An Integrated Machine Learning Workflow to Estimate In Situ Stresses Based on Downhole Sonic Logs and Laboratory Triaxial Ultrasonic Velocity Data

• Published in: Journal of geophysical research. Machine learning and computation Vol. 1; no. 4
• Main Authors: Mustafa, Ayyaz, Kelley, Mark, Lu, Guanyi, Bunger, Andrew P.
• Format: Journal Article
• Language: English
• Published: Wiley 01.12.2024
• Subjects: enhanced geothermal systems; in situ stress estimations; integrated machine learning; ML‐based empirical correlations; Utah forge
• ISSN: 2993-5210; 2993-5210
• DOI: 10.1029/2024JH000318

The optimum performance of various subsurface operations such as stimulation treatments, wellbore drilling, horizontal well placement, underground mining, and tunneling rely on accurate estimation of the in situ stresses. This study presents an integrated machine learning (ML) workflow for the reliable determination of the in situ stress in subsurface rock formations. The study workflow was completed in three phases. In the first phase, six supervised ML regression techniques were employed to develop the stress prediction models using laboratory true triaxial ultrasonic velocity tests (labTUV) data of subsurface rock samples retrieved from well 16A(78)‐32 located at the Utah FORGE geothermal site. In the second phase, subsurface geological formations were classified into rock facies using an unsupervised K‐means clustering algorithm. Finally, in the third phase, the optimized ML models were employed for predicting the in situ stresses in the corresponding rock facies in the well 16A(78)‐32 using field sonic logs. A comparison of evaluation metrics revealed the superior performance of ANN models for horizontal and vertical stress predictions with root mean squared error of 1.5, 0.6, and 1.7 MPa, and determination coefficient (R2) of 0.98, 0.98, and 0.96, for the testing/validation phases, respectively. The generalization capability of ML models was explored by uncovering the underlying physics. The mathematical expressions of constitutive relations were extracted from three ANN models. Further, a total of five rock facies were identified in the subsurface geological formations. The novel workflow would be capable of delivering reliable in situ stress profiles in subsurface geological formations without performing expensive field tests. Plain Language Summary The stresses in the subsurface geological rocks are critical to know for the successful completion of various subsurface operations such as wellbore drilling, tunneling, and mining, and production of geo‐energy resources. This study leverages the strength of machine learning techniques and labTUV experiments to explore the direct relationship between ultrasonic wave (compressional and shear) velocities and stresses in subsurface rocks. The ML models are developed and optimized for predicting stresses using the labTUV data of subsurface rock samples and successfully implemented to the field sonic log data for estimating stresses in the corresponding subsurface rocks classes. The field application is optimized by classifying the subsurface geological rocks into various rock classes. Further, empirical mathematical correlations extracted from optimized ML models can also be used to estimate the subsurface stresses without running the ML algorithms. The case study was performed to estimate the subsurface rock stresses at the Utah FORGE geothermal site. The proposed novel and integrated ML workflow can deliver the reliable estimation of stresses in subsurface rock formations. Key Points An integrated machine learning (ML) workflow was successfully implemented to estimate the in situ stresses in subsurface rocks A constitutive relationship between ultrasonic wave velocities and stresses was explored using machine learning and laboratory tests Empirical mathematical expressions of proposed intelligent models were extracted to use for stresses estimation without running the codes