Random noise attenuation based on residual learning of deep convolutional neural network

Si, Xu; Yuan, Yijun

doi:10.1190/segam2018-2985176.1

Cited by 20 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, after learning and extracting features from high signal‐to‐noise ratio (SNR) seismic data labels, it is difficult for the neural network to output better results than the labeled. The second category generates labels by creating synthetic data (Si and Yuan, 2018; Jin et al ., 2018; Zhao et al ., 2018). The advantage of this category is that the labels are completely clean.…”

Section: Introductionmentioning

confidence: 99%

“…It can obtain valuable information from the data by learning the abstract representation in the form of combination of multiple layers (LeCun et al ., 2015). Currently, label‐based machine learning approaches have been successfully applied to suppress seismic data noise (Zhao et al ., 2018; Liu et al ., 2019; Zhang et al ., 2019b; Si and Yuan, 2018; Liu et al ., 2018; Jin et al ., 2018). According to the strategy for generating labels, these approaches can mainly be divided into two categories.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Seismic noise attenuation by signal reconstruction: an unsupervised machine learning approach

Gao

Zhao²,

et al. 2021

Geophysical Prospecting

View full text Add to dashboard Cite

Random noise attenuation is an essential step in seismic data processing for improving seismic data quality and signal‐to‐noise ratio. We adopt an unsupervised machine learning approach to attenuate random noise via signal reconstruction strategy. This approach can be accomplished in the following steps: Firstly, we randomly mute a part of the input data of the neural network according to a certain percentage, and then the network outputs the reconstructed data influenced by this randomly mute. The objective function measures the distance between the input data and the reconstructed data. Secondly, we use the adaptive moment estimation algorithm to minimize the distance, and the network adjusts its internal parameters so that sparse representations can be captured by the multiple processing layers of the neural network. Finally, we take the same proportion of random mute on the raw seismic data which are fed to the trained neural network. Through this network, reconstruction of seismic data and attenuation of random noise are completed simultaneously. We use both synthetic and field data to testify the feasibility and applicability of the proposed method. Synthetic data experiment indicates that the proposed method achieves better denoised results than the conventional methods. Field data applications further demonstrate its superiority and practicality.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Seismic noise attenuation by signal reconstruction: an unsupervised machine learning approach

Gao

Zhao²,

et al. 2021

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…Deep learning enables the extraction of hidden features by learning the low-level features of data, which can then be used for prediction or classification [33,34]. Thus, deep-learning algorithms [35,36] facilitate seismic random noise attenuation based on data-driven approaches. Most deeplearning methods are based on supervised learning [37] and unsupervised learning [38].…”

Section: Introductionmentioning

confidence: 99%

Seismic Random Noise Attenuation Using a Tied-Weights Autoencoder Neural Network

Zhou

Guo

2021

Minerals

View full text Add to dashboard Cite

Random noise is unavoidable in seismic data acquisition due to anthropogenic impacts or environmental influences. Therefore, random noise suppression is a fundamental procedure in seismic signal processing. Herein, a deep denoising convolutional autoencoder network based on self-supervised learning was developed herein to attenuate seismic random noise. Unlike conventional methods, our approach did not use synthetic clean data or denoising results as a training label to build the training and test sets. We directly used patches of raw noise data to establish the training set. Subsequently, we designed a robust deep convolutional neural network (CNN), which only depended on the input noise dataset to learn hidden features. The mean square error was then evaluated to establish the cost function. Additionally, tied weights were used to reduce the risk of over-fitting and improve the training speed to tune the network parameters. Finally, we denoised the target work area signals using the trained CNN network. The final denoising result was obtained after patch recombination and inverse operation. Results based on synthetic and real data indicated that the proposed method performs better than other novel denoising methods without loss of signal quality loss.

show abstract

“…After convolutional neural networks (CNNs) were introduced, various noise attenuation methods based on the CNN architecture have been proposed (Jian and Seung, 2009;Gordonara, 2016;Lefkimmiatis, 2017), and the denoising convolutional neural network (DnCNN) suggested by Zhang et al (2017) attained good results in random noise suppression in natural images. The DnCNN was applied to attenuate various types of noise from seismic data such as ground roll (Li et al, 2018) from onshore field prestack seismic data and random noise from synthetic prestack seismic data (Si and Yuan, 2018) and three-dimensional field seismic cubes (Liu et al, 2018). The DnCNN uses residual learning (He et al, 2016) and has the advantage of minimizing damage to the seismic signal by estimating the noise from seismic data rather than directly analyzing the signal.…”

Section: Introductionmentioning

confidence: 99%

Random Noise Attenuation of Sparker Seismic Oceanography Data with Machine Learning

Jun¹,

Jou²,

Kim³

et al. 2020

Preprint

View full text Add to dashboard Cite

Abstract. Seismic oceanography (SO) acquires water column reflections by seismic exploration compensating for the drawbacks of conventional physical oceanographic equipment. Most SO studies obtain data using air guns, which have relatively low-frequency bands. For higher-frequency bands at a low exploration cost, using a smaller seismic exploration system, such as a sparker source with a shorter receiver length, would be an alternative. However, the sparker source has a relatively low energy and consequently produces data with a low signal-to-noise (S / N) ratio. To solve the problem of the low S / N ratio of sparker SO data, we applied machine learning. The purpose of this study is to attenuate the random noise in the East Sea sparker SO data without distorting the true shape and amplitude of water column reflections. A denoising convolutional neural network (DnCNN) that successfully suppresses random noise in a natural image is adopted as the machine learning network architecture. One of the most important factors of machine learning is the generation of an appropriate training dataset. We have generated two different training datasets using synthetic and field data. Models trained with the different training datasets are applied to the test data, and the denoised results are quantitatively compared. The trained models are applied to the target seismic data, i.e., the East Sea sparker water column seismic reflection data, and the denoised seismic sections are evaluated. The results show that machine learning can successfully attenuate the random noise of sparker water column seismic reflection data.

show abstract

Random noise attenuation based on residual learning of deep convolutional neural network

Cited by 20 publications

References 8 publications

Seismic noise attenuation by signal reconstruction: an unsupervised machine learning approach

Seismic noise attenuation by signal reconstruction: an unsupervised machine learning approach

Seismic Random Noise Attenuation Using a Tied-Weights Autoencoder Neural Network

Random Noise Attenuation of Sparker Seismic Oceanography Data with Machine Learning

Contact Info

Product

Resources

About