Improving seismic fault detection by super-attribute-based classification

Abstract

Fault interpretation is one of the routine processes used for subsurface structure mapping and reservoir characterization from 3D seismic data. Various techniques have been developed for computer-aided fault imaging in the past few decades; for example, the conventional methods of edge detection, curvature analysis, red-green-blue rendering, and the popular machine-learning methods such as the support vector machine (SVM), the multilayer perceptron (MLP), and the convolutional neural network (CNN). However, most of the conventional methods are performed at the sample level with the local reflection pattern ignored and are correspondingly sensitive to the coherent noises/processing artifacts present in seismic signals. The CNN has proven its efficiency in utilizing such local seismic patterns to assist seismic fault interpretation, but it is quite computationally intensive and often demands higher hardware configuration (e.g., graphics processing unit). We have developed an innovative scheme for improving seismic fault detection by integrating the computationally efficient SVM/MLP classification algorithms with local seismic attribute patterns, here denoted as the super-attribute-based classification. Its added values are verified through applications to the 3D seismic data set over the Great South Basin (GSB) in New Zealand, where the subsurface structure is dominated by polygonal faults. A good match is observed between the original seismic images and the detected lineaments, and the generated fault volume is tested usable to the existing advanced fault interpretation tools/modules, such as seeded picking and automatic extraction. It is concluded that the improved performance of our scheme results from its two components. First, the SVM/MLP classifier is computationally efficient in parsing as many seismic attributes as specified by interpreters and maximizing the contributions from each attribute, which helps minimize the negative effects from using a less useful or “wrong” attribute. Second, the use of super attributes incorporates local seismic patterns into training a fault classifier, which helps exclude the random noises and/or artifacts of distinct reflection patterns.

A comparison of seismic saltbody interpretation via neural networks at sample and pattern levels

“…The benefits of such pattern‐level classification on seismic interpretation, including improved noise robustness and reduced computational resources, are comprehensively demonstrated in Di et al . ().…”

Transformer assisted dual U-net for seismic fault detection

“…Therefore, many fault detection methods are proposed to enhance those discontinuities using some seismic attributes including the semblance, coherence and curvature (Marfurt et al, 1998;Marfurt et al, 1999;Roberts, 2001). To pursue better performance, more improved approaches are proposed including the ant tracking and attributes fused methods (Pedersen et al, 2002;Di et al, 2019;Yuan et al, 2020;Acuña-Uribe et al, 2021;Yuan et al, 2022), but the results still rely heavily on the experience of interpreters and the quality of the seismic attributes used. Moreover, the presence of noise in seismic images can negatively impact the accuracy of fault detection.…”

Salt structure identification based on U-net model with target flip, multiple distillation and self-distillation methods

“…On seismic images, the geometrical, steep sides of the salt structure, seismic wave propagation and velocity pattern analyses are fundamental salt structure identification methods (Jones and Davison, 2014;Asgharzadeh et al, 2018;Shahbazi et al, 2020). Considering the physical property differences among the salt and the surrounding sediment layers, methods to classify salt structure boundaries have been adopted e.g., seismic attribution extraction (Di et al, 2019a;2019b). Salt-structure detection has been aided by machinelearning methods development, including normalized full gradient machines (Soleimani et al, 2018), the oriented gradients histogram combined with support vector machines (Hosseini-Fard et al, 2022) and mostly, convolution neural networks (CNNs) (Di et al, 2018;Gramstad and Nickel, 2018;Karchevskiy et al, 2018).…”