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...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuang Wang, Xiangpeng Wang, Yuhan Yang, Peifan Jiang, Bin Wang, Yuanhao Li
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