Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Predicting Dynamic-to-Static Correction Factor from Petrophysical Data and Chemostratigraphy using Unsupervised Machine Learning

Journal Article · · SPE Journal
DOI:https://doi.org/10.2118/225435-PA· OSTI ID:2997101
Estimating static mechanical properties of stratigraphic layers is critical for optimizing subsurface engineering applications. To estimate dynamic-to-static correction factor Fds (static-to-dynamic Young’s modulus ratio) across the Caney shale interval in Oklahoma, USA, we integrated triaxial test measurements and petrophysical data, including well logs and X-ray fluorescence (XRF) using unsupervised machine learning (ML). We used a novel workflow that includes principal component analysis (PCA) to reduce data set dimensionality of well logs and XRF data sets—both separately and combined—creating three scenarios, and later applied inverse distance weighting (IDW) to derive Fds profiles for these scenarios. Furthermore, we applied K-means clustering on each scenario to predict depositional facies, and built a stiffness zonation profile through chemostratigraphic analysis of the terrigenous elements to validate the predicted Fds. The predicted Fds profile from each scenario using the PCA-IDW method was compared with the constant Fds approach from our previous study by calculating the root mean square error (RMSE). The combined data sets scenario yielded the lowest RMSE value of 0.113, while the RMSE values for the well logs and XRF scenarios were 0.131 and 0.129, respectively. In addition, the predicted Fds from the XRF scenario well-matched the stiffness zonation from the chemostratigraphic analysis that was built using the optimized K-means clustering of nine clusters for that scenario. These methods and findings offer a valuable tool for refining lithological classification and improving the Fds profile, potentially enhancing drilling and stimulation strategies for subsurface energy engineering applications.
Research Organization:
National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)
Sponsoring Organization:
USDOE
Grant/Contract Number:
FE0031776
OSTI ID:
2997101
Journal Information:
SPE Journal, Journal Name: SPE Journal Journal Issue: 05 Vol. 30; ISSN 1086-055X; ISSN 1930-0220
Publisher:
Society of Petroleum Engineers (SPE)Copyright Statement
Country of Publication:
United States
Language:
English

References (27)

Prediction of Compressional, Shear, and Stoneley Wave Velocities from Conventional Well Log Data Using a Committee Machine with Intelligent Systems journal September 2011
Mechanical Properties of Shale After CO2 and CO2-Based Fluids Imbibition: Experimental and Modeling Study journal January 2022
Creep Properties of Shale and Predicted Impact on Proppant Embedment for the Caney Shale, Oklahoma journal May 2023
A novel data-driven model for real-time prediction of static Young's modulus applying mud-logging data journal September 2024
Experimental analysis of dynamic and static mechanical properties of deep thick anhydrite cap rocks under high-stress conditions journal June 2018
Workflow to build a continuous static elastic moduli profile from the drilling data using artificial intelligence techniques journal August 2021
Predicting shear wave velocity from conventional well logs with deep and hybrid machine learning algorithms journal July 2022
Mechanical behavior and constitutive model of shale under real-time high temperature and high stress conditions journal November 2022
Bakken stratigraphic and type well log learning network exploited to predict and data mine shear wave acoustic velocity journal February 2020
Mineralogy and reactive fluid chemistry evolution of hydraulically fractured Caney shale of Southern Oklahoma journal November 2024
What controls the mechanical properties of shale rocks? – Part I: Strength and Young's modulus journal November 2015
New and Highly Accurate Static Young’s Modulus Model Using Machine Learning Techniques journal September 2024
Augmenting and eliminating the use of sonic logs using artificial intelligence: A comparative evaluation journal May 2022
Mechanical properties of shale-gas reservoir rocks — Part 1: Static and dynamic elastic properties and anisotropy journal September 2013
Effect of Mineralogy and Petrophysical Characteristics on Acoustic and Mechanical Properties of Organic Rich Shale conference August 2013
The impact of rock composition on geomechanical properties of a shale formation: Middle and Upper Devonian Horn River Group shale, Northeast British Columbia, Canada journal February 2017
Integrated Microstructural Characterisation of Caney Shale, OK conference January 2020
Connecting Geomechanical Properties with Potential for Proppant Embedment and Production Decline for the Emerging Caney Shale, Oklahoma conference January 2021
Integrating Experiments and Well Logs to Predict Caney Shale Static Mechanical Properties During Production with Supervised Machine Learning conference January 2024
Multiscale Characterization of the Caney Shale — An Emerging Play in Oklahoma journal September 2021
Static and dynamic elastic properties, the cause of the difference and conversion methods – case study journal November 2015
Acoustic And Biaxial Measurement Of Rock Mechanical Properties For Interpretation Of Logs For Design Of Well-Completion Operations conference September 1979
Evaluation of the Rock Mechanical Properties of Shale Oil Reservoirs: A Case Study of Permian Lucaogou Formation in the Jimusar Sag, Junggar Basin journal November 2023
Application of Machine Learning in Evaluation of the Static Young’s Modulus for Sandstone Formations journal March 2020
Experiments and Modeling of Proppant Embedment and Fracture Conductivity for the Caney Shale, Oklahoma, USA conference June 2022
Effects of Interactions Between Produced Formation Fluid and Rock Matrix on Pore Structure of Caney Shale, Southern Oklahoma conference June 2024
Comparison of Geochemical Reactivity of Marcellus and Caney Shale Based on Effluent Analysis conference June 2024