Invited Talk
ML-based workflow to enhance seismic fault interpretation in OBN seismic data
Matheus Nilo · Invited Speaker
Abstract
In this work, I propose deep learning approaches that can be successfully applied to the challenge of fault interpretation in pre-salt seismic data. I first review some conventional seismic interpretation methods and deep learning-based methods. Next, I propose a workflow for synthetic data generation. Following a description of convolutional neural networks and how these models are trained, I analyze and evaluate model performance. Finally, I present application in field examples and discuss their merits from a qualitative perspective.
Speaker Bio
Matheus Nilo is an invited speaker at AIEPS 2026 and will present in hybrid format.
Materials and Images
- Slides: To be added.
- Related links: To be added.
- Images: To be added.