MICHAEL J. PYRCZ, Ph.D., P.Eng., Associate Professor
Cockrell School of Engineering, Jackson School of Geosciences
and Bureau of Economic Geology

The University of Texas at Austin, Austin, Texas, USA

Here is my team of graduate students that I have the privilege to work with here at the University of Texas at Austin. Here's a list of my students and some details on their projects.

We are the Texas Center for Data Analytics and Geostatistics

Our research focused on subsurface/spatial data analytics, geostatistics, and machine learning.

Graduate Students

Wen Pan (Ph.D. Student, cosupervised with Prof. Torres-Verdin)

Novel pix-2-pix method for deep learning-based subsurface models with improved conditioning to geological concepts, local observations (well data) and large scale, exhaustive imaging (seismic data).
New, geologically realistic rule-based subsurface modeling methods and workflows for training subsurface deep learning  

Honggeun Jo (Ph.D. Student)
New, geologically realistic subsurface modeling methods and workflows with deep convolutional generative adversarial networks (DCGANS)
New, geologically realistic rule-based subsurface modeling methods and workflows for training subsurface deep learning 
Improved data integration for subsurface models with machine learning, including well and production data
Started Ph.D. Fall 2017

Ryan Farell (Ph.D. student, cosupervised with Prof. Bickel)
New geostatistical and spatial data analytics methods to support subsurface development decision making

Mahmood Shakiba (Ph.D. student, cosupervised with Prof. Lake)
New geostatistical and spatial statistics to characterize and model lineaments/fractures for spatial/subsurface settings
Methods for accounting for limited spatial samples and correcting for edge effects

Javier Santos (Ph.D. student, cosupervised with Prof. Prodanović)
Multiscale flow through porous media modeling with deep learning.
Convolutional neural network-based machine learning intragranular flow through porous media surrogate models
Deep learning architecture optimization and machine learning generalization and transfer learning
Started Ph.D. Fall 2018

Wendi Liu (Ph.D. student)
New geostatistics, spatial data analytics, machine learning methods and workflows for unconventional reservoirs
New methods for spatial anomaly detection, heterogeneity measures and spatial debiasing for spatial predictive machine learning
Started Ph.D. Fall 2018

Jack Xiao (Ph.D. student, cosupervised with Prof. John Foster)
Geostatistical modeling, Multivariate, Spatiotemporal modeling, Machine learning
Texas induced seismicity statistical analysis, statistical modeling in collaboration with the Bureau of Economic Geology of the Jackson School of Geosciences
Geostatistical groundwater modeling in Texas
Machine Learning for optimum and safe hydrofracturing for unconventional reservoirs in Texas
Started Ph.D. Fall 2018

Julian Salazar (Ph.D. student, cosupervised with Prof. Larry Lake)
New geostatistics, spatial data analytics, machine learning methods and workflows for unconventional reservoirs
New spatial data analytics and spatial statistics methods and workflows for geostatistical significance and trend modeling.
Started Ph.D. Fall 2018

Thamer Sulaimani (Ph.D. student, cosupervised with Prof. Wheeler)
Integration of physics into machine learning subsurface flow through porous media surrogate modeling.

Jose Hernandez (Ph.D. Student)
New geostatistics, spatial data analytics, machine learning methods and workflows for unconventional reservoirs
Novel methods to visualize and model flow through porous media with machine learning.
Started Ph.D. Fall 2019

Eduardo Maldonado (Ph.D. Student)
New workflows and methods for generalizable machine learning-based large-scale surrogate models for forecasting flow through porous media
Started Ph.D. Fall 2019

Midé Mabadeje (Ph.D. Student)
New data analytics and machine learning workflows to address various sources of spatial/subsurface bias that impact decision making
New workflows to use spatial data analytics to detect and automatically correct for spatial data sampling bias/clustered sampled
Started Ph.D. Fall 2019

Completed Graduate Students

Azor Nwachukwu (Ph.D. student, cosupervised with Prof. Larry Lake)
New subsurface machine learning methods and workflows for subsurface modeling and physics surrogate temporal forecasting with artificial neural networks and long-short term memory (LSTM), recurrent neural networks
Ph.D. defended Fall 2018 and hired by Halliburton

Summer Undergraduate Research Initiative (SURI) Students

Arham Junaid, The University of Texas at Austin
Principal components for inferential machine learning and dimensionality reduction interactive Python teaching tool in Jupyter Notebook with matplotlib and ipywidgets packages
Summer 2020

John McCarthy, The University of Texas at Austin
Artificial neural networks for predictive machine learning interactive Python teaching tool in Jupyter Notebook with matplotlib and ipywidgets packages
Summer 2020

Alan Sherman, Rice University
Lorenz coefficient, Ripley’s K and Ripley’s cross K functions for calculating and display in Python to add to GeostatsPy
Summer 2020

Jonathon Crammer, The University of Texas at Austin (cosupervised with George Pemberton, University of Alberta, Canada and Erin Pemberton, ConocoPhillips)
Data analysis, Statistics, Neurology, Biochemistry, Geology, Artificial intelligence, Cybernetics, Geospatial, Education psychology
Project on Modeling Degree of Bioturbation by Quantifying Spatial Features jointly with Dr. Erin Pemberton (ConocoPhillips) and Prof. George Pemberton (University of Alberta)
Summer 2018