Search

Deghosting of marine seismic data is an important and challenging step in the seismic processing flow. We describe a novel approach to train a supervised convolutional neural network to perform joint source and receiver deghosting of single‐component (hydrophone) data. The training dataset is generated by demigration of stacked depth migrated images into shot gathers with and without ghosts using the actual source and receiver locations from a real survey. To create demigrated data with ghosts, we need an estimate of the depth of the sources and receivers and the reflectivity of the sea surface. In the training process, we systematically perturbed these parameters to create variability in the ghost timing and amplitude and show that this makes the convolutional neural network more robust to variability in source/receiver depth, swells and sea surface reflectivity. We tested the new method on the Marmousi synthetic data and real North Sea field data and show that, in some respects, it performs better than a standard deterministic deghosting method based on least‐squares inversion in the τ‐p domain. On the synthetic data, we also demonstrate the robustness of the new method to variations in swells and sea‐surface reflectivity. [ABSTRACT FROM AUTHOR]

Ghost reflections from the free surface distort the source signature and generate notches in the seismic amplitude spectrum. For this reason, removing ghost reflections is essential to improve the bandwidth and signal‐to‐noise ratio of seismic data. We have developed a novel approach that involves training a convolutional neural network to remove source and receiver ghosts from marine dual‐component data. High‐quality training data is essential for the network to produce accurate predictions on real data. We have used the demigration of a stacked depth‐migrated image to create training shot gathers. Demigrated pressure and vertical velocity data are used to train the network. We apply the trained network on real pressure and vertical velocity data with ghosts. The network's output may be either source deghosting and receiver deghosting, or both. We test our method on synthetic Marmousi and real North Sea data with dual‐component streamers. The method is compared with conventional dual‐component deghosting using the summation of pressure and vertical velocity. Results show that the method can accurately remove the ghosts with only minor errors in synthetic data. Based on a decimation test, the method is less affected by spatially aliased data than a conventional method, which could benefit data with high frequencies and/or large receiver or cable separations. On real data, the results show consistency with conventional deghosting, both within and outside the training area. This indicates that the method is a viable alternative to conventional methods on real data. [ABSTRACT FROM AUTHOR]

Regularization and interpolation of 3D offset classes prior to imaging are an important and challenging step in the marine seismic data processing flow. Here we describe how to perform this task using a deep neural network, and we explain how to overcome the challenge of creating a suitable training data set. The training data set is generated by de‐migrating stacked pre‐stack depth migration images. For each offset class volume, we de‐migrate the pre‐stack depth migrated stacked image into two configurations: (i) the original survey configuration consisting of the recorded source/receiver positions and (ii) an 'Ideal' survey configuration with constant offset and azimuth for each 3D offset class. The training creates a 3D convolutional encoder–decoder model that will regularize and interpolate seismic data. The convolutional encoder–decoder is trained on 3D sliding windows in each 3D offset cube to map from (i) to (ii), i.e. to map the original survey configuration with irregular and sparse sampling into the fully sampled regular offset cubes suitable for offset‐based migration, such as Kirchhoff migration. Such migration algorithms rely on regular and sufficiently dense sampling to achieve constructive interference to image the structures and destructive interference to suppress migration noise. We test the new method on one synthetic and one field data example and show that it performs better than a standard regularization/interpolation method based on anti‐leakage Fourier transform, especially for the smallest offset classes. On the synthetic data, we also demonstrate that the convolutional encoder–decoder method preserves the amplitude versus offset as well as the standard method. [ABSTRACT FROM AUTHOR]