EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PCS-UNETR: A Physically Constrained SwinUNETR Model for Robust Seismic First Arrival Picking

Yang Li, Haiwei Guo, Xianfeng Gong, Yundong Guo, Duanshi Lv

IEEE Access · 2026 · 14 · 62310-62321

DOI: 10.1109/access.2026.3684960 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Yang Li und 4 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Major National Science and Technology Special Project for New Oil and Gas Exploration and Development in China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of low accuracy, poor noise resistance, and inefficiency in seismic first arrival picking, this paper proposes Physical-Constraint SwinUNETR (PCS-UNETR). First, a SoftLabel dataset is constructed by converting seismic traces into single-band 2D images with Gaussian probability density labels to enrich gradient information. Second, a physical prior-constrained SwinUNETR model is designed. By incorporating an amplitude change rate penalty term into the loss function, the model is forced to identify arrivals on the rising edge of the first peak. Finally, morphological operations define a region of interest, where the pixel with the maximum predicted probability is selected as the final pick. Experiments on Sinopec Zhongyuan Oilfield’s Puguang seismic data (10.24 million traces) demonstrate that PCS-UNETR effectively reduces outliers, significantly improves accuracy and noise resistance, and achieves full automation without manual intervention. The innovation lies in fusing physical priors with deep learning via a “global probability prediction + local morphological constraint” mechanism, offering a new approach for intelligent seismic processing with high application value.

Förderung

  • Major National Science and Technology Special Project for New Oil and Gas Exploration and Development in China

Zitieren

APA

Li, Y., Guo, H., Gong, X., Guo, Y., & Lv, D. (2026). PCS-UNETR: A Physically Constrained SwinUNETR Model for Robust Seismic First Arrival Picking. IEEE Access, 14, 62310-62321. https://doi.org/10.1109/access.2026.3684960

Vancouver

Li Y, Guo H, Gong X, Guo Y, Lv D. PCS-UNETR: A Physically Constrained SwinUNETR Model for Robust Seismic First Arrival Picking. IEEE Access. 2026;14:62310-62321. doi:10.1109/access.2026.3684960

BibTeX
@article{Li2026,
  author = {Li, Yang and Guo, Haiwei and Gong, Xianfeng and Guo, Yundong and Lv, Duanshi},
  title = {PCS-UNETR: A Physically Constrained SwinUNETR Model for Robust Seismic First Arrival Picking},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {62310--62321},
  doi = {10.1109/access.2026.3684960}
}
Kostenlos starten →