Ground-roll Separation From Land Seismic Records Based on Convolutional Neural Network

TL;DR

This paper introduces a CNN-based method for separating ground-roll noise from land seismic data, improving upon traditional transform domain techniques by automatically learning features for effective noise removal.

Contribution

The paper presents a novel CNN approach that automatically learns to distinguish ground-roll from reflections, reducing the need for complex parameter tuning in traditional methods.

Findings

Effective separation of ground-roll demonstrated on synthetic data

Good generalization to real seismic data shown in experiments

Outperforms traditional transform-based filtering methods

Abstract

Ground-roll wave is a common coherent noise in land field seismic data. This Rayleigh-type surface wave usually has low frequency, low apparent velocity, and high amplitude, therefore obscures the reflection events of seismic shot gathers. Commonly used techniques focus on the differences of ground-roll and reflection in transformed domain such as $f-k$ domain, wavelet domain, or curvelet domain. These approaches use a series of fixed atoms or bases to transform the data in time-space domain into transformed domain to separate different waveforms, thus tend to suffer from the complexity for a delicate design of the parameters of the transform domain filter. To deal with these problems, a novel way is proposed to separate ground-roll from reflections using convolutional neural network (CNN) model based method to learn to extract the features of ground-roll and reflections automatically based on training data. In the proposed method, low-pass filtered seismic data which is contaminated by ground-roll wave is used as input of CNN, and then outputs both ground-roll component and low-frequency part of reflection component simultaneously. Discriminative loss is applied together with similarity loss in the training process to enhance the similarity to their train labels as well as the difference between the two outputs. Experiments are conducted on both synthetic and real data, showing that CNN based method can separate ground roll from reflections effectively, and has generalization ability to a certain extent.