Utah FORGE 2439: Machine Learning for Well 16A(78)-32 Stress Predictions

Publicly accessible License 

This report reviews the training of machine learning algorithms to laboratory triaxial ultrasonic velocity data for Utah FORGE Well 16A(78)-32. Three machine learning (ML) predictive models were developed for the prediction of vertical and two orthogonally oriented horizontal stresses in the well. The ML models were trained using laboratory-based triaxial ultrasonic wave velocity (labTUV) data wherein wave velocities were measured with various combinations of true triaxial applied stress. The ultrasonic velocities data include compressional, fast shear, and slow shear velocities in each of three directions for a total of nine velocities for each stress combination. However, because the ultimate goal is to deploy the trained model for interpretation of field sonic log data where only the vertically propagating waves are measured, the work here focuses on just the wave velocities with vertical (z-direction) propagation. Also, because vertical (overburden) is often well constrained, one approach explored here is to take the vertical stress also as known and train the model to predict the two horizontal stresses. This work was done as part of Utah FORGE project 2439: A Multi-Component Approach to Characterizing In-Situ Stress at the U.S. DOE FORGE EGS Site: Laboratory, Modeling and Field Measurement.

Citation Formats

TY - DATA AB - This report reviews the training of machine learning algorithms to laboratory triaxial ultrasonic velocity data for Utah FORGE Well 16A(78)-32. Three machine learning (ML) predictive models were developed for the prediction of vertical and two orthogonally oriented horizontal stresses in the well. The ML models were trained using laboratory-based triaxial ultrasonic wave velocity (labTUV) data wherein wave velocities were measured with various combinations of true triaxial applied stress. The ultrasonic velocities data include compressional, fast shear, and slow shear velocities in each of three directions for a total of nine velocities for each stress combination. However, because the ultimate goal is to deploy the trained model for interpretation of field sonic log data where only the vertically propagating waves are measured, the work here focuses on just the wave velocities with vertical (z-direction) propagation. Also, because vertical (overburden) is often well constrained, one approach explored here is to take the vertical stress also as known and train the model to predict the two horizontal stresses. This work was done as part of Utah FORGE project 2439: A Multi-Component Approach to Characterizing In-Situ Stress at the U.S. DOE FORGE EGS Site: Laboratory, Modeling and Field Measurement. AU - Kelley, Mark A2 - Mustafa, Ayyaz A3 - Bunger, Andrew DB - Geothermal Data Repository DP - Open EI | National Renewable Energy Laboratory DO - KW - geothermal KW - energy KW - machine learning KW - in-situ stress KW - stress characterization KW - Utah FORGE KW - geophysics KW - seismic KW - triaxial KW - stress prediction KW - artificial neural network KW - model KW - feed forward artificial neural network LA - English DA - 2023/06/19 PY - 2023 PB - Battelle Memorial Institute T1 - Utah FORGE 2439: Machine Learning for Well 16A(78)-32 Stress Predictions UR - https://gdr.openei.org/submissions/1519 ER -
Export Citation to RIS
Kelley, Mark, et al. Utah FORGE 2439: Machine Learning for Well 16A(78)-32 Stress Predictions. Battelle Memorial Institute, 19 June, 2023, Geothermal Data Repository. https://gdr.openei.org/submissions/1519.
Kelley, M., Mustafa, A., & Bunger, A. (2023). Utah FORGE 2439: Machine Learning for Well 16A(78)-32 Stress Predictions. [Data set]. Geothermal Data Repository. Battelle Memorial Institute. https://gdr.openei.org/submissions/1519
Kelley, Mark, Ayyaz Mustafa, and Andrew Bunger. Utah FORGE 2439: Machine Learning for Well 16A(78)-32 Stress Predictions. Battelle Memorial Institute, June, 19, 2023. Distributed by Geothermal Data Repository. https://gdr.openei.org/submissions/1519
@misc{GDR_Dataset_1519, title = {Utah FORGE 2439: Machine Learning for Well 16A(78)-32 Stress Predictions}, author = {Kelley, Mark and Mustafa, Ayyaz and Bunger, Andrew}, abstractNote = {This report reviews the training of machine learning algorithms to laboratory triaxial ultrasonic velocity data for Utah FORGE Well 16A(78)-32. Three machine learning (ML) predictive models were developed for the prediction of vertical and two orthogonally oriented horizontal stresses in the well. The ML models were trained using laboratory-based triaxial ultrasonic wave velocity (labTUV) data wherein wave velocities were measured with various combinations of true triaxial applied stress. The ultrasonic velocities data include compressional, fast shear, and slow shear velocities in each of three directions for a total of nine velocities for each stress combination. However, because the ultimate goal is to deploy the trained model for interpretation of field sonic log data where only the vertically propagating waves are measured, the work here focuses on just the wave velocities with vertical (z-direction) propagation. Also, because vertical (overburden) is often well constrained, one approach explored here is to take the vertical stress also as known and train the model to predict the two horizontal stresses. This work was done as part of Utah FORGE project 2439: A Multi-Component Approach to Characterizing In-Situ Stress at the U.S. DOE FORGE EGS Site: Laboratory, Modeling and Field Measurement. }, url = {https://gdr.openei.org/submissions/1519}, year = {2023}, howpublished = {Geothermal Data Repository, Battelle Memorial Institute, https://gdr.openei.org/submissions/1519}, note = {Accessed: 2025-04-25} }

Details

Data from Jun 19, 2023

Last updated Feb 18, 2025

Submitted Jul 12, 2023

Organization

Battelle Memorial Institute

Contact

Mark Kelley

614.424.3704

Authors

Mark Kelley

Battelle Memorial Institute

Ayyaz Mustafa

University of Pittsburgh

Andrew Bunger

University of Pittsburgh

DOE Project Details

Project Name Utah FORGE

Project Lead Lauren Boyd

Project Number EE0007080

Share

Submission Downloads