ResACEUnet: An Improved Transformer Unet Model for 3D Seismic Fault Detection

• Published in: Journal of geophysical research. Machine learning and computation Vol. 1; no. 3
• Main Authors: Zu, Shaohuan, Zhao, Penghui, Ke, Chaofan, Junxing, Cao
• Format: Journal Article
• Language: English
• Published: 01.09.2024
• Subjects: deep learning; fault detection; semantic segmentation; transformer; Unet
• ISSN: 2993-5210; 2993-5210
• DOI: 10.1029/2024JH000232

Detecting fault constitutes a pivotal aspect of seismic interpretation, significantly influencing the outcomes of petroleum and gas exploration. As artificial intelligence advances, convolutional neural network (CNN) has proven effective in detecting faults in seismic interpretation. Nevertheless, the receptive field of a convolutional layer within CNN is inherently limited, focusing on extracting local features, which lead to the detection of fewer and discontinuous fault features. In this study, integrating the local feature extraction capabilities of CNN with the global feature extraction prowess of transformer, we proposed a U‐shaped hybrid architecture model named ResACEUnet (Attention‐Convolution Unet with Efficient block) to detect fault of three‐dimensional (3D) seismic data. In ResACEUnet, we introduced a module called ACE block, which integrates convolution and attention mechanisms. This module enabled the model to simultaneously extract local features and model global contextual information, capturing more accurate fault features. In addition, we utilized a joint loss function named BCEDice loss, which composed of BCE (binary cross‐entropy) loss and dice loss to tackle the challenge of imbalanced positive and negative samples. The model was trained on a synthetic data set, with a range of data augmentation techniques were employed to bolster its generalization capabilities and robustness. We implemented our proposed method on the offshore F3 seismic data from the Netherlands and seismic data from Kerry3D and Parihaka in New Zealand. Compared to conventional popular models such as Unet, ResUnet, and SwinUnetR, ResACEUnet demonstrated superior capabilities in capturing more features and identifying fault with higher accuracy and continuity. Plain Language Summary We introduced an end‐to‐end neural network that can directly interpret 3D seismic fault from seismic data without manual processing. This model adopts a U‐shaped architecture, combining the strengths of CNN and transformer, to learn more fault features and improve the accuracy of fault identification. We train the network using synthetic data set, which is generated by convolving random faults, folds, and noise added to reflectivity models with Ricker wavelets. Our model not only exhibits good predictive performance on synthetic data but also effectively captures fault features on multiple different publicly available real data. The identification results of three field‐realistic seismic data demonstrate the model's predictive performance and generalization capabilities. Key Points Introduce an improved transformer Unet model for detecting 3D seismic fault The integration of convolutional neural network with transformer architectures empowers the model to discern and harness an expanded array of fault attributes We have demonstrated the feasibility of our method on real field data