Title:  Computational Seismic Interpretation using Geometric Representation and Tensor-based Texture Analysis

Committee:

Dr. Ghassan AlRegib, ECE, Chair , Advisor

Dr. James McClellan, ECE

Dr. Faramarz Fekri, ECE

Dr. Zhigang Peng, EAS

Dr. Mohamed A. Deriche, King Fahd University

Abstract:

In this dissertation, we design a framework that interactively delineates important geological structures such as faults and salt domes in seismic volumes. Within the seismic volume, we divide seismic sections into two classes, reference and predicted ones. In reference sections, we implement interpreter-assisted workflows that delineate faults and salt domes using their geometric representations and texture features. Then, we introduce automated tracking workflows that delineate target structures in predicted sections by tracking corresponding labeled results in reference sections through the seismic volume. To ensure accurate tracking, we extract features along geological structures using tensor-based subspace learning methods. Experimental results on real seismic data sets show that our interactive interpretation framework outperforms state-of-the-art methods in terms of accuracy and efficiency.