Seismic Random Noise Attenuation via Self-Supervised Transfer Learning

Random noise attenuation is an important step in seismic data processing. Unfortunately, most conventional denoising methods heavily rely on specific prior knowledge and fine-tuning of the parameters. Therefore, they often fail to suppress random noise. Recent works based on supervised learning techniques for seismic noise suppression show outstanding performance. However, this paradigm needs large-scale labeled training datasets that are not available for seismic field data. Inspired by the self-supervised learning, we propose a promising unsupervised learning scheme that aims at suppressing the random noise with only a noisy shot gather. The method is based on a specific \mathcal {J} -invariant function and an assumption that the noise is statistical independent while the useful signal exhibits some correlation. To further improve the denoising quality, we integrate the transfer learning strategy. We experimentally demonstrate that the proposed framework faithfully recovers the denoised data on both prestack and poststack synthetic and field data although the pretrained network is trained with the prestack synthetic dataset. The preliminary comparisons with traditional and learning-based approaches indicate the effectiveness and robustness as well.