S2S-WTV: Seismic Data Noise Attenuation Using Weighted Total Variation Regularized Self-Supervised Learning

• URL: http://arxiv.org/abs/2212.13523v1
• Date: Tue, 27 Dec 2022 15:36:09 GMT
• Title: S2S-WTV: Seismic Data Noise Attenuation Using Weighted Total Variation Regularized Self-Supervised Learning
• Authors: Zitai Xu, Yisi Luo, Bangyu Wu, Deyu Meng
• Abstract summary: We propose a self-supervised method that combines the capacities of deep denoiser and the generalization abilities of hand-crafted regularization for seismic data random noise attenuation. Our method, dubbed as S2S-WTV, enjoys both high representation abilities brought from the self-supervised deep network and good generalization abilities of the hand-crafted WTV regularizer.
• Score: 37.3794830249412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Seismic data often undergoes severe noise due to environmental factors, which seriously affects subsequent applications. Traditional hand-crafted denoisers such as filters and regularizations utilize interpretable domain knowledge to design generalizable denoising techniques, while their representation capacities may be inferior to deep learning denoisers, which can learn complex and representative denoising mappings from abundant training pairs. However, due to the scarcity of high-quality training pairs, deep learning denoisers may sustain some generalization issues over various scenarios. In this work, we propose a self-supervised method that combines the capacities of deep denoiser and the generalization abilities of hand-crafted regularization for seismic data random noise attenuation. Specifically, we leverage the Self2Self (S2S) learning framework with a trace-wise masking strategy for seismic data denoising by solely using the observed noisy data. Parallelly, we suggest the weighted total variation (WTV) to further capture the horizontal local smooth structure of seismic data. Our method, dubbed as S2S-WTV, enjoys both high representation abilities brought from the self-supervised deep network and good generalization abilities of the hand-crafted WTV regularizer and the self-supervised nature. Therefore, our method can more effectively and stably remove the random noise and preserve the details and edges of the clean signal. To tackle the S2S-WTV optimization model, we introduce an alternating direction multiplier method (ADMM)-based algorithm. Extensive experiments on synthetic and field noisy seismic data demonstrate the effectiveness of our method as compared with state-of-the-art traditional and deep learning-based seismic data denoising methods.

Related papers

• DREMnet: An Interpretable Denoising Framework for Semi-Airborne Transient Electromagnetic Signal [10.676243830905754]
  The SATEM method is capable of conducting rapid surveys over large-scale and hard-to-reach areas. Traditional denoising techniques rely on parameter selection strategies, which are insufficient for processing field data in noisy environments. We propose an interpretable decoupled representation learning framework, termed DREMnet, that disentangles data into content and context factors.
  arXiv  Detail & Related papers  (2025-03-28T08:13:23Z)
• Triply Laplacian Scale Mixture Modeling for Seismic Data Noise Suppression [51.87076090814921]
  Sparsity-based tensor recovery methods have shown great potential in suppressing seismic data noise. We propose a novel triply Laplacian scale mixture (TLSM) approach for seismic data noise suppression.
  arXiv  Detail & Related papers  (2025-02-20T08:28:01Z)
• Self-supervised learning for denoising quasiparticle interference data [0.0]
  Tunneling spectroscopy is an important tool for the study of correlated electron systems. Machine learning provides techniques to reduce the noise in post-processing. We adapt the unsupervised Noise2Noise and self-supervised Noise2Self algorithms, which allow for denoising without clean examples.
  arXiv  Detail & Related papers  (2024-09-13T15:06:51Z)
• A convolutional neural network approach to deblending seismic data [1.5488464287814563]
  We present a data-driven deep learning-based method for fast and efficient seismic deblending. A convolutional neural network (CNN) is designed according to the special character of seismic data. After training and validation of the network, seismic deblending can be performed in near real time.
  arXiv  Detail & Related papers  (2024-09-12T10:54:35Z)
• Learning with Noisy Foundation Models [95.50968225050012]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets. We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Explainable Artificial Intelligence driven mask design for self-supervised seismic denoising [0.0]
  Self-supervised coherent noise suppression methods require extensive knowledge of the noise statistics. We propose the use of explainable artificial intelligence approaches to see inside the black box that is the denoising network. We show that a simple averaging of the Jacobian contributions over a number of randomly selected input pixels, provides an indication of the most effective mask.
  arXiv  Detail & Related papers  (2023-07-13T11:02:55Z)
• Realistic Noise Synthesis with Diffusion Models [68.48859665320828]
  Deep image denoising models often rely on large amount of training data for the high quality performance. We propose a novel method that synthesizes realistic noise using diffusion models, namely Realistic Noise Synthesize Diffusor (RNSD) RNSD can incorporate guided multiscale content, such as more realistic noise with spatial correlations can be generated at multiple frequencies.
  arXiv  Detail & Related papers  (2023-05-23T12:56:01Z)
• Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling [22.525679742823513]
  We present a learnability enhancement strategy to reform paired real data according to noise modeling. Our strategy consists of two efficient techniques: shot noise augmentation (SNA) and dark shading correction (DSC)
  arXiv  Detail & Related papers  (2022-07-13T10:23:28Z)
• Towards Adversarially Robust Deep Image Denoising [199.2458715635285]
  This work systematically investigates the adversarial robustness of deep image denoisers (DIDs) We propose a novel adversarial attack, namely Observation-based Zero-mean Attack (sc ObsAtk) to craft adversarial zero-mean perturbations on given noisy images. To robustify DIDs, we propose hybrid adversarial training (sc HAT) that jointly trains DIDs with adversarial and non-adversarial noisy data.
  arXiv  Detail & Related papers  (2022-01-12T10:23:14Z)
• Capturing scattered discriminative information using a deep architecture in acoustic scene classification [49.86640645460706]
  In this study, we investigate various methods to capture discriminative information and simultaneously mitigate the overfitting problem. We adopt a max feature map method to replace conventional non-linear activations in a deep neural network. Two data augment methods and two deep architecture modules are further explored to reduce overfitting and sustain the system's discriminative power.
  arXiv  Detail & Related papers  (2020-07-09T08:32:06Z)
• Learning Model-Blind Temporal Denoisers without Ground Truths [46.778450578529814]
  Denoisers trained with synthetic data often fail to cope with the diversity of unknown noises. Previous image-based method leads to noise overfitting if directly applied to video denoisers. We propose a general framework for video denoising networks that successfully addresses these challenges.
  arXiv  Detail & Related papers  (2020-07-07T07:19:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.