Search USGS⌕ Search
Home/Archive/USGS

USGS · 70221769

Machine learning to identify geologic factors associated with production in geothermal fields: A case-study using 3D geologic data, Brady geothermal field, Nevada

Drew L. Siler·Jeffrey D. Pepin·Velimir V. Vesselinov·Maruti K. Mudunuru·Bulbul Ahmmed
View original source ↗Export metadata ↓

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 fluid-flow pathways are relatively rare in the subsurface, but are critical components of hydrothermal systems like Brady and many other types of fluid-flow 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 (NMF k ), 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.

Explore related subjects

Geothermal Energy – Science, Society and TechnologyArticle
90° N90° S · 180° W ← longitude → 180° E
Source-reported bounding extent: 39.16414104768742° to 40.212440718286466° latitude; -119.70703125° to -118.38867187499999° longitude. This indicates report coverage, not an exact sampling location. View area on OpenStreetMap.

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Drew L. Siler, Jeffrey D. Pepin, Velimir V. Vesselinov, Maruti K. Mudunuru, Bulbul Ahmmed. 2021-06-30. Machine learning to identify geologic factors associated with production in geothermal fields: A case-study using 3D geologic data, Brady geothermal field, Nevada. https://doi.org/10.1186/s40517-021-00199-8

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2019

Three-dimensional geologic mapping to assess geothermal potential: Examples from Nevada and Oregon

Geologic structure plays an important role in controlling fluid flow in geothermal systems. In particular, very complex structural settings, consisting of many closely spaced and intersecting faults, host many geothermal systems. To elucidate the key geologic factors that affect fault-controlled geothermal circulation, it is critical to precisely characterize the structural and stratigraphic geometries in these complex settings. Here, we present a methodology and the results of 3D geologic analyses of two geothermal systems in the Basin and Range, USA. This methodology is a quantitative and geologically focused technique that can be used to precisely characterize geothermal areas, in a time when future geothermal growth demands increased exploration precision and efficiency. Surficial and subsurface geologic and geophysical data are synthesized in the construction of detailed 3D geologic maps of geothermal areas. Based on these 3D geologic maps, we examine several geologic attributes that control permeability development and geothermal fluid flow along faults. We use the stress state of faults and the distribution of structural discontinuities (i.e., fault intersections and fault terminations) to identify locations of upflow along faults in these geothermal systems. These results and the methodology presented herein are directly applicable to structurally controlled geothermal fields in the Basin and Range and worldwide. As development focus shifts toward blind geothermal resources, integration of precisely characterized subsurface structural information into exploration methods will be increasingly critical to continued growth in geothermal exploration and development.

Nevada, Oregon↗