Random noise attenuation based on residual learning of deep convolutional neural network
Xu Si, Yijun Yuan · 2018
The denoising convolutional neural network (DnCNN) algorithm is a noise attenuation method that was originally developed for the purposes of image denosing. The DnCNN algorithm is based on the principle of neural network and statistics to learn the residual image from the data with noise and to obtain the results by subtracting. Since random noise attenuation in seismic data is similar to image denoising, we propose to use the DnCNN algorithm to attenuate the random noise of seismic data. Tests on the synthetic data demonstrate that DnCNN algorithm is very effective for random noise attenuation in seismic data. Presentation Date: Tuesday, October 16, 2018 Start Time: 1:50:00 PM Location: 204B (Anaheim Convention Center) Presentation Type: Oral