Single-channel and multi-channel seismic random noise suppression based on the regularized non-stationary decomposition

Abstract

Strong random noise existing in the seismic data often deteriorates many processing and interpretation tasks in the whole seismic imaging workflow. To tackle the challenge in processing noise-contaminated seismic data, we propose to apply a regularized non-stationary decomposition (RNSD) method to attenuate the strong noise in the seismic data. The RNSD method can not only be applied to denoise single-channel seismic data, e.g., micro-seismic data, but also be used to deal with multi-channel seismic data. The RNSD is formulated as an inverse problem, in which the noise is assumed to be the misfit within the inverse problem. When the RNSD method is applied to denoise single-channel seismic data, only temporal constraint is applied to invert the decomposing results. When the RNSD method is applied to denoise multi-channel seismic data, both time and space constraints are enforced. For the convenience of applying the constraints, we apply the shaping method to enforce the decomposed results to be either temporally smooth or bi-laterally smooth. We apply the proposed method to both synthetic and field data examples to illustrate the denoising power of the proposed method.