Low-frequency swell noise suppression based on U-Net

• 作 者: Zhang Rui-qi Song Peng Liu Bao-hua Zhang Xiao-bo Tan Jun Zou Zhi-hui Xie Chuang Wang Shao-wen
• 机 构: College of Marine Geosciences, Ocean University of China, Qingdao 266100, China;Laboratory for MMR,
• 出 处: 应用地球物理（英文版）
• 发表日期: 2020年3期
• 关键词: U-Net swell noise noise attenuation residual learning generalization

Low-frequency band-shaped swell noise with strong amplitude is common in marine seismic data. The conventional high-pass filtering algorithm widely used to suppress swell noise often results in serious damage of effective information. This paper introduces the residual learning strategy of denoising convolutional neural network (DnCNN) into a U-shaped convolutional neural network (U-Net) to develop a new U-Net with more generalization, which can eliminate low-frequency swell noise with high precision. The results of both model date tests and real data processing show that the new U-Net is capable of efficient learning and high-precision noise removal, and can avoid the overfitting problem which is very common in conventional neural network methods. This new U-Net can also be generalized to some extent and can effectively preserve low-frequency effective information. Compared with the conventional high-pass filtering method commonly used in the industry, the new U-Net can eliminate low-frequency swell noise with higher precision while effectively preserving low-frequency effective information, which is of great significance for subsequent processing such as amplitude-preserving imaging and full waveform inversion.