Automated Geological Features Detection in 3D Seismic Data Using Semi-Supervised Learning

Abstract

A geological interpretation plays an important role to gain 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. We propose a semi-supervised learning technique to automatically and accurately delineate the geological features from 3D seismic data. To generate labeling data for training the supervised Convolutional Neural Network (CNN) model, we propose an efficient workflow based on unsupervised learning. This workflow utilized seismic attributes and KernelPCA to enhance the visualization of geological targets and clustering the features into binary classes using K-means approach. With this workflow, we are able to develop a data-driven model and reduce human subjectivity. We applied this technique in two cases with different geological settings. The synthetic data and the real seismic investigation from the A Field in the Malay Basin. From this application, we demonstrate that our CNN-based model is highly accurate and consistent with the previous manual interpretation in both cases. In addition to qualitatively evaluating the interpretations, we further extract the predicted result into a 3D geobody. This result could help the interpreter focus on tasks requiring human expertise and aid the model’s prediction in the next studies.

Semi-Supervised Training for (Pre-Stack) Seismic Data Analysis

“…Geological feature detection [6] Post-stack CNN DSSL Binary classification Facies classification [9] Post-stack DNN DSSL Muticlass classification Facies classification [42] Pre-stack (indirect use) Deep autoencoder DSSL Muticlass classification Facies identification [43] Post-stack CNN DSSL Muticlass classification Gas-bearing prediction [10] Pre-stack CNN DSSL Binary classification Fault detection [20] Post-stack CNN Supervised Binary classification Salt bodies classification [21] Post-stack CNN Supervised Binary classification Gas chimney detection [23] Pre-stack MPL Supervised Binary classification Porosity prediction [27] Pre-stack CNN Supervised Estimation…”

“…Labeled data are essential for improving the performance and generalization of supervised deep learning algorithms in real-world problems. Different domains, such as healthcare [1,2], natural language processing (NLP) [3,4], and reservoir characterization [5,6], are significantly affected, due to privacy concerns and the need for expert annotations; labeling is also time-consuming and rather costly. However, there is a large amount of unlabeled data available in these domains: medical records, images, and genetic information in healthcare [7,8], and 3D seismic data in reservoir characterization [9,10].…”

“…Recently, there has been active research in training DSSL models for reservoir characterization. For example, Pratama [6] detected the presence of channels or non-channels with a CNN using 3D post-stack seismic data. Seismic facies were classified from elastic features by Asghar [9] using a DNN and with deep autoencoders by Liu [42].…”

Seismic Image Identification and Detection Based on Tchebichef Moment Invariant

“…In addition to supervised learning approaches, several studies have also explored the utilization of unsupervised learning methods for detecting geological features. For instance, principal component analysis [45], K-means clustering [46], a self-organizing map (SOM) [47], and a convolutional autoencoder [48] have been employed in these studies.…”

Artificial Intelligence Applications in Petroleum Exploration and Production

“…Pratama and Latiff [9] conducted automated geological feature detection in 3D seismic data using semi-supervised learning. It was demonstrated that the proposed convolutional neural network (CNN)-based model is highly accurate and consistent with the previous manual interpretation in both cases with the synthetic data and the real seismic investigation from the A Field in the Malay Basin.…”