Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 8, 2025Journal of Geophysics and EngineeringOpen Access

Multi-Condition Seismic Data Denoising using Feature-Expanded Gradient Penalty Generative Adversarial Network

View Full Paper
Ask AI
Bookmark
Share

Authors

XXXiaotian XueYXYi XiYLYujing Liao

Discussion

Loading...

Member takes

Overview

This approach improves image processing in seismic data, indicating that generative adversarial networks enhance signal preservation amidst noise using deep learning.

Key Points

  • Denoising significantly enhances signal preservation in seismic data while reducing noise levels.
  • Experimental results on both 2D and 3D datasets show advantages over traditional and unsupervised learning methods.
  • The approach utilizes a generative adversarial network framework with deep learning methodologies for improved outcomes.
  • The findings highlight the potential for real-world applications in seismic data processing and interpretation.

Cite This Study

Xue et al. (2025) studied this question.

synapsesocial.com/papers/694020e22d562116f28faa0bhttps://doi.org/10.1093/jge/gxaf158
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1High-Fidelity Seismic Image Generation From Limited Data Sets using Generative Adversarial Networks2025
  2. 2Time–Frequency Domain Seismic Signal Denoising Based on Generative Adversarial Networks2024 · 3 citations
  3. 3Ground-truth-free deep learning for 3D seismic denoising and reconstruction with channel attention mechanism2024 · 11 citations
  4. 4Unsupervised seismic random noise attention using 3D enhanced multi-scale features2025
  5. 5An effective self-supervised learning method for attenuating various types of seismic noise2024 · 24 citations