The use of machine learning algorithms have become more commonplace throughout different industries in recent years. Geoscientists have had some success in implementing machine learning algorithms to automate seismic facies classification. In this study, we use a random forest learning algorithm to predict seismic lithofacies aided by wireline logs and stratigraphical interpretation. The random forest algorithm is a tree-based classifier which is commonly used as an alternative toneural-network and support vector machine based algorithms.
The aim of the study is to apply a random forest learning algorithm to classify seismic facies and determine the importance of each attribute in classifying seismic facies (i.e. sensitivity). The determination of attribute importance will help to choose the input attribute and reduce the amount of computations needed. The predicted facies using a random forest algorithm thoroughly define the Lime and Shale facies in a Barnett shale survey.
Presentation Date: Tuesday, October 16, 2018
Start Time: 9:20:00 AM
Location: Poster Station 1
Presentation Type: Poster
