EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A self-supervised Swin-Unet method for ground roll suppression based on Fourier positional encoding and masking strategy

Xichao Shi, Xiaodong Sun, Yuanhua Zhang, Pengjie Xue

Geophysical Journal International · 10.07.2026 · 246 (3)

DOI: 10.1093/gji/ggag262 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Journal International, online erschienen am 08.07.2026. Verfasst von Xichao Shi und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, China University of Petroleum, SINOPEC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenge in seismic exploration where strong-energy ground roll severely interferes with effective signals and conventional suppression methods tend to damage these signals, this paper proposes a self-supervised Swin-Unet network method for ground roll suppression based on Fourier positional encoding and a bespoke masking strategy. This method operates without the need for clean label data. By employing a specially designed fan-shaped masking strategy, it disrupts the spatiotemporal coherence of the ground roll, thereby guiding the network to learn the intrinsic characteristics of the effective signals and reconstruct the data. The core innovation lies in the introduction of Fourier positional encoding, which overcomes the inherent low-frequency bias of the Transformer architecture. This significantly enhances the network’s capability to model and recover high-frequency effective signals. Experimental results on synthetic data and field 2-D/3-D seismic data sets demonstrate that the proposed method not only effectively suppresses strong ground roll but also surpasses the traditional $f - k$ filtering method in terms of signal fidelity, particularly in preserving deep, weak reflections and high-frequency components. This showcases its robustness and potential for application in complex seismic data processing.

Förderung

  • Fundamental Research Funds for the Central Universities
  • China University of Petroleum
  • SINOPEC
  • China Scholarship Council
  • CSC

Zitieren

APA

Shi, X., Sun, X., Zhang, Y., & Xue, P. (2026). A self-supervised Swin-Unet method for ground roll suppression based on Fourier positional encoding and masking strategy. Geophysical Journal International, 246(3). https://doi.org/10.1093/gji/ggag262

Vancouver

Shi X, Sun X, Zhang Y, Xue P. A self-supervised Swin-Unet method for ground roll suppression based on Fourier positional encoding and masking strategy. Geophysical Journal International. 2026;246(3). doi:10.1093/gji/ggag262

BibTeX
@article{Shi2026,
  author = {Shi, Xichao and Sun, Xiaodong and Zhang, Yuanhua and Xue, Pengjie},
  title = {A self-supervised Swin-Unet method for ground roll suppression based on Fourier positional encoding and masking strategy},
  journal = {Geophysical Journal International},
  year = {2026},
  volume = {246},
  number = {3},
  doi = {10.1093/gji/ggag262}
}
Kostenlos starten →