Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
9826509 | Journal of Petroleum Science and Engineering | 2005 | 12 Pages |
Abstract
The neural network architectures were designed using a trial-and-error technique. Initially, a constructive design was employed by adding complexity to the architecture in terms of increasing the number of input variables as well as the number of hidden layers and nodes. A technique based on conventional statistical parameters was developed to numerically describe the patterns observed in log crossplots. These numerical descriptions were then prioritized and used as neural network inputs to be correlated with known production response.
Related Topics
Physical Sciences and Engineering
Earth and Planetary Sciences
Economic Geology
Authors
William W. “Bill” Weiss, Jason W. Weiss, Visveswaran “Vishu” Subramaniam, Xina Xie,