Self-supervised multi-stage deep learning network for seismic data denoising
Seismic data denoising is a critical process usually applied at various stages of the seismic processing workflow, as our ability to mitigate noise in seismic data affects the quality of our subsequent analyses. However, finding an optimal balance between preserving seismic signals and effectively r...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2025-06-01
|
| Series: | Artificial Intelligence in Geosciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266654412500019X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850164028142256128 |
|---|---|
| author | Omar M. Saad Matteo Ravasi Tariq Alkhalifah |
| author_facet | Omar M. Saad Matteo Ravasi Tariq Alkhalifah |
| author_sort | Omar M. Saad |
| collection | DOAJ |
| description | Seismic data denoising is a critical process usually applied at various stages of the seismic processing workflow, as our ability to mitigate noise in seismic data affects the quality of our subsequent analyses. However, finding an optimal balance between preserving seismic signals and effectively reducing seismic noise presents a substantial challenge. In this study, we introduce a multi-stage deep learning model, trained in a self-supervised manner, designed specifically to suppress seismic noise while minimizing signal leakage. This model operates as a patch-based approach, extracting overlapping patches from the noisy data and converting them into 1D vectors for input. It consists of two identical sub-networks, each configured differently. Inspired by the transformer architecture, each sub-network features an embedded block that comprises two fully connected layers, which are utilized for feature extraction from the input patches. After reshaping, a multi-head attention module enhances the model’s focus on significant features by assigning higher attention weights to them. The key difference between the two sub-networks lies in the number of neurons within their fully connected layers. The first sub-network serves as a strong denoiser with a small number of neurons, effectively attenuating seismic noise; in contrast, the second sub-network functions as a signal-add-back model, using a larger number of neurons to retrieve some of the signal that was not preserved in the output of the first sub-network. The proposed model produces two outputs, each corresponding to one of the sub-networks, and both sub-networks are optimized simultaneously using the noisy data as the label for both outputs. Evaluations conducted on both synthetic and field data demonstrate the model’s effectiveness in suppressing seismic noise with minimal signal leakage, outperforming some benchmark methods. |
| format | Article |
| id | doaj-art-529ee0e2fa6f4407a957528281a8568b |
| institution | OA Journals |
| issn | 2666-5441 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Artificial Intelligence in Geosciences |
| spelling | doaj-art-529ee0e2fa6f4407a957528281a8568b2025-08-20T02:22:05ZengKeAi Communications Co. Ltd.Artificial Intelligence in Geosciences2666-54412025-06-016110012310.1016/j.aiig.2025.100123Self-supervised multi-stage deep learning network for seismic data denoisingOmar M. Saad0Matteo Ravasi1Tariq Alkhalifah2King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi Arabia; Corresponding author.King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi Arabia; Shearwater GeoServicesKing Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi ArabiaSeismic data denoising is a critical process usually applied at various stages of the seismic processing workflow, as our ability to mitigate noise in seismic data affects the quality of our subsequent analyses. However, finding an optimal balance between preserving seismic signals and effectively reducing seismic noise presents a substantial challenge. In this study, we introduce a multi-stage deep learning model, trained in a self-supervised manner, designed specifically to suppress seismic noise while minimizing signal leakage. This model operates as a patch-based approach, extracting overlapping patches from the noisy data and converting them into 1D vectors for input. It consists of two identical sub-networks, each configured differently. Inspired by the transformer architecture, each sub-network features an embedded block that comprises two fully connected layers, which are utilized for feature extraction from the input patches. After reshaping, a multi-head attention module enhances the model’s focus on significant features by assigning higher attention weights to them. The key difference between the two sub-networks lies in the number of neurons within their fully connected layers. The first sub-network serves as a strong denoiser with a small number of neurons, effectively attenuating seismic noise; in contrast, the second sub-network functions as a signal-add-back model, using a larger number of neurons to retrieve some of the signal that was not preserved in the output of the first sub-network. The proposed model produces two outputs, each corresponding to one of the sub-networks, and both sub-networks are optimized simultaneously using the noisy data as the label for both outputs. Evaluations conducted on both synthetic and field data demonstrate the model’s effectiveness in suppressing seismic noise with minimal signal leakage, outperforming some benchmark methods.http://www.sciencedirect.com/science/article/pii/S266654412500019XSeismic data denoisingSelf-supervisedMulti-stage deep learning |
| spellingShingle | Omar M. Saad Matteo Ravasi Tariq Alkhalifah Self-supervised multi-stage deep learning network for seismic data denoising Artificial Intelligence in Geosciences Seismic data denoising Self-supervised Multi-stage deep learning |
| title | Self-supervised multi-stage deep learning network for seismic data denoising |
| title_full | Self-supervised multi-stage deep learning network for seismic data denoising |
| title_fullStr | Self-supervised multi-stage deep learning network for seismic data denoising |
| title_full_unstemmed | Self-supervised multi-stage deep learning network for seismic data denoising |
| title_short | Self-supervised multi-stage deep learning network for seismic data denoising |
| title_sort | self supervised multi stage deep learning network for seismic data denoising |
| topic | Seismic data denoising Self-supervised Multi-stage deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S266654412500019X |
| work_keys_str_mv | AT omarmsaad selfsupervisedmultistagedeeplearningnetworkforseismicdatadenoising AT matteoravasi selfsupervisedmultistagedeeplearningnetworkforseismicdatadenoising AT tariqalkhalifah selfsupervisedmultistagedeeplearningnetworkforseismicdatadenoising |