Saved in:
Bibliographic Details
Main Authors: Gong, Xinyue, Fomel, Sergey, Chen, Yangkang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.13645
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917341251502080
author Gong, Xinyue
Fomel, Sergey
Chen, Yangkang
author_facet Gong, Xinyue
Fomel, Sergey
Chen, Yangkang
contents We introduce the Seismic Waveforms dataset for Automatic Neural-network processing (SWAN), a comprehensive and standardized benchmark designed to advance data-driven seismic signal processing. SWAN aggregates diverse synthetic and real seismic waveforms spanning a wide range of geological structures, noise conditions, propagation environments, and acquisition geometries, providing a unified foundation for training highly generalizable models. Leveraging this dataset, we develop and evaluate a conditionally constrained residual diffusion model for core seismic processing tasks, focusing on missing-trace reconstruction. Extensive experiments demonstrate that diffusion models trained on SWAN achieve state-of-the-art performance across heterogeneous testing scenarios, outperforming leading deep-learning and physics-based baselines on both synthetic benchmarks and field data examples. The results highlight SWAN's value as both a scalable training corpus and a rigorous evaluation framework, and illustrate the strong potential of diffusion-based architectures for robust, generalizable seismic data processing.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13645
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Training a generalizable diffusion model for seismic data processing using a large-scale open-source waveform dataset
Gong, Xinyue
Fomel, Sergey
Chen, Yangkang
Geophysics
We introduce the Seismic Waveforms dataset for Automatic Neural-network processing (SWAN), a comprehensive and standardized benchmark designed to advance data-driven seismic signal processing. SWAN aggregates diverse synthetic and real seismic waveforms spanning a wide range of geological structures, noise conditions, propagation environments, and acquisition geometries, providing a unified foundation for training highly generalizable models. Leveraging this dataset, we develop and evaluate a conditionally constrained residual diffusion model for core seismic processing tasks, focusing on missing-trace reconstruction. Extensive experiments demonstrate that diffusion models trained on SWAN achieve state-of-the-art performance across heterogeneous testing scenarios, outperforming leading deep-learning and physics-based baselines on both synthetic benchmarks and field data examples. The results highlight SWAN's value as both a scalable training corpus and a rigorous evaluation framework, and illustrate the strong potential of diffusion-based architectures for robust, generalizable seismic data processing.
title Training a generalizable diffusion model for seismic data processing using a large-scale open-source waveform dataset
topic Geophysics
url https://arxiv.org/abs/2603.13645