Abstract: Data Analytics and Machine Learning for Energy Geoscience and Engineering

Every energy company that I visit is interested in growing internal capabilities to add value with data analytics and machine learning. Energy has a long history of working with large, complicated geoscience and engineering datasets and there is a growing toolbox of old and new emerging data-driven methods available that may offer improved efficiency and potentially new insights from vast and complicated subsurface datasets. This talk is an opportunity to link subsurface data analytics and machine learning to fundamental concepts from probability, statistics, geoscience and engineering and to provide an enthusiastic, but at times critical perspective on what we may expect in the data-driven science revolution.

Every energy company that I visit is interested in growing internal capabilities to add value with data analytics and machine learning. Energy has a long history of working with large, complicated geoscience and engineering datasets and there is a growing toolbox of old and new emerging data-driven methods available that may offer improved efficiency and potentially new insights from vast and complicated subsurface datasets. This talk is an opportunity to link subsurface data analytics and machine learning to fundamental concepts from probability, statistics, geoscience and engineering and to provide an enthusiastic, but at times critical perspective on what we may expect in the data-driven science revolution.

Distinguished Lecturer

Michael J.

Michael J. Pyrcz

The University of Texas at Austin

Video Presentation

Contacts

Adriane Hausher Programs Coordinator
Susie Nolen Programs Team Leader +1 918 560 2634