Contents

This repository contains publically available data for the Inventors Program sprint for Fall 2019

• WTI oil price data - EIA
• Oil production data - EIA
• Refinery production - EIA
• Refinery capacity - EIA
• Imports and Exports - EIA
• Oil consumption - EIA
• Economic indicators (GDP, vehicle sales, etc.) -U.S. Bureau of Economic Analysis

2019 Inventors Program

NSC 323 - Inventors Program Unique I.D.: NSC 323 45749

Principal Investigator: Michael Pyrcz

Research Educator: Jesse Pisel

Course Objectives

You will gain:

1. Experience with working with energy datasets
2. Understanding of the role of data analytics, geostatistics and machine learning for energy applications (subsurface and above surface).
3. Expert knowledge of methods, workflows and decisions in data analytics, geostatistics and machine learning, and the theoretical and practical considerations, and limitations over the various stages:
   • Data Analysis and Statistics
   • Estimation and Simulation
   • Uncertainty Characterization
   • Decision Making
4. Expert knowledge of the fundamental algorithms and some ability to customize for advanced workflows.
5. Understand current practice limitations and new opportunities for advancement of geostatistics.

Prerequisites: None

MEETS: TTH 9:00-10:30 AM PMA(RLM) 7.116

INSTRUCTOR: Jesse Pisel

Suggested References:

Geostatistics:

• Pyrcz, M.J., and Deutsch, C.V.,2014, Geostatistical Reservoir Modeling. Oxford University Press.
• Jensen, J. R., Lake, L. W., Corbett P. M. W., and Goggin, D. J., 2000, Statistics for Petroleum Engineers and Geoscientists, Elsevier.

Statistics / Statistical Modeling:

• Dekking, F. M., Kraaikamp, C., Lopuhaa, H. P., and Meester L. E., 2007, A Modern Introduction to Probability and Statistics Understanding Why and How. Springer-Verlag.
• James, G., Witten, D., Hastie, T., Tibshirani, R., 2013, An Introduction to Statistical Learning with Applications in R, Springer.

Additional Instructional Materials

The instructor will distribute field examples in the class or on the course website.

Want to Work Together?

I hope that this is helpful to those that want to learn more about energy analytics, geostatistics, subsurface modeling, geology, and machine learning.

Want to invite us to visit your company for training, mentoring, project review, workflow design and consulting, we would be happy to drop by and work with you!

Interested in partnering, supporting graduate student research or the Subsurface Data Analytics and Machine Learning consortium (co-PIs including Profs. Foster, Torres-Verdin and van Oort)? Our 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!

WTI Crude Oil Price Prediction

To view the final results of the sprint project, view the Jupyter notebook titled "WTI Crude Oil Price Prediction". The "Sprint - Data Munging" notebook was the initial exploration and testing, and does not include documentation of code. Refer to the "WTI Crude Oil Price Prediction" notebook for an understanding of methodologies and code.