but are critical components of hydrothermal systems like Brady and many other types of fuid-fow systems in fractured rock. Here, we analyze geologic data with ML methods to unravel the local geologic controls on these pathways. The ML method, non-negative matrix factorization with k-means clustering (NMFk), is applied to a library of 14 3D geologic characteristics hypothesized to control hydrothermal circulation in the Brady geothermal field. Our results indicate that macro-scale faults and a local step-over in the fault system preferentially occur along production wells when compared to injection wells and non-productive wells. We infer that these are the key geologic characteristics that control the through-going hydrothermal transmission pathways at Brady. Our results demonstrate: (1) the specific geologic controls on the Brady hydrothermal system and (2) the efficacy of pairing ML techniques with 3D geologic characterization to enhance the understanding of subsurface processes.

This submission includes the published journal article detailing this work, the published 3D geologic map of the Brady Geothermal Area used as a basis to develop structural and geological variables that are hypothesized to control or effect permeability or connectivity, 3D well data, along which geologic data were sampled for PCA analyses, and associated metadata file. This work was done using the GeoThermalCloud framework, which is part of SmartTensors (both are linked below).

6 Resources

*downloads since 2019

Related Datasets

Datasets associated with the same DOE project
  Submission Name Resources Submitted Status

Additional Info

DOE Project Name: Insightful Subsurface Characterizations and Predictions
DOE Project Number: 35517
DOE Project Lead: Mike Weathers
DOI: 10.15121/1832133
Last Updated: 7 months ago
Oct
2021
Data from October, 2021
Submitted Nov 10, 2021

Contact

United States Geological Survey


Status

Publicly accessible License 

Authors

Drew Siler
United States Geological Survey
Jeff D. Pepin
United States Geological Survey
Velimir V. Vesselinov
Los Alamos National Laboratory
Maruti K. Mudunuru
Pacific Northwest National Laboratory
Bulbul Ahmmed
Los Alamos National Laboratory

Keywords

geothermal, energy, NMFK, Brady Hot Springs, machine learning, ML, BHS, Nonnegative Matrix Factorization k-means, hydrothermal, Brady, k-means, clustering, nonnegative matrix factorization, matrix factorization, GeoThermalCloud, SmartTensors, unsupervised, 3D well data, 3D geologic map, geologic structure, faults, stress, geology, characterization, geologic model, production, code

Share

Export Citation to RIS
Submission Downloads