Stanley P Mordensky
Stanley is a Research Geologist at the Geology, Minerals, Energy, and Geophysics Science Center. Since joining the USGS, Stanley has devoted his career to developing machine learning methods for analysis of geothermal systems, groundwater, and subsurface heat flow and specializes in experimental rock mechanics, volcano processes, fluid transport, and hydrothermal alteration.
Stanley joined the USGS as a Mendenhall Research Fellow with the Geology, Minerals, Energy, and Geophysics Science Center in February 2021. His research interests vary from machine learning, geothermal systems, and volcano monitoring to rock mechanics, geochemistry, and geohazards. Stan spent several seasons mapping lithology, geotechnical units, geothermal hazards, and volcanic hazards across several geophysical provinces and has taught these subjects to university students. He also served as a volunteer for the Hawaiian Volcano Observatory and Yellowstone National Park.
Professional Experience
2020: Guest Scientist, Yellowstone National Park, Mammoth Hot Springs, WY
2017: Guest Scientist, Yellowstone National Park, Mammoth Hot Springs, WY
2014 - 2015: Research Fellow, National Energy and Technology Laboratory. Albany, OR
2010: National Association of Geoscience Teachers Fellow, Reston, VA
Education and Certifications
Ph.D., Engineering Geology, University of Canterbury, New Zealand, 2019
MSc, Geological Sciences, University of Oregon, USA, 2012
BSc, Economics, George Washington University, USA 2009
BA, Geological Sciences, George Washington University, USA 2009
Affiliations and Memberships*
Geological Society of America
Science and Products
Maps of elevation trend and detrended elevation for the Great Basin, USA
Geothermal resource favorability: select features and predictions for the western United States curated for DOI 10.1016/j.geothermics.2023.102662
Heat flow maps and supporting data for the Great Basin, USA
Predicting large hydrothermal systems
We train five models using two machine learning (ML) regression algorithms (i.e., linear regression and XGBoost) to predict hydrothermal upflow in the Great Basin. Feature data are extracted from datasets supporting the INnovative Geothermal Exploration through Novel Investigations Of Undiscovered Systems project (INGENIOUS). The label data (the reported convective signals) are extracted from meas
Cursed? Why one does not simply add new data sets to supervised geothermal machine learning models
Recent advances in machine learning (ML) identifying areas favorable to hydrothermal systems indicate that the resolution of feature data remains a subject of necessary improvement before ML can reliably produce better models. Herein, we consider the value of adding new features or replacing other, low-value features with new input features in existing ML pipelines. Our previous work identified st
Don’t Let Negatives Hold You Back: Accounting for Underlying Physics and Natural Distributions of Hydrothermal Systems When Selecting Negative Training Sites Leads to Better Machine Learning Predictions
Selecting negative training sites is an important challenge to resolve when utilizing machine learning (ML) for predicting hydrothermal resource favorability because ideal models would discriminate between hydrothermal systems (positives) and all types of locations without hydrothermal systems (negatives). The Nevada Machine Learning project (NVML) fit an artificial neural network to identify area
Detrending Great Basin elevation to identify structural patterns for identifying geothermal favorability
When less is more: How increasing the complexity of machine learning strategies for geothermal energy assessments may not lead toward better estimates
New maps of conductive heat flow in the Great Basin, USA: Separating conductive and convective influences
What did they just say? Building a Rosetta stone for geoscience and machine learning
Predicting geothermal favorability in the western United States by using machine learning: Addressing challenges and developing solutions
Science and Products
- Data
Maps of elevation trend and detrended elevation for the Great Basin, USA
Topography provides information about the structural controls of the Great Basin and therefore information that may be used to identify favorable structural settings for geothermal systems. Specifically, local relative topography gives information about locations of faults and fault intersections relative to mountains, valleys, or at the transitions between. As part of U.S. Geological Survey efforGeothermal resource favorability: select features and predictions for the western United States curated for DOI 10.1016/j.geothermics.2023.102662
The data contained herein are five input features (i.e., heat flow, distance to the nearest quaternary fault, distance to the nearest quaternary magma body, seismic event density, maximum horizontal stress) and labels (i.e., where known geothermal systems have been identified) from Williams and DeAngelo (2008) and nine favorability maps from Mordensky et al. (2023). The favorability maps are the uHeat flow maps and supporting data for the Great Basin, USA
