Well-Constrained Conditional Generative Adversarial Network for Weak Seismic Signal Enhancement

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.