Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs)
A high-resolution seismic image is the key factor for helping geophysicists and geologists to recognize the geological structures below the subsurface. More and more complex geology has challenged traditional techniques and resulted in a need for more powerful denoising methodologies. The deep learn...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/18/6569 |
| _version_ | 1797488948890566656 |
|---|---|
| author | Hao Zhang Wenlei Wang |
| author_facet | Hao Zhang Wenlei Wang |
| author_sort | Hao Zhang |
| collection | DOAJ |
| description | A high-resolution seismic image is the key factor for helping geophysicists and geologists to recognize the geological structures below the subsurface. More and more complex geology has challenged traditional techniques and resulted in a need for more powerful denoising methodologies. The deep learning technique has shown its effectiveness in many different types of tasks. In this work, we used a conditional generative adversarial network (CGAN), which is a special type of deep neural network, to conduct the seismic image denoising process. We considered the denoising task as an image-to-image translation problem, which transfers a raw seismic image with multiple types of noise into a reflectivity-like image without noise. We used several seismic models with complex geology to train the CGAN. In this experiment, the CGAN’s performance was promising. The trained CGAN could maintain the structure of the image undistorted while suppressing multiple types of noise. |
| first_indexed | 2024-03-10T00:10:34Z |
| format | Article |
| id | doaj.art-dbdd18f729f34d51ae3394627685cff8 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T00:10:34Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-dbdd18f729f34d51ae3394627685cff82023-11-23T16:01:57ZengMDPI AGEnergies1996-10732022-09-011518656910.3390/en15186569Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs)Hao Zhang0Wenlei Wang1Institute of Geomechanics, Chinese Academy of Geological Sciences, Beijing 100081, ChinaInstitute of Geomechanics, Chinese Academy of Geological Sciences, Beijing 100081, ChinaA high-resolution seismic image is the key factor for helping geophysicists and geologists to recognize the geological structures below the subsurface. More and more complex geology has challenged traditional techniques and resulted in a need for more powerful denoising methodologies. The deep learning technique has shown its effectiveness in many different types of tasks. In this work, we used a conditional generative adversarial network (CGAN), which is a special type of deep neural network, to conduct the seismic image denoising process. We considered the denoising task as an image-to-image translation problem, which transfers a raw seismic image with multiple types of noise into a reflectivity-like image without noise. We used several seismic models with complex geology to train the CGAN. In this experiment, the CGAN’s performance was promising. The trained CGAN could maintain the structure of the image undistorted while suppressing multiple types of noise.https://www.mdpi.com/1996-1073/15/18/6569seismic imagingdenoisingdeep learningdeblur generative adversarial networks |
| spellingShingle | Hao Zhang Wenlei Wang Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs) Energies seismic imaging denoising deep learning deblur generative adversarial networks |
| title | Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs) |
| title_full | Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs) |
| title_fullStr | Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs) |
| title_full_unstemmed | Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs) |
| title_short | Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs) |
| title_sort | imaging domain seismic denoising based on conditional generative adversarial networks cgans |
| topic | seismic imaging denoising deep learning deblur generative adversarial networks |
| url | https://www.mdpi.com/1996-1073/15/18/6569 |
| work_keys_str_mv | AT haozhang imagingdomainseismicdenoisingbasedonconditionalgenerativeadversarialnetworkscgans AT wenleiwang imagingdomainseismicdenoisingbasedonconditionalgenerativeadversarialnetworkscgans |