AUTOMATED GEOLOGICAL INTERPRETATION IN 3D SEISMIC DATA USING SEMI-SUPERVISED LEARNING

A geological interpretation plays an important role in gaining information about the structural and stratigraphic of hydrocarbon reservoirs. However, this is a time consuming
task due to the complexity and size of seismic data. Recently, the growth of computing power has enabled the application of Artificial Intelligence and Deep Learning models in service of studying many geoscience challenges, including the
prediction of geological features in seismic data. Although, the Deep Learning model relies on two aspects, including the dataset size and the hyperparameter selection. This research proposed a semi-supervised machine learning method which combined unsupervised technique to gather and build the dataset and supervised technique named Convolutional Neural Network (CNN) to automatically and accurately delineate the geological features from 3D seismic data. A new enhanced workflow based on unsupervised learning has been designed to generate labelling data for the training model.