WorldWide Drilling Rescource

Ten Geothermal Projects Awarded Funding Information Provided by the U.S. Department of Energy The U.S. Department of Energy (DOE) is awarding ten new projects up to $5.5 million to apply machine learning techniques to geothermal exploration projects. It is believed machine learning could help locate geothermal resources by using advanced algorithms to identify patterns from data. In addition to improving success rates in exploratory drilling, machine learning could also lead to greater efficiency in plant operations and lower the overall costs for geothermal energy. The selected projects include: j Colorado School of Mines will apply machine learning techniques to analyze remote-sensing images, with the goal of developing a process to identify blind geothermal resources based on surface characteristics. The school will also develop a methodology to automatically label data from hyperspectral images of Brady’s Hot Springs, Desert Rock, and the Salton Sea. j Lawrence Livermore National Laboratory is developing and applying new machine learning techniques to a multiphysics (magnetotelluric and seis- mic) dataset from the Raft River geothermal field to better identify and target fracture zones for drilling production wells. j Los Alamos National Laboratory will be developing an extendable, open source cloud-based machine learning framework called GTCloud (GeoThermal Cloud) which will incorporate local, regional, and continental scale geother- mal data to estimate risk, cost, and thermal power production outputs for geothermal exploration. j National Renewable Energy Laboratory is hoping to improve geothermal reservoir management by using machine learning in conjunction with physics-based subsurface flow paths and interwell connectivity models. j Pennsylvania State University is planning to use machine learning methodologies to study microearthquakes and their linkages to probable zones of permeability, as well as the risks associated with induced seismicity in geothermal development. The project team has demonstrated significant success in predicting earthquakes at the laboratory scale, proving passive seismic signals contain information on the evolution of stress and fractures in the subsurface. j University of Arizona will use its DOE funding to build a single web-based platform to allow geothermal researchers and developers access to continuously growing scientific and exploration data. The project will use a computer program to analyze the grammatical and visual relationships of words in the texts (e.g., noun, adjective) and use these relationships to build structured (e.g., spreadsheets) datasets for geothermal research. j University of Houston is developing a method to automatically detect subsurface fault/fracture zones from seismic im- ages, and reliably characterize the fractures with the fault/fracture zones using the ‘double-beam’ method. Investigators have already shown success using the techniques in gas and oil settings and will adapt them to the more difficult geother- mal environment. j University of Nevada is actually building on a prior project focused on defining geothermal ‘play fairways’ in Nevada; the previous project used several machine learning techniques to identify regions with high geothermal potential. However, it relied to some degree on expert opinion where training data was lacking. This application addresses the shortcoming through the introduction of an additional 100 training sites and the addition of an industry partner with extensive proprietary datasets. j University of Southern California is developing data-driven predictive mod- els for the integration of real-time fault detection and diagnosis. These models will be integrated by using predictive control algorithms to improve the effi- ciency of energy production operations in a geothermal power plant. j Upflow Limited: Will make multiple decades of closely guarded production data from one of the world’s longest operating geothermal fields in Taupo, New Zealand. This data will be com- bined with the archives from the largest geothermal company operating in the U.S. The models developed from this massive data store will enable the cre- ation of a prediction/recommendation engine to help operators improve plant availability. The Raft River geothermal project is located in Cassia County, Idaho. GEO Information: Joel Walton jwalton022@aol.com • (225) 744-4554 www.lgwa.org January 9, 2020 Paragon Casino - Marksville, LA Tower or Atrium hotel rooms call (800) 642-7777 and refer to LGWA Annual 2020 conference use code LGWA 01G Registration starts at 7 am, Seminars start at 8 am (Cocktail hour, dinner, and BINGO at 6 pm the night before the convention [the 8th].) Louisiana Ground Water Association Convention & Trade Show 30 OCTOBER 2019 WorldWide Drilling Resource ®