Well-Constrained Conditional Generative Adversarial Network for Weak Seismic Signal Enhancement
Open Access
- 31 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 28102-28110
Abstract
Seismic images are critical for understanding subsurface geology and resource distribution. However, deep seismic signals are often extremely weak due to subsurface absorption and random noise, limiting imaging resolution and accurate geological interpretation. Generative adversarial networks (GANs) can enhance resolution and suppress noise, but their unconstrained generation may overfit noise, produce geologically inconsistent artifacts, and fail to recover high- frequency details. Furthermore, the high-dimensional and complex nature of seismic data increases the risk of mode collapse, reducing output diversity. To address these challenges, we propose a well-constrained conditional GAN (W-CGAN) that incorporates well-log data as a geophysical constraint. This conditional guidance explicitly directs the generator to learn a mapping from low- to high-resolution signals, reducing the solution space, mitigating adversarial training blind spots, and lowering mode collapse risk. Additionally, integrating a VGG- based perceptual loss enables the model to recover weak effective signal energy and high-frequency details. Experiments on synthetic datasets demonstrate that the proposed method substantially improves weak-signal recovery, noise suppression, and resolution enhancement, while applications to field seismic data further validate its robust generalization capability, even when trained exclusively on synthetic data.Keywords
Funding Information
- Natural Science Foundation of Shandong Province (ZR2022QD112)
- Visiting and Research-Training Fund for Teachers at Ordinary Undergraduate Universities in Shandong Province
This publication has 34 references indexed in Scilit:
- SeisGAN: Improving Seismic Image Resolution and Reducing Random Noise Using a Generative Adversarial NetworkMathematical Geosciences, 2023
- Generative adversarial networks review in earthquake-related engineering fieldsBulletin of Earthquake Engineering, 2023
- Residual Learning of Cycle-GAN for Seismic Data DenoisingIEEE Access, 2021
- First arrival picking of microseismic signals based on nested U-Net and Wasserstein Generative Adversarial NetworkJournal of Petroleum Science and Engineering, 2020
- Stochastic Seismic Waveform Inversion Using Generative Adversarial Networks as a Geological PriorMathematical Geosciences, 2019
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs2018
- Residual Dense Network for Image Super-Resolution2018
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Deep Residual Learning for Image Recognition2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016