Deep denoising autoencoder for seismic random noise attenuation

Saad, Omar M.; Chen, Yangkang

doi:10.1190/geo2019-0468.1

Cited by 210 publications

(74 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed algorithm has several advantages over the recently published DDAE method (Saad and Chen, 2020b): The architecture of proposed algorithm has skip connections, allowing the network to extract high‐order features while the DDAE does not have these skip connections. …”

Section: Methodsmentioning

confidence: 99%

“…However, DDAE does not have dropout layers. Patch technique is used in the proposed algorithm, avoiding the possibility of artefacts occurrence which happened in DDAE (Saad and Chen, 2020b) when inappropriate initial parameters are set. The DDAE is a semi‐unsupervised denoising algorithm.…”

Section: Methodsmentioning

confidence: 99%

“…Patch technique is used in the proposed algorithm, avoiding the possibility of artefacts occurrence which happened in DDAE (Saad and Chen, 2020b) when inappropriate initial parameters are set.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A fully unsupervised and highly generalized deep learning approach for random noise suppression

Saad

Chen

2021

Geophysical Prospecting

Self Cite

View full text Add to dashboard Cite

In this study, we proposed a deep learning algorithm (PATCHUNET) to suppress random noise and preserve the coherent seismic signal. The input data are divided into several patches, and each patch is encoded to extract the meaningful features. Following this, the extracted features are decompressed to retrieve the seismic signal. Skip connections are used between the encoder and decoder parts, allowing the proposed algorithm to extract high‐order features without losing important information. Besides, dropout layers are used as regularization layers. The dropout layers preserve the most meaningful features belonging to the seismic signal and discard the remaining features. The proposed algorithm is an unsupervised approach that does not require prior information about the clean signal. The input patches are divided into 80% for training and 20% for testing. However, it is interesting to find that the proposed algorithm can be trained with only 30% of the input patches with an effective denoising performance. Four synthetic and four field examples are used to evaluate the proposed algorithm performance, and compared to the f−x deconvolution and the f−x singular spectrum analysis. The results indicate the ability of the proposed algorithm in attenuating the random noise and preserving the seismic signal effectively despite the existence of a large amount of random noise, for example, when the input signal‐to‐noise ratio is as low as −14.2 dB.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A fully unsupervised and highly generalized deep learning approach for random noise suppression

Saad

Chen

2021

Geophysical Prospecting

Self Cite

View full text Add to dashboard Cite

show abstract

“…The machine learning-based technique has drawn a lot of attention from various kinds of fields, such as medical science, biomedical engineering, text processing, (electronic) commerce, internet engineering (Chan et al 2002;Vafeiadis et al 2015). In seismological community, machine learning has been successfully applied to noise attenuation (Chen et al 2019;Zhu et al 2019;Saad and Chen 2020), signal recognition (Huang 2019), earthquake detection (Jia et al 2019;Mousavi et al 2019b), arrival picking (Yu et al 2018;Zhu and Beroza 2018;Zhao et al 2019;Jiang and Ning 2019;Zhang et al 2020), fault detection (Ping et al 2018), geophysical inversion (Chen et al 2018;Wu et al 2020a), traveltime parameters estimation (Liu et al 2020b) and reservoir porosity prediction (Chen et al 2020). As one of the machine learning methods, deep learning is composed of multiple processing layers to intelligently extract data features, which can dramatically improve the state-of-the-art in various fields (Lecun et al 2015).…”

Section: Edited By Jie Hao and Xiu-qiu Pengmentioning

confidence: 99%

A deep learning network for estimation of seismic local slopes

et al. 2020

View full text Add to dashboard Cite

The local slopes contain rich information of the reflection geometry, which can be used to facilitate many subsequent procedures such as seismic velocities picking, normal move out correction, time-domain imaging and structural interpretation. Generally the slope estimation is achieved by manually picking or scanning the seismic profile along various slopes. We present here a deep learning-based technique to automatically estimate the local slope map from the seismic data. In the presented technique, three convolution layers are used to extract structural features in a local window and three fully connected layers serve as a classifier to predict the slope of the central point of the local window based on the extracted features. The deep learning network is trained using only synthetic seismic data, it can however accurately estimate local slopes within real seismic data. We examine its feasibility using simulated and real-seismic data. The estimated local slope maps demonstrate the successful performance of the synthetically-trained network.

show abstract

“…Particularly, some state-of-theart deep learning techniques have been widely applied in various seismic data problems, such as seismic noise attenuation (e.g. [21]- [24]), automatic seismic event picking (e.g. [25]- [27]) and seismic structure interpretation (e.g.…”

Section: Introductionmentioning

confidence: 99%

A Physics-Based Neural-Network Way to Perform Seismic Full Waveform Inversion

Ren

Yang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Seismic full waveform inversion is a common technique that is used in the investigation of subsurface geology. Its classic implementation involves forward modeling of seismic wavefield based on a certain type of wave equation, which reflects the physics nature of subsurface seismic wavefield propagation. However, obtaining a good inversion result using traditional seismic waveform inversion methods usually comes with a high computational cost. Recently, with the emerging popularity of deep learning techniques in various computer vision tasks, deep neural network (DNN) has demonstrated an impressive ability in dealing with complex nonlinear problems, including seismic velocity inversion. Now, extensive efforts have been made in developing a DNN architecture to tackle the problem of seismic velocity inversion, and promising results have been achieved. However, due to the dependence of a labeled dataset, i.e., the barely accessible true velocity model corresponding to real seismic data, the current supervised deep learning inversion framework may suffer from limitations on generalization. One possible solution to mitigate this issue is to impose the governing physics into this kind of purely data-driven method. Thus, following the procedures of traditional seismic full waveform inversion, we propose a seismic waveform inversion network, namely SWINet, based on wave-equation-based forward modeling network cells. By treating the single-shot observation data and its corresponding shot position as training data pairs, the inverted velocity model can be obtained as the trainable network parameters. Moreover, since the proposed seismic waveform inversion method is performed in a neural-network way, its implementation and inversion effect could benefit from some built-in tools in Pytorch, such as automatic differentiation, Adam optimizer and minibatch strategy, etc. Numerical examples indicate that the SWINet method may possess great potential in resulting a good velocity inversion effect with relatively fast convergence and lower computation cost. INDEX TERMS acoustic wavefield modeling, deep learning inversion, seismic waveform inversion

show abstract

Deep denoising autoencoder for seismic random noise attenuation

Cited by 210 publications

References 33 publications

A fully unsupervised and highly generalized deep learning approach for random noise suppression

A fully unsupervised and highly generalized deep learning approach for random noise suppression

A deep learning network for estimation of seismic local slopes

A Physics-Based Neural-Network Way to Perform Seismic Full Waveform Inversion

Contact Info

Product

Resources

About