Deep Learning for Migration Artifacts Attenuation

Migrated images are often contaminated by uncompensated migration swings. While it is easy to visually distinguish the artifacts, it is often hard to remove them without damaging the image resolution. Here we propose a method for attenuation of migration artifacts that is based on a deep convolutional neural network. The network is trained on synthetic examples to predict clean seismic images from noisy migration results. Application to field data demonstrates the potential of the method to distinguish between migration swings and structural data, and successfully attenuate the artifacts.