Ground Roll Suppression using Convolutional Neural Networks

TL;DR

This paper introduces a novel approach using convolutional neural networks and generative adversarial networks to effectively detect and suppress ground roll noise in pre-stack seismic data, outperforming traditional filtering methods.

Contribution

The paper presents a new deep learning-based method for ground roll suppression in seismic data, demonstrating improved performance and discussing model generalization to different geological settings.

Findings

CNN-based ground roll detection outperforms traditional filters.

Generative adversarial networks effectively suppress ground roll noise.

Proposed metrics provide reliable evaluation of suppression quality.

Abstract

Seismic data processing plays a major role in seismic exploration as it conditions much of the seismic interpretation performance. In this context, generating reliable post-stack seismic data depends also on disposing of an efficient pre-stack noise attenuation tool. Here we tackle ground roll noise, one of the most challenging and common noises observed in pre-stack seismic data. Since ground roll is characterized by relative low frequencies and high amplitudes, most commonly used approaches for its suppression are based on frequency-amplitude filters for ground roll characteristic bands. However, when signal and noise share the same frequency ranges, these methods usually deliver also signal suppression or residual noise. In this paper we take advantage of the highly non-linear features of convolutional neural networks, and propose to use different architectures to detect ground roll in shot gathers and ultimately to suppress them using conditional generative adversarial networks. Additionally, we propose metrics to evaluate ground roll suppression, and report strong results compared to expert filtering. Finally, we discuss generalization of trained models for similar and different geologies to better understand the feasibility of our proposal in real applications.