Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.15289 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909586667077632 |
|---|---|
| author | Zeng, Yunlin Erdinc, Huseyin Tuna Orozco, Rafael Herrmann, Felix |
| author_facet | Zeng, Yunlin Erdinc, Huseyin Tuna Orozco, Rafael Herrmann, Felix |
| contents | Accurate seismic imaging and velocity estimation are essential for subsurface characterization. Conventional inversion techniques, such as full-waveform inversion, remain computationally expensive and sensitive to initial velocity models. To address these challenges, we propose a simulation-based inference framework with conditional elucidated diffusion models for posterior velocity-model sampling. Our approach incorporates both horizontal and vertical subsurface offset common-image gathers to capture a broader range of reflector geometries, including gently dipping structures and steep dipping layers. Additionally, we introduce the background-velocity model as an input condition to enhance generalization across varying geological settings. We evaluate our method on the SEAM dataset, which features complex salt geometries, using a patch-based training approach. Experimental results demonstrate that adding the background-velocity model as an additional conditioning variable significantly enhances performance, improving SSIM from $0.717$ to $0.733$ and reducing RMSE from $0.381\,$km/s to $0.274\,$km/s. Furthermore, uncertainty quantification analysis shows that our proposed approach yields better-calibrated uncertainty estimates, reducing uncertainty calibration error from $6.68\,$km/s to $3.91\,$km/s. These results show robust amortized seismic inversion with uncertainty quantification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15289 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Full-waveform variational inference with full common-image gathers and diffusion network Zeng, Yunlin Erdinc, Huseyin Tuna Orozco, Rafael Herrmann, Felix Geophysics Accurate seismic imaging and velocity estimation are essential for subsurface characterization. Conventional inversion techniques, such as full-waveform inversion, remain computationally expensive and sensitive to initial velocity models. To address these challenges, we propose a simulation-based inference framework with conditional elucidated diffusion models for posterior velocity-model sampling. Our approach incorporates both horizontal and vertical subsurface offset common-image gathers to capture a broader range of reflector geometries, including gently dipping structures and steep dipping layers. Additionally, we introduce the background-velocity model as an input condition to enhance generalization across varying geological settings. We evaluate our method on the SEAM dataset, which features complex salt geometries, using a patch-based training approach. Experimental results demonstrate that adding the background-velocity model as an additional conditioning variable significantly enhances performance, improving SSIM from $0.717$ to $0.733$ and reducing RMSE from $0.381\,$km/s to $0.274\,$km/s. Furthermore, uncertainty quantification analysis shows that our proposed approach yields better-calibrated uncertainty estimates, reducing uncertainty calibration error from $6.68\,$km/s to $3.91\,$km/s. These results show robust amortized seismic inversion with uncertainty quantification. |
| title | Full-waveform variational inference with full common-image gathers and diffusion network |
| topic | Geophysics |
| url | https://arxiv.org/abs/2504.15289 |