Conditional autoregressive model based on next scale prediction for missing data reconstruction
Abstract Seismic data collected under complex field conditions often contain missing traces. Traditional theory-driven methods rely heavily on empirically selected parameters and struggle to reconstruct continuous missing traces effectively. With advancements in deep learning, various generative mod...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-08830-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849238581509357568 |
|---|---|
| author | Shuang Wang Xiangpeng Wang Yuhan Yang Peifan Jiang Bin Wang Yuanhao Li |
| author_facet | Shuang Wang Xiangpeng Wang Yuhan Yang Peifan Jiang Bin Wang Yuanhao Li |
| author_sort | Shuang Wang |
| collection | DOAJ |
| description | Abstract Seismic data collected under complex field conditions often contain missing traces. Traditional theory-driven methods rely heavily on empirically selected parameters and struggle to reconstruct continuous missing traces effectively. With advancements in deep learning, various generative models have exhibited strong reconstruction capabilities. However, diffusion model-based methods face significant reconstruction time overhead due to their iterative sampling strategies. Existing transformer-based autoregressive methods flatten two-dimensional seismic data into one-dimensional sequences, disrupting the inherent two-dimensional structure and compromising the spatial locality of seismic information. To address these limitations, we propose a conditional autoregressive model based on next-scale prediction. Starting from the smallest scale, the model incrementally predicts larger-scale data using information from preceding smaller scales, ultimately achieving robust data reconstruction. This next-scale prediction approach avoids flattening the data, thereby preserving its spatial structure. Additionally, conditional constraints during autoregressive generation ensure that the predicted data at each scale remains consistent and aligns with the distribution of the known data. Reconstruction experiments on both field and synthetic datasets demonstrate that our method achieves superior reconstruction accuracy compared to existing approaches and effectively handles various complex missing data scenarios. |
| format | Article |
| id | doaj-art-e4b837a71b624b49b8634a6f5fb79249 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e4b837a71b624b49b8634a6f5fb792492025-08-20T04:01:34ZengNature PortfolioScientific Reports2045-23222025-07-0115111710.1038/s41598-025-08830-5Conditional autoregressive model based on next scale prediction for missing data reconstructionShuang Wang0Xiangpeng Wang1Yuhan Yang2Peifan Jiang3Bin Wang4Yuanhao Li5Key Laboratory of Earth Exploration and Information Techniques of Education Ministry, College of Geophysics, Chengdu University of TechnologyKey Laboratory of Earth Exploration and Information Techniques of Education Ministry, College of Geophysics, Chengdu University of TechnologyKey Laboratory of Earth Exploration and Information Techniques of Education Ministry, College of Geophysics, Chengdu University of TechnologyKey Laboratory of Earth Exploration and Information Techniques of Education Ministry, College of Geophysics, Chengdu University of TechnologyCollege of Computer Science and Cyber Security, Chengdu University of TechnologyKey Laboratory of Earth Exploration and Information Techniques of Education Ministry, College of Geophysics, Chengdu University of TechnologyAbstract Seismic data collected under complex field conditions often contain missing traces. Traditional theory-driven methods rely heavily on empirically selected parameters and struggle to reconstruct continuous missing traces effectively. With advancements in deep learning, various generative models have exhibited strong reconstruction capabilities. However, diffusion model-based methods face significant reconstruction time overhead due to their iterative sampling strategies. Existing transformer-based autoregressive methods flatten two-dimensional seismic data into one-dimensional sequences, disrupting the inherent two-dimensional structure and compromising the spatial locality of seismic information. To address these limitations, we propose a conditional autoregressive model based on next-scale prediction. Starting from the smallest scale, the model incrementally predicts larger-scale data using information from preceding smaller scales, ultimately achieving robust data reconstruction. This next-scale prediction approach avoids flattening the data, thereby preserving its spatial structure. Additionally, conditional constraints during autoregressive generation ensure that the predicted data at each scale remains consistent and aligns with the distribution of the known data. Reconstruction experiments on both field and synthetic datasets demonstrate that our method achieves superior reconstruction accuracy compared to existing approaches and effectively handles various complex missing data scenarios.https://doi.org/10.1038/s41598-025-08830-5 |
| spellingShingle | Shuang Wang Xiangpeng Wang Yuhan Yang Peifan Jiang Bin Wang Yuanhao Li Conditional autoregressive model based on next scale prediction for missing data reconstruction Scientific Reports |
| title | Conditional autoregressive model based on next scale prediction for missing data reconstruction |
| title_full | Conditional autoregressive model based on next scale prediction for missing data reconstruction |
| title_fullStr | Conditional autoregressive model based on next scale prediction for missing data reconstruction |
| title_full_unstemmed | Conditional autoregressive model based on next scale prediction for missing data reconstruction |
| title_short | Conditional autoregressive model based on next scale prediction for missing data reconstruction |
| title_sort | conditional autoregressive model based on next scale prediction for missing data reconstruction |
| url | https://doi.org/10.1038/s41598-025-08830-5 |
| work_keys_str_mv | AT shuangwang conditionalautoregressivemodelbasedonnextscalepredictionformissingdatareconstruction AT xiangpengwang conditionalautoregressivemodelbasedonnextscalepredictionformissingdatareconstruction AT yuhanyang conditionalautoregressivemodelbasedonnextscalepredictionformissingdatareconstruction AT peifanjiang conditionalautoregressivemodelbasedonnextscalepredictionformissingdatareconstruction AT binwang conditionalautoregressivemodelbasedonnextscalepredictionformissingdatareconstruction AT yuanhaoli conditionalautoregressivemodelbasedonnextscalepredictionformissingdatareconstruction |