The new process involves training the program at selected locations on the volume using measured well log curves. Emerge determines which combination of attributes are best used to predict a given parameter at these known locations, and then applies that combination of attributes to the entire seismic volume. A validation analysis is performed to ensure the program has not over trained the given data set. Two independent methods can be used in the prediction process: weighted convolutional sum (derived from the covariance matrix) and artificial neural networks (ANN). More from Hampson on http://www.hampson-russell.com.
Click here to
comment on this article
If your browser does not work with the MailTo button, send mail to firstname.lastname@example.org with PDM_V_2.0_199812_18 as the subject.
© Oil IT Journal - all rights reserved.