An unsupervised learning approach to deblend seismic data from denser shot coverage surveys

Wang, Kunxi; Hu, Tianyue; Wang, Shangxu

doi:10.1093/gji/ggac222

Cited by 9 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2022) use iterative inversion and a multi‐resolution U‐Net to take advantage of the multiscale nature of seismic data. Deep neural network–based approaches can also be used for gradient denoising in iterative schemes, both in a supervised (K. Wang, Mao, et al., 2022; K. Wang & Hu, 2022) and in an unsupervised (K. Wang, Hu, et al., 2022) fashion.…”

Section: Introductionmentioning

confidence: 99%

Focal deblending: Marine data processing experiences

Kontakis

Verschuur

2023

Geophysical Prospecting

View full text Add to dashboard Cite

In contrast to conventional acquisition practices, simultaneous source acquisition allows for overlapping wavefields to be recorded. Relaxing the shot schedule in this manner has certain advantages, such as allowing for faster acquisition and/or denser shot sampling. This flexibility usually comes at the cost of an extra step in the processing workflow, where the wavefields are deblended, that is, separated. An inversion‐type algorithm for deblending, based on the focal transform, is investigated. The focal transform uses an approximate velocity model to focus seismic data. The combination of focusing with sparsity constraints is used to suppress blending noise in the deblended wavefield.The focal transform can be defined in different ways to better match the spatial sampling of different types of marine surveys. To avoid solving a large inverse problem, involving a large part of the survey simultaneously, the input data can be split into sub‐sets that are processed independently. We discuss the formation of such sub‐sets for ocean bottom node and streamer‐type acquisitions. Two deblending experiments are then carried out. The first is on numerically blended ocean bottom node field data. The second is on field‐blended towed streamer data with a challenging signal overlap. The latter experiment is repeated using curvelet‐based deblending for comparison purposes, showing the virtues of the focal deblending process. Several challenges of basing deblending around the focal transform are discussed as well as some suggestions for improved implementations.

show abstract

Section: Introductionmentioning

confidence: 99%

Focal deblending: Marine data processing experiences

Kontakis

Verschuur

2023

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…The method can solve the problem of missing the label data and training data sets. Wang et al (2022c) propose an iterative inversion method based on the unsupervised DNN to deblend the simultaneous-source data from a denser shot coverage survey, which can also solve the problem of missing training data sets.…”

Section: Introductionmentioning

confidence: 99%

A multi‐data training method for a deep neural network to improve the separation effect of simultaneous‐source data

Wang

Mao

Song

et al. 2022

Geophysical Prospecting

Self Cite

View full text Add to dashboard Cite

Within the field of seismic data acquisition with active sources, the technique of acquiring simultaneous data, also known as blended data, offers operational advantages. The preferred processing of blended data starts with a step of deblending, that is separation of the data acquired by the different sources, to produce data that mimic data from a conventional seismic acquisition and can be effectively processed by standard methods. Recently, deep learning methods based on the deep neural network have been applied to the deblending task with promising results, in particular using an iterative approach. We propose an enhancement to deblending with an iterative deep neural network, whereby we modify the training stage of the deep neural network in order to achieve better performance through the iterations. We refer to the method that only uses the blended data as the input data as the general training method. Our new multi-data training method allows the deep neural network to be trained by the data set with the input patches composed of blended data, noisy data with low amplitude crosstalk noise, and unblended data, which can improve the ability of the deep neural network to remove crosstalk noise and protect weak signal. Based on such an extended training data set, the multi-data training method embedded in the iterative separation framework can result in different outputs at different iterations and converge to the best result in a shorter iteration number. Transfer learning can further improve the generalization and separation efficacy of our proposed method to deblend the simultaneous-source data. Our proposed method is tested on two synthetic data and two field data to prove the effectiveness and superiority in the deblending of the simultaneous-source data compared with the general training method, generic noise attenuation network and low-rank matrix factorization methods.

show abstract

Self-supervised Multistep Seismic Data Deblending

Chen,

Wang

2023

Surv Geophys

View full text Add to dashboard Cite

An unsupervised learning approach to deblend seismic data from denser shot coverage surveys

Cited by 9 publications

References 47 publications

Focal deblending: Marine data processing experiences

Focal deblending: Marine data processing experiences

A multi‐data training method for a deep neural network to improve the separation effect of simultaneous‐source data

Self-supervised Multistep Seismic Data Deblending

Contact Info

Product

Resources

About