Graduate class at the University of Texas at Austin, from the syllabus:
“You will get the opportunity to learn theory and practice geostatistical reservoir modeling, data analytics and machine learning in a simulated subsurface asset team. As a result, you will gain the practical skills to integrate and better impact reservoir modeling in any company dealing with spatial / subsurface datasets.”
You will gain:
- understanding of the role of reservoir modeling and the reservoir modeler within a subsurface asset development team.
- expert knowledge of methods, workflows and decisions in reservoir modeling, and the theoretical and practical considerations, and limitations over the various stages: a. Spatial Data Analytics and Statistics b. Spatial Estimation and Simulation c. Spatial Machine Learning (brief) d. Uncertainty Characterization e. Decision Making
- Expert knowledge of the fundamental algorithms and workflows and the ability to build custom subsurface advanced workflows.
- Understand current practice limitations and new opportunities for advancement of geostatistics.
Novel Data Analytics, Geostatistics and Machine Learning Subsurface Solutions
With over 17 years of experience in subsurface consulting, research and development, Michael has returned to academia driven by his passion for teaching and enthusiasm for enhancing engineers' and geoscientists' impact in subsurface resource development.
For more about Michael check out these links:
Come and join us as we learn more about subsurface data analytics, modeling and statistical / machine learning.
-
The Lectures: During the term I will record the lectures and place them on YouTube.
-
The Project: There is a dataset for you to work with, or use your own.
-
Updates: check out our project updates as we work through this term-long subsurface modeling project.
-
Opensource: work in Jupyter Notebook with workflow development in Python.
-
GeostatsPy: GSLIB++ functionality in Python for great, efficient experiential learning.
-
Professional Communicaton: class is conducted like a subsurface asset team with myself as the subsurface asset team lead. Practice professional communication, oral and written reporting.
To get started, check out these course resources and begin your journey.
-
The Recorded Lectures are available at Course Lectures on YouTube
-
The Hands-on Demos are available in this repository Coure Workflows and Demonstrations GitHub
-
Project Updates, written project updates available here Written Updates and Oral Updates.
An example dataset, similar to the ones provided to the project teams in the class is available in this repository.
-
0_sample_data.csv - comma delimited well data with X and Y coordinates (meters), Facies 0 and 1 (1 is sandstone and 0 interbedded sand and mudstone), Porosity (fraction), permeability as Perm (mDarcy) and acoustic impedance as AI (kg/m2s*10^6).
-
0_AI.csv - 2D comma delimited array with acoustic impedance (kg/m2s*10^6) at 10 m cell resolution over the area of itnerest X [0,1000m] and Y [0,1000m].
This class has no examination! No quizes! No multiple guess! Students will demonstrate their mastery through regular project updates (every two weeks). This includes short written (yes, PowerPoint is not enough) updates with:
- Executive Summary
- Workflow
- Results
- Recommendations
They will also provide oral reports to the rest of the asset team. An oppornity for searching questions and consensus building for the team.
Updates will continue to be shared as a we proceed:
- recorded oral presentation on YouTube Oral Updates
- update report in .pdf in this repository Written Updates
Here's my first recorded oral and written update for basic univariate and spatial analysis of dataset 12:
Update 1, Univariate and Spatial - Oral Presentation
Update 1, Univariate and Spatial - Written Report
Hands-on demos for experiential learning are being added all the time. Here's some of them:
-
Working with Pandas DataFrames for tabular data DataFrames Demo
-
Working with NumPy ndarrays for gridded data ndarrays Demo
-
Univariate Data Distributions Distributions Demo
-
Plotting Spatial Data Spatial Data Demo
I hope you join us in my PGE 383: Subsurface Modeling class. We have about 40 graduate students from engineering and geoscience participating here at the University of Texas at Austin. The Jackson School of Geosciences offered a new classroom in their building after we outgrew our room in the Petroleum and Geosystems engineering department. I appreciate the excellent support from both the Hidebrand Department of Petroleum and Geosystems Engineering and the Jackson School of Geosciences.
I hope that this is helpful to those that want to learn more about subsurface modeling, data analytics and machine learning. Students and working professionals are welcome to participate.
-
Want to invite me to visit your company for training, mentoring, project review, workflow design and consulting, I'd be happy to drop by and work with you!
-
Interested in partnering, supporting my graduate student research or my Subsurface Data Analytics and Machine Learning consortium (co-PIs including Profs. Foster, Torres-Verdin and van Oort)? My research combines data analytics, stochastic modeling and machine learning theory with practice to develop novel methods and workflows to add value. We are solving challenging subsurface problems!
-
I can be reached at mpyrcz@austin.utexas.edu.
I'm always happy to discuss,
Michael
Michael Pyrcz, Ph.D., P.Eng. Associate Professor The Hildebrand Department of Petroleum and Geosystems Engineering, Bureau of Economic Geology, The Jackson School of Geosciences, The University of Texas at Austin