Geothermal well data from Southern Methodist University (SMU, 2021) and the U.S. Geological Survey (Sass et al., 2005) were used to create maps of estimated background conductive heat flow across the greater Great Basin region of the western US. The heat flow maps in this data release were created using a process that sought to remove hydrothermal convective influence from predictions of backgroun - Publications
Predicting large hydrothermal systems
We train five models using two machine learning (ML) regression algorithms (i.e., linear regression and XGBoost) to predict hydrothermal upflow in the Great Basin. Feature data are extracted from datasets supporting the INnovative Geothermal Exploration through Novel Investigations Of Undiscovered Systems project (INGENIOUS). The label data (the reported convective signals) are extracted from meas
AuthorsStanley Paul Mordensky, Erick Burns, Jacob DeAngelo, John LiporCursed? Why one does not simply add new data sets to supervised geothermal machine learning models
Recent advances in machine learning (ML) identifying areas favorable to hydrothermal systems indicate that the resolution of feature data remains a subject of necessary improvement before ML can reliably produce better models. Herein, we consider the value of adding new features or replacing other, low-value features with new input features in existing ML pipelines. Our previous work identified st
AuthorsStanley Paul Mordensky, Erick Burns, John Lipor, Jacob DeAngeloDon’t Let Negatives Hold You Back: Accounting for Underlying Physics and Natural Distributions of Hydrothermal Systems When Selecting Negative Training Sites Leads to Better Machine Learning Predictions
Selecting negative training sites is an important challenge to resolve when utilizing machine learning (ML) for predicting hydrothermal resource favorability because ideal models would discriminate between hydrothermal systems (positives) and all types of locations without hydrothermal systems (negatives). The Nevada Machine Learning project (NVML) fit an artificial neural network to identify area
AuthorsPascal D. Caraccioli, Stanley Paul Mordensky, Cary R. Lindsey, Jacob DeAngelo, Erick Burns, John LiporDetrending Great Basin elevation to identify structural patterns for identifying geothermal favorability
Topography provides information about the structural controls of the Great Basin and therefore information that may be used to identify favorable structural settings for geothermal systems. The Nevada Machine Learning Project (NVML) tested the use of a digital elevation map (DEM) of topography as an input feature to predict geothermal system favorability. A recent study re-examines the NVML data,AuthorsJacob DeAngelo, Erick Burns, Stanley Paul Mordensky, Cary Ruth LindseyWhen less is more: How increasing the complexity of machine learning strategies for geothermal energy assessments may not lead toward better estimates
Previous moderate- and high-temperature geothermal resource assessments of the western United States utilized data-driven methods and expert decisions to estimate resource favorability. Although expert decisions can add confidence to the modeling process by ensuring reasonable models are employed, expert decisions also introduce human and, thereby, model bias. This bias can present a source of errAuthorsStanley Paul Mordensky, John Lipor, Jacob DeAngelo, Erick R. Burns, Cary Ruth LindseyNew maps of conductive heat flow in the Great Basin, USA: Separating conductive and convective influences
Geothermal well data from Southern Methodist University and the U.S. Geological Survey (USGS) were used to create maps of estimated background conductive heat flow across the Great Basin region of the western United States. These heat flow maps were generated as part of the USGS hydrothermal and Enhanced Geothermal Systems resource assessment process, and the creation process seeks to remove the iAuthorsJacob DeAngelo, Erick R. Burns, Emilie Gentry, Joseph F. Batir, Cary Ruth Lindsey, Stanley Paul MordenskyWhat did they just say? Building a Rosetta stone for geoscience and machine learning
Modern advancements in science and engineering are built upon multidisciplinary projects that bring experts together from different fields. Within their respective disciplines, researchers rely on precise terminology for specific ideas, principles, methods, and theories. Hence, the potential for miscommunication is substantial, especially when common words have been adopted by one (or both) group(AuthorsStanley Paul Mordensky, John Lipor, Erick R. Burns, Cary Ruth LindseyPredicting geothermal favorability in the western United States by using machine learning: Addressing challenges and developing solutions
Previous moderate- and high-temperature geothermal resource assessments of the western United States utilized weight-of-evidence and logistic regression methods to estimate resource favorability, but these analyses relied upon some expert decisions. While expert decisions can add confidence to aspects of the modeling process by ensuring only reasonable models are employed, expert decisions also inAuthorsStanley Paul Mordensky, John Lipor, Jacob DeAngelo, Erick R. Burns, Cary Ruth Lindsey
*Disclaimer: Listing outside positions with professional scientific organizations on this Staff Profile are for informational purposes only and do not constitute an endorsement of those professional scientific organizations or their activities by the USGS, Department of the Interior, or U.S. Government