Jaewook "Jake" Lee
Jaewook (Jake) Lee, Ph.D., is an Assistant Professor of Geophysics in the Department of Geosciences at The University of Texas Permian Basin whose work focuses on exploration seismology, induced seismicity, and data-driven subsurface modeling. He earned his Ph.D. in Geophysics from The University of Texas at Dallas, where his dissertation centered on seismic rock physics and machine learning, and he later served as a Postdoctoral Fellow with the Texas Seismological Network at the Bureau of Economic Geology (UT Austin). His research applies geostatistics, machine learning, and deep learning to integrate seismic (2D/3D/4D Time-lapse), well logs, and core-derived measurements for reservoir characterization, monitoring, and carbon storage applications.
Teaching
Undergraduate: Physical Geology, Geophysics, Structural Geology
Graduate: Exploration Geophysics, Quantitative Interpretation, Data Analysis and Machine Learning, Mapping and Cartography
Research Interests
Time-lapse reservoir monitoring for fluid injection operations (EOR, CCUS, and geothermal); subsurface geomodeling with rock physics and petrophysics; induced seismicity in energy operations; seismic inversion and interpretation with geostatistical and machine learning techniques.
Selected Publications
- Lee, J., Byun, J., Kim, B., Yoo, D., 2017, Delineation of gas hydrate reservoirs in the Ulleung Basin using unsupervised multi-attribute clustering without well log data, Journal of Natural Gas Science and Engineering, 46, 326-337
- Lee, J., & Lumley, D. E. (2023). Interpreting the effects of shale rock properties on seismic anisotropy by statistical and machine learning methods, Geoenergy Science and Engineering, 224, 211631.
- Lee, J., & Lumley, D. E. (2023). Predicting mineralogic brittleness index from seismic properties by using Shapley value regression and deep learning, Journal of Petroleum Science and Engineering, 220, 111231.
- Lee, J., Lumley, D. E., & Lim, U. Y. (2022). Improving total organic carbon estimation for unconventional shale reservoirs by using Shapley value regression and deep learning, AAPG Bulletin, 106(11), 2297–2314.
- Lee, J., Chen, Y., Dommisse, R., Huang, G. D., Savvaidis, A. (2024). Basin-Scale Prediction of S-wave Sonic Logs Using Machine Learning Techniques from Conventional Logs, Geophysical Prospecting, 72(7), 2557–2579.
Recent Presentations
- Onyeakusi, C., Ude-Akpeh, T., Lee, J., Trentham, R., Henderson, M., Cagle, C., Dupree, R. (2025). Seismic Impedance-Based Lithology Classification and Petrophysical Prediction for CO₂ Storage Site Characterization in the Delaware Basin, AAPG-SEG IMAGE 2025.
- Ude-Akpeh, T., Onyeakusi, C., Lee, J., Trentham, R., Henderson, M., Cagle, C., Dupree, R. (2025). Formation-Specific Porosity–Seismic Statistical Analysis in the Delaware Basin for CO₂ Storage Applications, AAPG-SEG IMAGE 2025.
- Lee, J., Chen, Y., Dommisse, R., Saad, O. M., Huang, G. D., Savvaidis, A. (2025). Enhanced Prediction of S-wave Velocity and Geomechanical Properties using Depth-Constrained Recurrent Neural Networks (online first), Geophysics.
- Lee, J., Dommisse, R., Savvaidis, A. (2024). Constructing a comprehensive 3D S-wave velocity model of the Delaware Basin, AAPG-SEG IMAGE 2024.
- Lee, J., Chen, Y., Dommisse, R., Savvaidis, A. (2024). Rock physics attribute analysis for identifying brittle zones in upper Delaware Basin formations, AAPG-SEG IMAGE 2024.
Service
• Team Lead, SEG Early Career Committee Quarterly Webinar Series Team (2025–present).
• Committee Member, SEG Lumley Scholarship Committee (2024–present).
• Scientific peer reviewer for journals and conferences including Scientific Reports, Marine and Petroleum Geology, Computational Geosciences, Journal of Geophysical Research, Journal of Applied Geophysics, Natural Resources Research, The Leading Edge, and SEG IMAGE abstracts.
Personal Links
Curriculum Vitae
Google Scholar
LinkedIn
Geophysics Research Laboratory
The Geophysics Research Laboratory, led by Dr. Jaewook Lee, supports advanced research and teaching in exploration seismology, induced seismicity, and subsurface modeling with an emphasis on practical solutions to energy, carbon mitigation, and environmental challenges. The lab develops and applies data-driven methods—such as geostatistics, machine learning, and deep learning—to better understand and predict the behavior of the Earth’s subsurface. Researchers work with a wide range of real-world datasets, including seismic surveys (2D, 3D, and time-lapse), conventional and unconventional well logs, velocity and synthetic models, and digitized core measurements. Analysis and modeling are enabled by industry-standard geoscience software (for example, Petrel, Techlog, Kingdom, Petra, Hampson-Russell, RokDoc, and PaleoScan) together with high-performance computing resources. These tools are combined to process, integrate, and visualize complex data, turning it into actionable insight for both research and student training.