Integrating self-supervised denoising in inversion-based seismic deblending

To limit the time, cost, and environmental impact associated with the acquisition of seismic data in recent decades, considerable effort has been put into so-called simultaneous shooting acquisitions, where seismic sources are fired at short time intervals between each other. As a consequence, waves originating from consecutive shots are entangled within the seismic recordings, yielding so-called blended data. For processing and imaging purposes, the data generated by each individual shot must be retrieved. This process, called deblending, is achieved by solving an inverse problem that is heavily underdetermined. Conventional approaches rely on the action of the adjoint of the blending operator that renders the blending noise into burst-like noise while preserving the signal of interest. Compressed sensing type regularization is then applied, where sparsity in some domain is assumed for the signal of interest. The domain of choice generally depends on the acquisition geometry and the separability between the signal and noise within the chosen domain. In this work, we introduce a new concept that consists of embedding a self-supervised denoising network into the plug-and-play (PnP) framework. A novel network is introduced whose design extends an existing blind-spot network architecture for partially coherent noise (i.e., correlated in time). The network is then trained directly on the noisy input data at each step of the PnP algorithm. By leveraging the underlying physics of the problem and the great denoising capabilities of our blind-spot network, our algorithm is shown to outperform standard industry methods while being comparable in terms of computational cost. Moreover, being independent of the acquisition geometry, our method can be easily applied to marine and land data without any significant modification.