A Denoising Method for Seismic Data Based on SVD and Deep Learning
When reconstructing seismic data, the traditional singular value decomposition (SVD) denoising method has the challenge of difficult rank selection. Therefore, we propose a seismic data denoising method that combines SVD and deep learning. In this method, seismic data with different signal-to-noise...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/24/12840 |
| _version_ | 1797461609776414720 |
|---|---|
| author | Guoli Ji Chao Wang |
| author_facet | Guoli Ji Chao Wang |
| author_sort | Guoli Ji |
| collection | DOAJ |
| description | When reconstructing seismic data, the traditional singular value decomposition (SVD) denoising method has the challenge of difficult rank selection. Therefore, we propose a seismic data denoising method that combines SVD and deep learning. In this method, seismic data with different signal-to-noise ratios (SNRs) are processed by SVD. Data sets are created from the decomposed right singular vectors and data sets divided into two categories: effective signal and noise. The lightweight MobileNetV2 network was chosen for training because of its quick response speed and great accuracy. We forecasted and categorized the right singular vectors by SVD using the trained MobileNetV2 network. The right singular vector (RSV) corresponding to the noise in the seismic data was removed during reconstruction, but the effective signal was kept. The effective signal was projected to smooth the RSV. Finally, the goal of low SNR denoising of two-dimensional seismic data was accomplished. This approach addresses issues with deep learning in seismic data processing, including the challenge of gathering sample data and the weak generalizability of the training model. Compared with the traditional denoising method, the improved denoising method performs well at removing Gaussian and irregular noise with strong amplitudes. |
| first_indexed | 2024-03-09T17:21:52Z |
| format | Article |
| id | doaj.art-2f20e0bd1d644de7882075296e6a82c7 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:21:52Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2f20e0bd1d644de7882075296e6a82c72023-11-24T13:05:38ZengMDPI AGApplied Sciences2076-34172022-12-0112241284010.3390/app122412840A Denoising Method for Seismic Data Based on SVD and Deep LearningGuoli Ji0Chao Wang1State Key Laboratory of Ore Deposit Geochemistry, Institute of Geochemistry, Chinese Academy of Sciences, Guiyang 550081, ChinaState Key Laboratory of Ore Deposit Geochemistry, Institute of Geochemistry, Chinese Academy of Sciences, Guiyang 550081, ChinaWhen reconstructing seismic data, the traditional singular value decomposition (SVD) denoising method has the challenge of difficult rank selection. Therefore, we propose a seismic data denoising method that combines SVD and deep learning. In this method, seismic data with different signal-to-noise ratios (SNRs) are processed by SVD. Data sets are created from the decomposed right singular vectors and data sets divided into two categories: effective signal and noise. The lightweight MobileNetV2 network was chosen for training because of its quick response speed and great accuracy. We forecasted and categorized the right singular vectors by SVD using the trained MobileNetV2 network. The right singular vector (RSV) corresponding to the noise in the seismic data was removed during reconstruction, but the effective signal was kept. The effective signal was projected to smooth the RSV. Finally, the goal of low SNR denoising of two-dimensional seismic data was accomplished. This approach addresses issues with deep learning in seismic data processing, including the challenge of gathering sample data and the weak generalizability of the training model. Compared with the traditional denoising method, the improved denoising method performs well at removing Gaussian and irregular noise with strong amplitudes.https://www.mdpi.com/2076-3417/12/24/12840MobileNetV2seismic datadenoisingdeep learningSVD |
| spellingShingle | Guoli Ji Chao Wang A Denoising Method for Seismic Data Based on SVD and Deep Learning Applied Sciences MobileNetV2 seismic data denoising deep learning SVD |
| title | A Denoising Method for Seismic Data Based on SVD and Deep Learning |
| title_full | A Denoising Method for Seismic Data Based on SVD and Deep Learning |
| title_fullStr | A Denoising Method for Seismic Data Based on SVD and Deep Learning |
| title_full_unstemmed | A Denoising Method for Seismic Data Based on SVD and Deep Learning |
| title_short | A Denoising Method for Seismic Data Based on SVD and Deep Learning |
| title_sort | denoising method for seismic data based on svd and deep learning |
| topic | MobileNetV2 seismic data denoising deep learning SVD |
| url | https://www.mdpi.com/2076-3417/12/24/12840 |
| work_keys_str_mv | AT guoliji adenoisingmethodforseismicdatabasedonsvdanddeeplearning AT chaowang adenoisingmethodforseismicdatabasedonsvdanddeeplearning AT guoliji denoisingmethodforseismicdatabasedonsvdanddeeplearning AT chaowang denoisingmethodforseismicdatabasedonsvdanddeeplearning |