A Self-Supervised Method Using Noise2Noise Strategy for Denoising CRP Gathers

Wang, Xiaokai; Fan, Siyuan; Zhao, Chen; Liu, Dawei; Chen, Wenchao

doi:10.1109/lgrs.2023.3285951

Cited by 3 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The generated pseudo-denoised shots were then paired with the original shots to train the DNN in the N2NE framework. We employed F-X deconvolution, a median filter, and a blind-trace network (Liu et al, 2023) as the conventional methods. To evaluate the enhanced denoising capability of the N2NE framework, we compared the results of conventional denoising methods with those achieved using the N2NE framework.…”

Section: Without Repeated Shot Acquisition Scenariomentioning

confidence: 99%

“…For the median filter implemented in the Python numerical analysis library SciPy (Virtanen et al, 2010), we adjusted the filter length in the temporal and spatial directions. In the blind-trace network (Liu et al, 2023), we used the same U-net architecture as in the N2NE framework (Figure 3).…”

Section: Appendices Appendix a Hyperparameter Search Of Conventional ...mentioning

confidence: 99%

“…This bias can significantly affect DNN denoising performance when applied to noisy raw data. Wang et al (2023) utilized high self-similarity in the horizontal direction of common reflection gathers following a normal move-out correction to generate a paired noisy dataset. Song et al (2023) proposed Shot2Shot (S2S) with a re-de-noising regularization method, which uses the pair of a shot gather and its neighboring shot gather for DNN training.…”

mentioning

confidence: 99%

“…The denoising ability of AEs has been demonstrated in seismic domains (Chen et al, 2019;Zhang et al, 2019b;Saad and Chen, 2020;Song et al, 2020). The blindspot strategy (Krull et al, 2019) has been proven to effectively attenuate random noise in seismic data in a self-supervised manner (Birine et al, 2021a(Birine et al, , 2021bLiu et al, 2023;Birine and Ravasi, 2024). Ma et al (2023) proposed an Attention Cycle GAN Network (ACGNet) for unpaired training, which was trained using a diverse hybrid training set that included both noisy and synthetically generated clean data.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Enhancing Seismic Noise Suppression Using the Noise2Noise Framework

Ozawa

2024

Preprint

View full text Add to dashboard Cite

Although supervised deep learning (DL) offers a potent solution for removing noise from seismic records, challenges are encountered owing to the scarcity of noise-free labels. The innovative Noise2Noise method eliminates the need for clean training targets and extends the applicability of deep learning to seismic data denoising. In this study, we introduce the Noise2Noise Enhancement (N2NE) framework, which improves upon the conventional noise reduction methods used in seismic processing. The applicability of this framework was quantitatively examined using actual field noise under two scenarios: with and without repeated shots. In scenarios with repeated shots, the N2NE framework enhances the conventional stacking method. In addition, the substack strategy, which employs smaller substacks for preliminary noise suppression before DL training, boosts noise suppression. In scenarios without repeated shots, the N2NE framework refines conventional denoising methods (F-X deconvolution) by utilizing information from the common-shot and receiver domains. The N2NE framework lays a foundation for future research on N2N-based seismic denoising methods and contributes to improving the quality of seismic records and the efficiency of data acquisition.

show abstract

Section: Without Repeated Shot Acquisition Scenariomentioning

confidence: 99%

Section: Appendices Appendix a Hyperparameter Search Of Conventional ...mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Enhancing Seismic Noise Suppression Using the Noise2Noise Framework

Ozawa

2024

Preprint

View full text Add to dashboard Cite

show abstract

An effective self-supervised learning method for attenuating various types of seismic noise

Cheng,

Jiang

et al. 2024

GEOPHYSICS

View full text Add to dashboard Cite

In real-world scenarios, the effectiveness of seismic denoising methods based on supervised learning (SL) is hindered by the scarcity of clean labeled data. A network trained on synthetic data often struggles to adapt to the distinct feature distributions of field data. To address this challenge, we develop an effective self-supervised learning strategy that effectively attenuates various types of seismic noise using a single denoising network model. Our approach starts with a warm-up phase that pre-trains the network on artificially noisier-noisy data pairs, enhancing its stability and ability to recognize specific noise characteristics. This is followed by an iterative data refinement phase, where the model iteratively refines its predictions, narrowing the gap between noisy inputs and clean data. Field-data tests demonstrate that the proposed method outperforms traditional SL techniques on random, backscattered, and blending noise.

show abstract

Robust seismic data denoising via self-supervised deep learning

Li,

Trad,

Liu

2024

GEOPHYSICS

View full text Add to dashboard Cite

Seismic data denoising is a critical component of seismic data processing, yet effectively removing erratic noise, characterized by its non-Gaussian distribution and high amplitude, remains a substantial challenge for conventional methods and deep learning (DL) algorithms. Supervised learning frameworks typically outperform others, but they require pairs of noisy datasets alongside corresponding clean ground truth, which is impractical for real-world seismic datasets. On the other hand, unsupervised learning methods, which do not rely on ground truth during training, often fall short in performance when compared to their supervised or traditional denoising counterparts. Moreover, current unsupervised deep learning methods fail to address the specific challenges posed by erratic seismic noise adequately. This paper introduces a novel zero-shot unsupervised DL framework designed specifically to mitigate random and erratic noise, with a particular emphasis on blending noise. Drawing inspiration from Noise2Noise and data augmentation principles, we present a robust self-supervised denoising network named “Robust Noiser2Noiser.”. Our approach eliminates the need for paired noisy and clean datasets as required by supervised methods or paired noisy datasets as in Noise2Noise (N2N). Instead, our framework relies solely on the original noisy seismic dataset. Our methodology generates two independent re-corrupted datasets from the original noisy dataset, using one as the input and the other as the training target. Subsequently, we employ a deep-learning-based denoiser, DnCNN, for training purposes. To address various types of random and erratic noise, the original noisy dataset is re-corrupted with the same noise type. Detailed explanations for generating training input and target data for blended data are provided in the paper. We apply our proposed network to both synthetic and real marine data examples, demonstrating significantly improved noise attenuation performance compared to traditional denoising methods and state-of-the-art unsupervised learning methods.

show abstract

A Self-Supervised Method Using Noise2Noise Strategy for Denoising CRP Gathers

Cited by 3 publications

References 14 publications

Enhancing Seismic Noise Suppression Using the Noise2Noise Framework

Enhancing Seismic Noise Suppression Using the Noise2Noise Framework

An effective self-supervised learning method for attenuating various types of seismic noise

Robust seismic data denoising via self-supervised deep learning

Contact Info

Product

Resources

About