Less Data-Dependent Seismic Noise Suppression Method Based on Transfer Learning With Attention Mechanism

Deep learning (DL) exhibits excellent performance in seismic noise suppression, and DL successes are attributed to its ability to learn rich representations from a large amount of data. However, obtaining numerous high-quality labeled data is challenging owing to confidentiality, regional sensitivity, and manual labeling, which limits the capability of DL. To reduce data dependency and improve network generalization, this study proposes a novel denoising architecture based on small-sample transfer learning. The proposed architecture uses a fully pretrained model on the source data as a feature extractor, and then copies and transfers the rich features from the extractor to the denoiser for fine-tuning on the target data. Moreover, to reduce the discrepancy between two different data and better reuse the transferred features, a noise attention block is proposed to regularize the representations. The results of multi-region experiment indicate that the proposed network leads to a significant improvement in denoising performance, essentially outperforming existing denoising methods; additionally, it exhibits strong generalization for different types and regions of seismic noise. Moreover, the proposed method can effectively address the data dependency issue, thus providing great potential for real-time processing or small-device applications.