Robust seismic data denoising based on deep learning

Noise in seismic data is complicated, and the traditional modeling methods based on prior knowledge cannot describe the noise distribution accurately. In the denoising methods based on deep learning, a multi-layer convolutional neural network is employed to automatically extract the deep features of seismic data, and its nonlinear approximation ability is used for adaptive learning, which yields a complex denoising model and thus brings a new idea for the denoising of seismic data. How-ever, poor generalization ability is found in the cur-rent denoising methods based on deep learning in the case of insufficient sample coverage, greatly reducing the denoising effect. Therefore, this paper proposes a robust deep learning algorithm for denoising. The model is composed of two sub-networks, which realize the estimation of noise distribution and noise suppression of noisy seismic data respectively. The sub-network for estimating noise distribution is a multi-layer convolutional neural network. The sub-network for denoising introduces a strategy of feature fusion, which comprehensively considers the global and local information of seismic data, and a residual learning strategy is utilized to extract noise features. L1 norm loss is taken as the loss function for the two sub-networks to enhance the generalization ability of the model. Experiments show that the method proposed in this paper has a higher generalization ability than similar algorithms. Data processing results indicate that it better preserves event features and has a higher signal-to-noise ratio. © 2022, Editorial Department OIL GEOPHYSICAL PROSPECTING. All right reserved.