FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation

By Xinming Wu, Luming Liang, Yunzhi Shi, Sergey Fomel. Geophysics, 2019

712 citations recorded by the source corpus.

Delineating faults from seismic images is a key step for seismic structural interpretation, reservoir characterization, and well placement. In conventional methods, faults are considered as seismic reflection discontinuities and are detected by calculating attributes that estimate reflection continuities or discontinuities. We consider fault detection as a binary image segmentation problem of labeling a 3D seismic image with ones on faults and zeros elsewhere. We have performed an efficient image-to-image fault segmentation using a supervised fully convolutional neural network. To train the network, we automatically create 200 3D synthetic seismic images and corresponding binary fault labeling images, which are shown to be sufficient to train a good fault segmentation network. Because a binary fault image is highly imbalanced between zeros (nonfault) and ones (fault), we use a class-balanced binary cross-entropy loss function to adjust the imbalance so that the network is not trained or converged to predict only zeros. After training with only the synthetic data sets, the network automatically learns to calculate rich and proper features that are important for fault detection. Multiple field examples indicate that the neural network (trained by only synthetic data sets) can predict faults from 3D seismic images much more accurately and efficiently than conventional methods. With a TITAN Xp GPU, the training processing takes approximately 2 h and predicting faults in a [Formula: see text] seismic volume takes only milliseconds.

Subfields: Geophysics, Mechanical Engineering, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/4d29d0eb1e2b68990762885ce7a604bb7e73173a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Geophysics

In Mechanical Engineering

In Ocean Engineering

Citations in the corpus

Machine learning in acoustics: Theory and applications. (2019, methodology): “121, a 3D U-net was applied to detect or segment faults from a 3D seismic images.”
Deep-learning seismology (2022, background): “…for structural-interpretation tasks such as automatic identification of geological channels ( 57 ), bright spots ( 58 ), collapsed karst features ( 59 ), scatterers ( 60 ), bottom-simulating reflections ( 61 ), salt bodies ( 62 ), horizons ( 63 , 64 ), and faults ( 65 – 67 ) in seismic images.”
Deep learning for denoising (2018, background): “…determination and pattern detection (Huang et al., 2006), facies-classification (Ross and Cole, 2017), detecting faults (Huang et al., 2017; Zhao and Mukhopadhyay, 2018; Guo et al., 2018; Wu et al., 2018, 2019), channels (Pham et al., 2019) and salt bodies (Shi et al., 2018), among others.”
Deep Learning for Geophysics: Current and Future Trends (2021, methodology): “Third, if the synthetic datasets are sufficiently complicated, that is, if the most important factors are considered when generating the datasets, the trained network may be able to process realistic datasets directly (Wu et al., 2020; Wu, Liang, et al., 2019).”