To attend, please RSVP to epp@cseg.ca.
Unless we have exceeded the allowable number of people for the auditorium, we will not be replying to your email.
LunchBox Geophysics is free! Simply bring your own lunch (refreshments provided) and enjoy.
Abstract
In supervised deep neural networks (DNNs), the seismic-to-rock property relationship is learned from the data. One of the major factors limiting the success of these methods is whether there exists enough labelled well data to train the neural network adequately. To overcome this issue, we generate synthetic data. The resulting collection of pseudo-well logs and synthetic seismic data, called the synthetic catalog, is used to train the DNN. Several case histories are shown using this methodology. Jon Downton is a Senior Research Advisor with CGG GeoSoftware. His current research is on machine learning and reservoir characterization. Jon has over 35 years of experience and a Ph.D. from the University of Calgary.
