Adaptive time-reassigned synchrosqueezing transform for seismic random noise suppression

Noise suppression is of great importance to seismic data analysis, processing and interpretation. Random noise always overlaps seismic reflections throughout the time and frequency, thus, its removal from seismic records is a challenging issue. We propose an adaptive time-reassigned synchrosqueezing transform (ATSST) by introducing a time-varying window function to improve the time-frequency concentration, and integrate an improved Optshrink algorithm for the suppression of seismic random noise. First of all, a noisy seismic signal is transformed into a sparse time-frequency matrix via the ATSST. Then, the obtained time-frequency matrix is decomposed into a low-rank component and a sparse component via an improved Optshrink algorithm, where the D transformation and its first derivative are further simplified to reduce the computational burden of the original OptShrink algorithm. Finally, the denoised signal is reconstructed by implementing an inverse ATSST on the low-rank component. We have tested the proposed method using synthetic and real datasets, and make a comparison with some classical denoising algorithms such as f - x deconvolution and Cadzow filtering. The obtained results demonstrate the superiority of the proposed method in denoising seismic data.