Poster at Asia Petroleum Geoscience Conference & Exhibition 2022
Written by Support
Cameron, G.H. and Vestrum, R.W., 2022, Convolutional neural networks to augment PSDM velocity model building, APGCE Conference, Kuala Lumpur, Malaysia
- Built convolutional neural network (CNN) to estimate TTI PSDM velocity models from shot gathers
- Traditional automated methods for PSDM velocity estimation in complex-structure land areas are unstable, so we rely on the human understanding of the geology to build geologic models
- The goal is to use machine learning to supplement human learning
- Field-data example shows imaging improvements on certain shallow reflectors, which shows the potential of the method
Leave a Reply
You must be logged in to post a comment.