Back to Faculty Directory
Photo of Pyrcz, Michael
Office Location: CPE 5.174

Michael Pyrcz


B. J. Lancaster Professorship in Petroleum Engineering and Fellow of the Herring Professorship in Petroleum Engineering

Department Research Areas:
Geologic Carbon Storage
Integrated Reservoir Characterization
Unconventional Resources
Petrophysics and Pore Scale Processes

Personal Website

Educational Qualifications
BSc Engineering (Class Rank #1), Mining Engineering, School of Mining and Petroleum Engineering, University of Alberta, Canada

PhD Engineering, Geostatistical Reservoir Modeling, University of Alberta, Canada

PGE Courses
PGE 338: Data Analytics and Geostatistics
PGE 383: Stochastic Methods for Reservoir Modeling
PGE 383: Subsurface Machine Learning

Dr. Pyrcz’s current research focuses on improving spatial, subsurface modeling with new data science (including spatial data analytics, geostatistics and machine learning) models and workflows to improve mineral, hydrocarbon and water resource management and extraction, while minimizing and mitigating environmental impacts. He and his students work on developing subsurface data science methods that account for all engineering and geoscience information sources, spatiotemporal aspects of data, scale of the data and models, and uncertainty sources, all to support optimum decision making. Dr. Pyrcz freely shares all of his university educational content online (see “GeostatsGuy Lectures” on YouTube and “GeostatsGuy” on GitHub and Twitter).

Awards & Honors
International Association for Mathematical Geosciences Distinguished Lecturer, 2024.

Society for Petroleum Engineers, Gulf Coast Section Data Science and Engineering Analytics Award, 2021.

Associate Editor, Computers and Geosciences, International Association of Mathematical Geosciences, 2017.

Geostatistical Congress 2016 Scientific Committee, 2016.

International Association of Mathematical Geoscientists Council Nominee, 2016.

Geological Society of London, Reservoir Modeling Conference at University of Aberdeen, Invited Keynote Speaker, Talk “When Reservoir Models Become Unfit for Purpose,” 2015.

American Association Petrol Geologists, A.I. Levorsen Award for Best Paper Pacific Section, Ventura, California, for paper “Allocyclicity of Sediment Volume and Composition Provide the Basis for a Predictive Model of Turbidite Channel Architectures,” T. McHargue, J. Clark, M. Sullivan, M. Pyrcz, A. Fildani, M. Levy, H. Posamentier, B. W. Romans, and J. A. Covault, May 3–5, 2009.

Outstanding Technical Editor, Society of Petroleum Engineers, Reservoir Evaluation & Engineering Journal, 2008.

Best Heavy Oil Paper, Canadian Society of Petroleum Geologists, Canadian Heavy Oil Association, 2004.

National Science and Engineering Research Council of Canada (NSERC), Post Graduate Scholarships (PGS) A and B, 2000–2004.

Association of Professional Engineers and Geoscientists of Alberta (APEGA) Gold Medal for B.Sc. Class Rank #1, 2000.

Professional Engineer Alberta, Canada.

Highlighted Publications and Google Scholar Profile

Pyrcz, M.J., and Deutsch, C.V., 2014, Geostatistical Reservoir Modeling, 2nd Edition, Oxford University Press, New York, p. 448.

Peer Reviewed Journal Articles
Nwachukwu, A., Jeong, H., Pyrcz, M.J. and Lake, L.W. Fast Evaluation of Well Placements in Heterogeneous Reservoir Models Using Machine Learning. Journal of Petroleum Science and Engineering 163, 463-475, Apr. 2018.

Santos, J.E., Yin, Y., Jo, H., Pan, W., Kang, Q., Viswanathan, H.W., Prodanović, M., Pyrcz, M.J., and Lubbers N., Computationally Efficient Multiscale Neural Networks Applied to Fluid Flow in Complex 3D Porous Media. Transport in Porous Media, 140, p. 241-272, May 2021.

Pan, W., Torres-Verdin, C., and Pyrcz, M.J. Stochastic Pix2pix: A New Machine Learning Method for Geophysical and Well Conditioning of Rule-Based Channel Reservoir Models. Natural Resources Research 30, 1319–1345, Nov. 2021.

Santos, J.E., Xu, D., Jo, H., Landry, C.J., Prodanović, M., and Pyrcz, M.J. PoreFlow-Net: A 3D Convolutional Neural Network to Predict Fluid Flow Through Porous Media. Advances in Water Resources v. 138, p. 103539 [12 pgs], Apr. 2020.

Maldonado-Cruz, E., and Pyrcz, M.J. Tuning Machine Learning Dropout for Subsurface Uncertainty Model Accuracy. Journal of Petroleum Science and Engineering, 205, 108975 [9 pgs], Oct. 2021.

Jo, H., Pan, W., Santos, J.E., Jung, H., and Pyrcz, M.J. Machine Learning Assisted History Matching for a Deepwater Lobe System. Journal of Petroleum Science and Engineering, 109086 [18 pgs] Dec. 2021.

Pan, W., Jo, H., Santos, J., Torres-Verdin, C., Pyrcz, M. J. Hierarchical Machine Learning Workflow for Conditional and Multiscale Deepwater Reservoir Modeling, American Association of Petroleum Geologists Bulletin, Jul. 2022.

Jo, H., Laugier, F.L., Sullivan, M.D., Pyrcz, M.J., Stratigraphic Controls on Connectivity and Flow Performance in Deepwater Lobe-Dominated Reservoirs, American Association of Petroleum Geologists Bulletin, 107(6), [19 pgs], June 2023,

Shakiba, M., Lake, L.W., Gale, J.F.W., and Pyrcz, M.J., Characterization of Spatial Relationships Between Fractures from Different Sets Using K-function Analysis, American Association of Petroleum Geologists Bulletin, 107(7), [20 pgs], Jul. 2023,

Liu, L., Santos, J.E., Prodanovic, M., and Pyrcz, M.J., Mitigation of Nonstationarity with Vision Transformers, Computers and Geosciences, 178, [8 pgs], Sept. 2023,