Signal recovery and noise suppression of the Ocean-Bottom Cable P-component data based on improved dense convolutional network

Effective attenuation of noise in seismic data is important for high-quality seismic imaging. Noise suppression in Ocean-Bottom Cable data is particularly challenging. The challenge for the geophysicist is to process the individual hydrophone and vertical geophone data up to a level where they can conveniently be combined for effective multiple suppressions. In this study, we propose a deep learning-based solution for noise attenuation and signal recovery of the P-component of Ocean-Bottom Cable data. To effectively attenuate complex noise, a denoising model based on dense convolutional network is proposed for Ocean-Bottom Cable data processing. The backbone of the denoising network uses dense blocks to extract the potential features. Dense connections are applied to fuse the features at each stage to further enhance the effective information and thus improve the reconstruction of the signal. A high-quality training set was built for the training network to ensure that the trained model was suitable for noise suppression. Synthesis and field experiments show that the proposed method can completely eliminate complex noise and recover weak signals from the P-component data of the Ocean-Bottom Cable data.