As a process that identifies geologic structures of interest such as faults, salt domes, or elements of petroleum systems in general, seismic structural interpretation depends heavily on the domain knowledge and experience of interpreters as well as visual cues of geologic structures, such as texture and geometry. With the dramatic increase in size of seismic data acquired for hydrocarbon exploration, structural interpretation has become more time consuming and labor intensive. By treating seismic data as images rather than signal traces, researchers have been able to utilize advanced image-processing and machine-learning techniques to assist interpretation directly. In this paper, we mainly focus on the interpretation of two important geologic structures, faults and salt domes, and summarize interpretation workflows based on typical or advanced image-processing and machine-learning algorithms. In recent years, increasing computational power and the massive amount of available data have led to the rise of deep learning. Deep-learning models that simulate the human brain's biological neural networks can achieve state-of-the-art accuracy and even exceed human-level performance on numerous applications. The convolutional neural network — a form of deep-learning model that is effective in analyzing visual imagery — has been applied in fault and salt dome interpretation. At the end of this review, we provide insight and discussion on the future of structural interpretation.

Depicting geologic sequences from 3D seismic surveying is of significant value to subsurface reservoir exploration, but it is usually time- and labor-intensive for manual interpretation by experienced seismic interpreters. We have developed a semisupervised workflow for efficient seismic stratigraphy interpretation by using the state-of-the-art deep convolutional neural networks (CNNs). Specifically, the workflow consists of two components: (1) seismic feature self-learning (SFSL) and (2) stratigraphy model building (SMB), each of which is formulated as a deep CNN. Whereas the SMB is supervised by knowledge from domain experts and the associated CNN uses a similar network architecture typically used in image segmentation, the SFSL is designed as an unsupervised process and thus can be performed backstage while an expert prepares the training labels for the SMB CNN. Compared with conventional approaches, the our workflow is superior in two aspects. First, the SMB CNN, initialized by the SFSL CNN, successfully inherits the prior knowledge of the seismic features in the target seismic data. Therefore, it becomes feasible for completing the supervised training of the SMB CNN more efficiently using only a small amount of training data, for example, less than 0.1% of the available seismic data as demonstrated in this paper. Second, for the convenience of seismic experts in translating their domain knowledge into training labels, our workflow is designed to be applicable to three scenarios, trace-wise, paintbrushing, and full-sectional annotation. The performance of the new workflow is well-verified through application to three real seismic data sets. We conclude that the new workflow is not only capable of providing robust stratigraphy interpretation for a given seismic volume, but it also holds great potential for other problems in seismic data analysis.

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.

Salt bodies are important subsurface structures with significant implications for hydrocarbon accumulation and sealing in offshore petroleum reservoirs. This study presents an unsupervised workflow for delineating the surface of salt bodies from three-dimensional (3D) seismic surveying based on a multi-attribute $$k$ $-means cluster analysis. The workflow consists of four steps. First, a suite of seismic attributes are selected and computed from the volume of original seismic amplitude, each of which separates the target salt boundaries from the surrounding non-boundary seismic features in its unique way. Second, two sets of representative samples are manually picked in an interpreter-specified vertical section to help initialize the centers of the boundary and non-boundary clusters. Third, the $$k$ $-means cluster analysis is performed on the seismic attributes to generate a clustering model for volumetric processing. Finally, applying the built $$k$ $-means model to every sample in the seismic volume provide us with a probability volume, in which the high values indicate the presence of salt-dome boundaries. The effectiveness of the proposed method is verified for interpreting the multiple salt bodies in the F3 seismic dataset over the Netherlands North Sea, and the generated salt-boundary volume can serve as input for more advanced salt interpretation, such as salt surface/body extraction, to assist structural framework modeling in the subsalt zones of high geologic complexities and petroleum potentials. We conclude that the proposed workflow paves the way for computer-aided seismic interpretation in a more comprehensive manner by incorporating more advanced machine learning algorithms (e.g. artificial neural network) and targeting other important seismic structures (e.g. fault).