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
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).
Citation Formats
TY - DATA
AB - 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).
AU - Siler, Drew
A2 - Pepin, Jeff D.
A3 - Vesselinov, Velimir V.
A4 - Mudunuru, Maruti K.
A5 - Ahmmed, Bulbul
DB - Open Energy Data Initiative (OEDI)
DP - Open EI | National Renewable Energy Laboratory
DO - 10.15121/1832133
KW - geothermal
KW - energy
KW - NMFK
KW - Brady Hot Springs
KW - machine learning
KW - ML
KW - BHS
KW - Nonnegative Matrix Factorization k-means
KW - hydrothermal
KW - Brady
KW - k-means
KW - clustering
KW - nonnegative matrix factorization
KW - matrix factorization
KW - GeoThermalCloud
KW - SmartTensors
KW - unsupervised
KW - 3D well data
KW - 3D geologic map
KW - geologic structure
KW - faults
KW - stress
KW - geology
KW - characterization
KW - geologic model
KW - production
KW - code
LA - English
DA - 2021/10/01
PY - 2021
PB - United States Geological Survey
T1 - 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
UR - https://doi.org/10.15121/1832133
ER -
Siler, Drew, et al. 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. United States Geological Survey, 1 October, 2021, GDR. https://doi.org/10.15121/1832133.
Siler, D., Pepin, J., Vesselinov, V., Mudunuru, M., & Ahmmed, B. (2021). 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. [Data set]. GDR. United States Geological Survey. https://doi.org/10.15121/1832133
Siler, Drew, Jeff D. Pepin, Velimir V. Vesselinov, Maruti K. Mudunuru, and Bulbul Ahmmed. 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. United States Geological Survey, October, 1, 2021. Distributed by GDR. https://doi.org/10.15121/1832133
@misc{OEDI_Dataset_7460,
title = {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},
author = {Siler, Drew and Pepin, Jeff D. and Vesselinov, Velimir V. and Mudunuru, Maruti K. and Ahmmed, Bulbul},
abstractNote = {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).},
url = {https://gdr.openei.org/submissions/1344},
year = {2021},
howpublished = {GDR, United States Geological Survey, https://doi.org/10.15121/1832133},
note = {Accessed: 2025-05-09},
doi = {10.15121/1832133}
}
https://dx.doi.org/10.15121/1832133
Details
Data from Oct 1, 2021
Last updated May 21, 2024
Submitted Nov 10, 2021
Organization
United States Geological Survey
Contact
Drew Siler
Authors
Original Source
https://gdr.openei.org/submissions/1344Research Areas
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, codeDOE Project Details
Project Name Insightful Subsurface Characterizations and Predictions
Project Lead Mike Weathers
Project Number 35517