Self-supervised surface-related multiple suppression with multidimensional convolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916715985633280 |
|---|---|
| author | Cheng, Shijun Wang, Ning Alkhalifah, Tariq |
| author_facet | Cheng, Shijun Wang, Ning Alkhalifah, Tariq |
| contents | Surface-related multiples pose significant challenges in seismic data processing, often obscuring primary reflections and reducing imaging quality. Traditional methods rely on computationally expensive algorithms, the prior knowledge of subsurface model, or accurate wavelet estimation, while supervised learning approaches require clean labels, which are impractical for real data. Thus, we propose a self-supervised learning framework for surface-related multiple suppression, leveraging multi-dimensional convolution to generate multiples from the observed data and a two-stage training strategy comprising a warm-up and an iterative data refinement stage, so the network learns to remove the multiples. The framework eliminates the need for labeled data by iteratively refining predictions using multiples augmented inputs and pseudo-labels. Numerical examples demonstrate that the proposed method effectively suppresses surface-related multiples while preserving primary reflections. Migration results confirm its ability to reduce artifacts and improve imaging quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00419 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-supervised surface-related multiple suppression with multidimensional convolution Cheng, Shijun Wang, Ning Alkhalifah, Tariq Geophysics Surface-related multiples pose significant challenges in seismic data processing, often obscuring primary reflections and reducing imaging quality. Traditional methods rely on computationally expensive algorithms, the prior knowledge of subsurface model, or accurate wavelet estimation, while supervised learning approaches require clean labels, which are impractical for real data. Thus, we propose a self-supervised learning framework for surface-related multiple suppression, leveraging multi-dimensional convolution to generate multiples from the observed data and a two-stage training strategy comprising a warm-up and an iterative data refinement stage, so the network learns to remove the multiples. The framework eliminates the need for labeled data by iteratively refining predictions using multiples augmented inputs and pseudo-labels. Numerical examples demonstrate that the proposed method effectively suppresses surface-related multiples while preserving primary reflections. Migration results confirm its ability to reduce artifacts and improve imaging quality. |
| title | Self-supervised surface-related multiple suppression with multidimensional convolution |
| topic | Geophysics |
| url | https://arxiv.org/abs/2505.00419 |