A model‐based data‐driven dictionary learning for seismic data representation

Yarman, Can Evren; Kumar, Rajiv

doi:10.1111/1365-2478.12533

Cited by 11 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [12] the authors consider planar waves events recorded in a seismic array that can be represented as lines in the Fourier domain. However, in the real world, seismic events usually have curvature or amplitude variability, which means that their Fourier transforms are no longer strictly linear but rather occupy conic regions of the Fourier domain that are narrow at low frequencies but broaden at high frequencies, where the effect of curvature becomes more pronounced.…”

Section: Geophysics Petroleum Engineeringmentioning

confidence: 99%

Imaging Applications with Variable Projections

Pereyra¹,

Scherer²

2019

AJCM

View full text Add to dashboard Cite

We review two important fields of application for the method of Variable Projections (VARPRO): Seismic Prospecting and Medical Imaging. We cover the period since 2002 when a first review was published. Variable Projections is a method for the solution of nonlinear least squares problems where the model is a linear combination of nonlinear functions. Its success is based on the fact that the reduced functional, where the linear parameters are eliminated converges always faster than if the same method of solution is applied to the original problem. More importantly, many of these problems are very hard to solve in their original format and VARPRO has shown its value in many different applications.

show abstract

Section: Geophysics Petroleum Engineeringmentioning

confidence: 99%

Imaging Applications with Variable Projections

Pereyra¹,

Scherer²

2019

AJCM

View full text Add to dashboard Cite

show abstract

“…Unfortunately, when dealing with DAS recordings containing complex noise, researchers have difficulty in obtaining optimal filtering parameters, which leads to noise residuals and loss of amplitude of the effective signal. In addition, many other methods have been widely used in seismic data processing including singular value decomposition (SVD) (Oropeza and Sacchi, 2011), dictionary learning methods (Chen et al, 2016;Yarman et al, 2018;Wang and Ma, 2020), robust principal component analysis (RPCA) (Cheng et al, 2015;Liu et al, 2021), but the application of these methods in DAS data denoising is rarely reported. It is difficult for conventional methods to provide a better processing effect when the DAS data is seriously disturbed by noise, and give consideration to SNR and resolution.…”

Section: Introductionmentioning

confidence: 99%

Multi-scale interactive network in the application of DAS seismic data processing

Wang

Lin²,

Shao³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Distributed acoustic sensing (DAS) is regarded as a novel acquisition technology for seismic data. Compared with conventional electrical geophones, DAS has a series of obvious advantages including low-cost, high spatial resolution, good coverage, and strong resistance to the harsh environment. Noise attenuation is an essential step in seismic data processing. However, there are two main difficulties faced by the denoising task of DAS seismic data. On the one hand, some background noise in DAS seismic data, such as optical low-frequency noise, horizontal noise, and fading noise, is unique and not presented in the conventional seismic data; on the other hand, the signal-to-noise ratio (SNR) of DAS seismic data is relatively low. Recently, a convolutional neural network (CNN) has shown superior denoising performance compared to the traditional method. To follow this promising trend, we propose a multi-scale interactive convolutional neural network (MSI-Net) and apply it to denoise the challenging DAS seismic data. Different from most of the existing CNN architecture used in seismic data denoising, the MSI-Net considers both coarse-scale and fine-scale features by improving the inherent serial convolution to multi-scale parallel convolution, which is beneficial to recover detailed information. Moreover, we utilize some connections to achieve the information interaction between different scales, which promotes the flow of information and enables the network to extract more informative multi-scale features from the DAS seismic data. Moreover, both synthetic and real examples demonstrate that the proposed MSI-Net can effectively attenuate a variety of unique DAS background noise and also completely recover the weak signals. Compared with conventional CNN architecture, MSI-Net exhibits better performance in global SNR and local details.

show abstract

“…Unfortunately, obtaining optimal filtering parameters when processing field seismic records is often extremely dependent on manual experience, and errors in coefficient selection may even lead to severe noise residuals and signal leakage. In addition, other representative methods, including singular value decomposition (Oropeza & Sacchi, 2011), weighted nuclear norm minimization (Li et al., 2020), dictionary learning methods (Chen et al., 2016; Wang & Ma, 2020; Yarman et al., 2018) and robust principal component analysis (Cheng et al., 2015; Liu et al., 2021), have also been gradually used for field seismic data denoising and have achieved a good denoising effect. However, when applying the above methods to hydrophone data, we found that although these methods can achieve certain results in terms of denoising, none of the above methods are satisfactory in terms of signal recovery, which motivated us to seek new solutions.…”

Section: Introductionmentioning

confidence: 99%

Signal recovery and noise suppression of the Ocean‐Bottom Cable P‐component data based on improved dense convolutional network

Wang,

Lin,

Dong

et al. 2023

Geophysical Prospecting

View full text Add to dashboard Cite

Effective attenuation of noise in seismic data is important for high‐quality seismic imaging. Noise suppression in Ocean‐Bottom Cable data is particularly challenging. The challenge for the geophysicist is to process the individual hydrophone and vertical geophone data up to a level where they can conveniently be combined for effective multiple suppressions. In this study, we propose a deep learning‐based solution for noise attenuation and signal recovery of the P‐component of Ocean‐Bottom Cable data. To effectively attenuate complex noise, a denoising model based on dense convolutional network is proposed for Ocean‐Bottom Cable data processing. The backbone of the denoising network uses dense blocks to extract the potential features. Dense connections are applied to fuse the features at each stage to further enhance the effective information and thus improve the reconstruction of the signal. A high‐quality training set was built for the training network to ensure that the trained model was suitable for noise suppression. Synthesis and field experiments show that the proposed method can completely eliminate complex noise and recover weak signals from the P‐component data of the Ocean‐Bottom Cable data.

show abstract

A model‐based data‐driven dictionary learning for seismic data representation

Cited by 11 publications

References 50 publications

Imaging Applications with Variable Projections

Imaging Applications with Variable Projections

Multi-scale interactive network in the application of DAS seismic data processing

Signal recovery and noise suppression of the Ocean‐Bottom Cable P‐component data based on improved dense convolutional network

Contact Info

Product

Resources

About