*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Dr. Zhigang Peng
Summary Sentence: A seminar by Dr. Ghassan AlRegib, School of Earth and Atmospheric Sciences
Full Summary: No summary paragraph submitted.
Ghassan AlRegibThe School of Earth and Atmospheric Sciences Presents Dr. Ghassan AlRegib, School of Electrical and Computer Engineering, Georgia Institute of Technology
Seismic Interpretation Using Machine Learning Approaches: Recent Advances and Future Directions
In this talk, I will summarize the major and most recent advances in the field of machine learning and the most successful applications of such data-driven approaches in solving problems that relate to seismic interpretation. I will emphasize the recent interest in using deep learning for seismic interpretation tasks, such as facies classification and inversion for elastic impedance. For such applications to be successful, a large publicly available annotated datasets for training and testing models is needed.
However, such data does not exist yet in our community. As a result, researchers have often resorted to some shortcuts that, in some cases, pose more serious challenges for the advancement of the field within our community. The talk will address such challenges and propose a few ways to overcome some of these obstacles. Specifically, the talk will focus on facies classification, structure labeling, and inversion.
Finally, the talk will conclude with listing a few best practices to truly utilize deep learning to advance the field of seismic interpretation.
