Li Yangyang

TL;DR: In this paper, a deep learning seismic data denoising method was proposed to overcome the problems that the feature extraction capability of a traditional shallow linear structure is limited, and an existing deep learning model based on deep learning is slow in convergence, long in training time and the like.

TL;DR: In this paper, a deep over-limit indicator diagram learning method is proposed, which comprises the following steps of: extracting indicator diagram deep feature vectors by utilizing a deep convolutional network, and inputting the indicator diagram feature vectors into an extreme learning machine to give an identification type.

TL;DR: Wang et al. as discussed by the authors proposed a data noise suppressing method based on a residual block full convolutional neural network, where a double residual block is fused on the basis of a Unet network according to the design principle of a network structure in order to enhance the capturing performance of the network for random noise.

TL;DR: In this paper, a residual convolutional self-encoding block composed of a residual block, a batch normalization layer and a self encoder is used as a basic denoising network structure.