NuSPAN: A Proximal Average Network for Nonuniform Sparse Model -- Application to Seismic Reflectivity Inversion
arXiv:2105.00003
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.
arXiv comment16 pages, 13 figures. This article builds on arXiv:2104.04704. Additions to the introductory sections; references added; results unchanged
References in corpus (10)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Nearly unbiased variable selection under minimax concave penalty
- Sparse Regularization via Convex Analysis
- Extrapolated full waveform inversion with deep learning
- Learned Convolutional Sparse Coding
- Seismic Full-Waveform Inversion Using Deep Learning Tools and Techniques
- Deep Residual Autoencoders for Expectation Maximization-inspired Dictionary Learning
- Deep Recurrent Architectures for Seismic Tomography
- Deep Sparse Coding Using Optimized Linear Expansion of Thresholds
- DuRIN: A Deep-unfolded Sparse Seismic Reflectivity Inversion Network