About This Item

Share This Item

The AAPG/Datapages Combined Publications Database

Houston Geological Society Bulletin


The Houston Geological Society Bulletin
Vol. 61 (2018), No. 4. (December), Page 19

Abstract: The Future of Artificial Intelligence (AI) Applications in Geology

Edward R. Jones1

The Previous HitscienceNext Hit of geology has a long history. It forms the basis for traditional geological metrics, such as predicting oil production from shale wells from geologic and completion rate parameters. In the past, calculations were driven from first-order geological principles developed using physical models. In some cases, these relationships were developed from established linear regression models.

Nowadays geologists are learning to make use of more advanced techniques originally developed for Artificial Intelligence applications, and now modified for solving geological and petroleum problems. These include cluster analysis, artificial neural networks, decision trees text mining, and many resampling methods such as random forests and ensemble models.

This talk describes the cross-over between some of the AI algorithms and modern geological metrics. The techniques are described in the contest of AI and then illustrated using problems associated with forecasting oil production from geological and well attributes.

Biographical Sketch

Dr. Jones is currently Executive Professor of Statistics at Texas A&M University and Academic Director of the MS Analytics Degree. In that capacity, he teaches data mining and text analytics, and provides expertise in business analytics and quality assurance to Fortune 500 Companies. His clients include the Department of Treasury, Chevron, IBM, Motorola, and Texas Instruments.

He received a PhD degree in Statistics from Virginia Tech and a BS in Previous HitComputerNext Hit Previous HitScienceNext Hit from Texas A&M University – Commerce. He also has hands on experience developing statistical and data mining software for companies in Silicon Valley and IMSL, the International Mathematical and Statistics Library.

He has taught Previous HitcomputerTop programming and has extensive experience programming in Python, SAS, Java and C.

Acknowledgments and Associated Footnotes

1 Edward R. Jones: Academic Director of MS Analytics Program, Texas A&M University

Copyright © 2018 by HGS (Houston Geological Society)