NuSPAN: A Proximal Average Network for Nonuniform Sparse Model -- Application to Seismic Reflectivity Inversion

TL;DR

This paper introduces NuSPAN, a novel neural network architecture based on proximal average strategies for nonuniform sparse signal deconvolution, specifically applied to seismic reflectivity inversion, demonstrating improved accuracy on synthetic and real data.

Contribution

The paper presents a learnable proximal average network that combines convex and non-convex regularizers for seismic deconvolution, advancing sparse modeling techniques.

Findings

Effective on synthetic 1-D seismic traces

Outperforms benchmark techniques on 2-D wedge models

Validates on real 3-D seismic data from Penobscot survey

Abstract

We solve the problem of sparse signal deconvolution in the context of seismic reflectivity inversion, which pertains to high-resolution recovery of the subsurface reflection coefficients. Our formulation employs a nonuniform, non-convex synthesis sparse model comprising a combination of convex and non-convex regularizers, which results in accurate approximations of the l0 pseudo-norm. The resulting iterative algorithm requires the proximal average strategy. When unfolded, the iterations give rise to a learnable proximal average network architecture that can be optimized in a data-driven fashion. We demonstrate the efficacy of the proposed approach through numerical experiments on synthetic 1-D seismic traces and 2-D wedge models in comparison with the benchmark techniques. We also present validations considering the simulated Marmousi2 model as well as real 3-D seismic volume data acquired from the Penobscot 3D survey off the coast of Nova Scotia, Canada.