Multitask learning for local seismic image processing: fault detection, structure-oriented smoothing with edge-preserving, and seismic normal estimation by using a single convolutional neural network

• Published in: Geophysical journal international Vol. 219; no. 3; pp. 2097 - 2109
• Main Authors: Wu, Xinming, Liang, Luming, Shi, Yunzhi, Geng, Zhicheng, Fomel, Sergey
• Format: Journal Article
• Language: English
• Published: 01-12-2019
• ISSN: 0956-540X; 1365-246X
• DOI: 10.1093/gji/ggz418

Summary
Fault detection in a seismic image is a key step of structural interpretation. Structure-oriented smoothing with edge-preserving removes noise while enhancing seismic structures and sharpening structural edges in a seismic image, which, therefore, facilitates and accelerates the seismic structural interpretation. Estimating seismic normal vectors or reflection slopes is a basic step for many other seismic data processing tasks. All the three seismic image processing tasks are related to each other as they all involve the analysis of seismic structural features. In conventional seismic image processing schemes, however, these three tasks are often independently performed by different algorithms and challenges remain in each of them. We propose to simultaneously perform all the three tasks by using a single convolutional neural network (CNN). To train the network, we automatically create thousands of 3-D noisy synthetic seismic images and corresponding ground truth of fault images, clean seismic images and seismic normal vectors. Although trained with only the synthetic data sets, the network automatically learns to accurately perform all the three image processing tasks in a general seismic image. Multiple field examples show that the network is significantly superior to the conventional methods in all the three tasks of computing a more accurate and sharper fault detection, a smoothed seismic volume with better enhanced structures and structural edges, and more accurate seismic normal vectors or reflection slopes. Using a Titan Xp GPU, the training processing takes about 8 hr and the trained model takes only half a second to process a seismic volume with $128\, \times \, 128\, \times \, 128$ image samples.