Graph Neural Network Approach for Seismic Fault Delineation
Explore a cutting-edge Graph Neural Network-based method for fault delineation in seismic data, leveraging Graph Total Variation and Multigraph technologies for enhanced accuracy and efficiency. Discover how this advanced approach automates fault detection in seismic data, transforming manual processes in industries dealing with earthquake-related faults.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
A Graph Neural Network Based Approach For Fault Delineation In Seismic Data Using Graph Total Variation And Multigraph Patitapaban Palo, Aurobinda Routray Department of Electrical Engineering, IIT Kharagpur Ritesh Chandra Tewari ATDC, IIT Kharagpur
Introduction A fault caused by earthquakes is highly nonlinear and nonuniform, and fault delineation is still done manually in many industries. Deep learning models used for automatic fault detection FaultNet3D Patch classification Multi-attribute SVM Attributes based CNN Graph neural networks (GNNs) have been successfully used for link prediction and graph classification. Multigraph GCN (MGCN) Multigraph chebnet Graph total variation (TV)
Methods synthetic data ? ? = ? ? ? ? + n t s(t) seismic trace w(t) the wavelet r(t) the reflectivity series n(t) the noise
Methods Graph Total Variation Function TVGs = | s ?????? |1& ?????= Chebyshev GCN Input ? ?? ??? normalized symmetric graph Laplacian ? = ? ? scaling ? Chebyshev expansion ??? = 2??? 1? ?? 2(?) mapped onto the Chebyshev ? = ?0 ? ?,?1 ? ?,?2 ? ? Approximate convolution is defined as ? = ?? Multi-Graph Convolutional Network ??,?= ?? ?1?? ?2? Y = ?0,0, ?0,1, , ??,?, , ?? 1,? 1 1 ?????
Dataset Krishna Godavari Basin, Bay of Bengal, India Seismic data consist of seismic amplitude values Synthetic Data ? ? = ? ? ? ? + ?(?) Training dataset has 10000 for each fault and non-fault data Validation dataset contains 2000 for each fault and non-fault data Testing dataset has 10000
