By Topic

An efficient technique for lithology classification

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
El-Sheikh, Talaat S. ; Dept. of Electron. & Commun., Cairo Univ., Giza, Egypt ; Syiam, M.M.

An efficient technique for the computer classification of lithologies is presented that utilizes well logs. For this study, a training data set has been obtained from a key well in the Abu-Garadig field area in the Western Desert of Egypt. The true classification of the training data is determined from the core description of the key well. Suboptimal feature selection techniques are used for the selection of the effective features containing most of the discriminatory information from a given set of measurements. The nearest-neighbor rule is used for classification after the editing and condensing of the training set in feature space. The classification rate, using all training patterns, is slightly higher than the rate obtained by using instead the condensed training set. The lithology classifier is used in other wells in the same field. The resulting classification rate demonstrates that the output lithologies are in accordance with geological reference

Published in:

Geoscience and Remote Sensing, IEEE Transactions on  (Volume:27 ,  Issue: 5 )