SPE Online Education
What To Do When Data Is Scarce: Data Augmentation for Drilling Data
Recorded On: 05/28/2020
The success of machine learning in areas like computer vision, speech recognition and text mining has attracted the attention of other problem domains. In particular, drilling automation has had a significant increase in the application of machine learning during the last five years. An important aspect to consider for the use of a machine learning approach is the data availability. Techniques like deep learning require a considerable amount of data. Unfortunately, drilling data is not always available at the required volume. For this case, it is possible to increase the quantity of data by means of data augmentation. In this talk, we will describe what is data augmentation and some available methods. We will focus on a couple of techniques which could be useful for augmenting drilling data. A use case will be present to show how it could be applied to drilling data.
All content contained within this webinar is copyrighted by Dr. Francisco Ocegueda-Hernandez and its use and/or reproduction outside the portal requires express permission from Dr. Francisco Ocegueda-Hernandez.
Dr. Francisco Ocegueda-Hernandez
Senior Machine Learning Scientist, NOV
Dr. Ocegueda-Hernandez is senior machine learning scientist at NOV, where Francisco performs research in drilling automation. He holds a Ph.D. in computer science from the University of Houston. His research interests are in machine learning and artificial intelligence applied to drilling automation. He has experience in applying machine learning in various fields including computer vision, physics, astronomy and drilling.
SPE Webinars are FREE to members courtesy of the