Noise-robust detection and tracking of salt domes in postmigrated volumes using texture, tensors, and subspace learning

Abstract

The identification of salt-dome boundaries in migrated seismic data volumes is important for locating petroleum reservoirs. The presence of noise in the data makes computer-aided salt-dome interpretation even more challenging. We have developed noise-robust algorithms that could label boundaries of salt domes effectively and efficiently. Our research is twofold. First, we used a texture-based gradient to accomplish salt-dome detection. We found that by using a dissimilarity measure based on the 2D discrete Fourier transform, the algorithm was capable of efficiently detecting salt-dome boundaries with accuracy. At the same time, our analysis determined that the proposed algorithm was robust to noise. Once the detection is performed for an initial 2D seismic section, we track the initial boundaries through the data volume to accomplish an efficient labeling process by avoiding the parameter tuning that would have been necessary if detection had been performed for every seismic section. The tracking process involves a tensor-based subspace learning process, in which we built texture tensors using patches from different seismic sections. To accommodate noise components with various levels in a texture tensor, we used noise-adjusted principal component analysis, so that principal components corresponding to greater signal-to-noise-ratio values might be selected for tracking. We validated our detection and tracking algorithms through experiments using seismic data sets acquired from the Netherlands offshore F3 block in the North Sea with very encouraging results.

Subsurface Structure Analysis Using Computational Interpretation and Learning: A Visual Signal Processing Perspective

“…Similarly, [27] takes advantage of active contour to track salt-dome boundaries in neighboring seismic sections. More recently, Wang et al [5] have proposed a salt-dome tracking method that extracts the features of salt-dome boundaries in reference sections using tensor-based subspace learning and delineates tracked boundaries by finding points in predicted sections, which are the most similar to reference ones. Fig.…”

Structure label prediction using similarity-based retrieval and weakly supervised label mapping

“…In recent years, there has been a significant interest in machine learning-based techniques for various seismic interpretation applications such as salt body delineation, fault and fracture detection, horizon extraction, and facies classification (e.g., Coléou et al, 2003;Barnes and Laughlin, 2005;Wang et al, 2015a;Guillen et al, 2015;Zhao et al, 2015;Wang et al, 2015b;Figueiredo et al, 2015;Qi et al, 2016;Ramirez et al, 2016;Lin et al, 2017). Supervised machine learning has proven to be one of the most successful machine learning paradigms.…”

A High-Speed, Real-Time Vision System for Texture Tracking and Thread Counting

“…To design a fast and robust vision system for an automatic sewing machine, Book et al [3] proposed a prototype in 1 This work was partially supported by a Walmart Foundation grant (#1806K45). which the concept of thread-count was first introduced.…”