Improved impedance inversion by the iterated graph Laplacian

TL;DR

This paper presents an iterative, graph Laplacian-based regularization method that improves acoustic impedance inversion accuracy and robustness, integrating classical and deep learning approaches with structural prior information.

Contribution

The paper introduces a novel iterative framework combining graph Laplacian regularization with initial estimates from classical or neural methods for seismic impedance inversion.

Findings

Rapid convergence and improved accuracy over initial estimates.

Enhanced robustness to noise in seismic data.

Validated on synthetic and real datasets across various noise levels.

Abstract

We introduce a data-adaptive inversion method that integrates classical or deep learning-based approaches with iterative graph Laplacian regularization, specifically targeting acoustic impedance inversion - a critical task in seismic exploration. Our method initiates from an impedance estimate derived using either traditional inversion techniques or neural network-based methods. This initial estimate guides the construction of a graph Laplacian operator, effectively capturing structural characteristics of the impedance profile. Utilizing a Tikhonov-inspired variational framework with this graph-informed prior, our approach iteratively updates and refines the impedance estimate while continuously recalibrating the graph Laplacian. This iterative refinement shows rapid convergence, increased accuracy, and enhanced robustness to noise compared to initial reconstructions alone. Extensive validation performed on synthetic and real seismic datasets across varying noise levels confirms the effectiveness of our method. Performance evaluations include four initial inversion methods: two classical techniques and two neural networks - previously established in the literature.