Random noise suppression of seismic data based on improved generative adversarial networks
To solve the problem that the seismic data acquired in geophysical exploration are covered by a large number of random noises,a random noise suppression method of seismic data based on improved Gen-erative Adversarial Network(GAN)is proposed.The core of the network is to introduce convolution layer into GAN,establish appropriate generator and discriminator,and introduce LeakyReLU and Sigmoid activa-tion functions to optimize the network training effect.The convolution layer replaces the full connection lay-er,and improves the computing efficiency while retaining the effective information of data through local con-nection and weight sharing.The experiment is carried out with actual seismic data and synthetic seismic da-ta.Under the evaluation indexes of data visualization and peak signal to noise ratio,the results show that compared with the original GAN and traditional methods,this method has better denoising effect under dif-ferent noise levels,which is conducive to subsequent seismic data interpretation and other links.
万方数据
维普
