EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Strong Noise Reduction Network for Seismic Records

Tong Shen, Xuan Jiang, Wenzheng Rong, Lei Xu, Xianguo Tuo, Guili Peng

Applied Sciences · 07.11.2024 · 14 (22) · 10262

DOI: 10.3390/app142210262 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 07.11.2024. Verfasst von Tong Shen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Youth Science Foundation of Sichuan Province, Doctoral Fund of Southwest University of Science and Technology, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Noise reduction is a critical step in seismic data processing. A novel strong noise reduction network is proposed in this study. The network enhances the U-Net architecture with an improved inception module and coordinate attention (CA) mechanism, suppressing noise and enhancing signal clarity. These enhancements improve the network’s capability to distinguish between signal and noise in the time–frequency domain. We trained and tested our model on the STEAD dataset, which eliminated noise across various frequency bands, improved the signal-to-noise ratio (SNR) of seismic records, and reduced the waveform distortion significantly. Comparative analyses against U-Net, DeepDenoiser, and DnRDB models, using signals with SNRs ranging from −14 dB to 0 dB, demonstrated our model’s superior performance. At the same time, we demonstrated that the Inception Conv Block has a significant impact on the denoising ability of the network. Furthermore, validation using the “Di Ting” dataset and real noisy signals confirmed the model’s generalizability. These results show that the proposed model significantly outperforms the comparative methods in terms of the SNR, correlation coefficient (r), and root mean square error (RMSE), delivering higher-quality seismograms. The enhanced phase-picking accuracy underscores the potential of our approach to advance in geophysics applications.

Förderung

  • Youth Science Foundation of Sichuan Province
  • Doctoral Fund of Southwest University of Science and Technology
  • National Natural Science Foundation of China

Zitieren

APA

Shen, T., Jiang, X., Rong, W., Xu, L., Tuo, X., & Peng, G. (2024). A Strong Noise Reduction Network for Seismic Records. Applied Sciences, 14(22), 10262. https://doi.org/10.3390/app142210262

Vancouver

Shen T, Jiang X, Rong W, Xu L, Tuo X, Peng G. A Strong Noise Reduction Network for Seismic Records. Applied Sciences. 2024;14(22):10262. doi:10.3390/app142210262

BibTeX
@article{Shen2024,
  author = {Shen, Tong and Jiang, Xuan and Rong, Wenzheng and Xu, Lei and Tuo, Xianguo and Peng, Guili},
  title = {A Strong Noise Reduction Network for Seismic Records},
  journal = {Applied Sciences},
  year = {2024},
  volume = {14},
  number = {22},
  pages = {10262},
  doi = {10.3390/app142210262}
}
Kostenlos starten →