LinkedInFeed

RGT Meets Deep Learning: Discover the Future of Geophysics

In this video, we explore an innovative research paper that presents a unified approach to the analysis of horizons and faults in seismic data through the application of deep learning. The paper introduces a volume-to-volume neural network, based on the UNet architecture, which estimates Relative Geologic Time (RGT) from seismic data. We will discuss the importance of RGT in determining the chronological sequence of geological events, and how this cutting-edge method employs multi-scale residual learning and attention mechanisms for efficient interpretation of geological structures in 3D seismic images. Join us as we examine the promising results and potential implications of this deep learning approach for the future of geophysics research. #DeepLearning #SeismicDataInterpretation #GeophysicsResearch
📓 Resources:
Deep Relative Geologic Time: A Deep Learning Method for Simultaneously Interpreting 3-D Seismic Horizons and Faults - https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2021JB021882
BE MY FRIEND:
🌎 My website/blog - https://ruslanmiftakhov.com/
🪢 LinkedIn - https://www.linkedin.com/in/ruslan-miftakhov/