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 (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.
Highlights
Crustal permeability is a key parameter in hydrothermal process models used in exploration and development of geothermal systems
negative matrix factorization with k-means clustering (NMFk) is applied to a suite of geologic factors that have been calculated along production, injection, and non-productive wells at Brady geothermal field in northwestern Nevada
The four signals from the NMFk results relative to the 47 geothermal wells: A sorted by well clusters, B sorted by S2 values
Summary
Crustal permeability is a key parameter in hydrothermal process models used in exploration and development of geothermal systems. Permeability is, highly variable in space (Caine et al 1996; Caine and Forster 1999; Fairley et al 2003; Fairley and Hinds 2004; Sanderson and Zhang 2004) and this complicates characterization of subsurface hydrothermal processes It is common in developed geothermal systems to produce fluid from a few, relatively small (sub-meter- to meter-long) intervals of a borehole that may be 100 s or 1000 s of meters in total length (based on Nevada Division of Minerals, publicly available data http://www.nbmg.unr.edu/Geothermal/ProductionInjection/index.html). Temperatures of produced fluid have been ~ 130–185 °C during this time (Benoit 2014, and based on Nevada Division of Minerals, publicly available data http://www.nbmg.unr.edu/Geothermal/ProductionInjection/index.html), though temperatures as high as 219 °C have been measured (Shevenell et al 2012) These relatively high temperatures occur at relatively shallow levels (as shallow as 300–600 m depth for some production wells) as a result of convective upwelling driven by temperaturerelated differences in fluid density, and/or hydraulic head driven fluid-flow through hot rock (advection). The production well field; an elliptical, ~ 3 km wide × 6 km long (across strike × along strike, relative to the north-northeast fault strike) temperature anomaly; surface geothermal features include active fumaroles, silica sinter, silicified sediments, and warm ground (Kratt et al 2006; Lechler and Coolbaugh 2007; Faulds et al 2010a, b, 2017); and diffuse degassing of anomalous CO2, H2S, and Rn are centered on the Brady step-over (Jolie et al 2015a, b, 2016)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
