A self-supervised scheme for ground roll suppression

TL;DR

This paper introduces a self-supervised method using blind-fan networks to effectively suppress complex aliased ground roll noise in seismic data without needing clean training data.

Contribution

It adapts self-supervised denoising techniques specifically for ground roll suppression, addressing a challenge not handled by existing methods.

Findings

Effectively attenuates aliased ground roll in synthetic data

Successfully applied to field seismic data

Does not require clean labeled data for training

Abstract

In recent years, self-supervised procedures have advanced the field of seismic noise attenuation, due to not requiring a massive amount of clean labeled data in the training stage, an unobtainable requirement for seismic data. However, current self-supervised methods usually suppress simple noise types, such as random and trace-wise noise, instead of the complicated, aliased ground roll. Here, we propose an adaptation of a self-supervised procedure, namely, blind-fan networks, to remove aliased ground roll within seismic shot gathers without any requirement for clean data. The self-supervised denoising procedure is implemented by designing a noise mask with a predefined direction to avoid the coherency of the ground roll being learned by the network while predicting one pixel's value. Numerical experiments on synthetic and field seismic data demonstrate that our method can effectively attenuate aliased ground roll.