Analysis of Seismic Inversion with Optimal Transportation and Softplus Encoding

09/09/2020
by   Lingyun Qiu, et al.
0

This paper is devoted to theoretical and numerical investigation of the local minimum issue in seismic full waveform inversion (FWI). This paper provides a mathematical analysis of optimal transportation (OT) type objective function's differentiability and proves that the gradient obtained in the adjoint-state method does not depend on the particular choice of the Kantorovich potentials. A novel approach using the softplus encoding method is presented to generalize and impose the OT metric on FWI. This approach improves the convexity of the objective function and mitigates the cycle-skipping problem. The effectiveness of the proposed method is demonstrated numerically on an inversion task with the benchmark Marmousi model.

READ FULL TEXT

Authors

page 12

page 14

page 15

page 16

01/31/2020

Optimal Transport Based Seismic Inversion: Beyond Cycle Skipping

Full waveform inversion (FWI) is today a standard process for the invers...
01/10/2020

Generalized L_p-norm joint inversion of gravity and magnetic data using cross-gradient constraint

A generalized unifying approach for L_p-norm joint inversion of gravity ...
02/08/2020

A data-driven choice of misfit function for FWI using reinforcement learning

In the workflow of Full-Waveform Inversion (FWI), we often tune the para...
10/22/2020

MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery

To address the issue that deep neural networks (DNNs) are vulnerable to ...
03/03/2022

Coupling Deep Learning with Full Waveform Inversion

Full waveform inversion (FWI) aims at reconstructing unknown physical co...
12/31/2021

Large-scale focusing joint inversion of gravity and magnetic data with Gramian constraint

A fast algorithm for the large-scale joint inversion of gravity and magn...
04/05/2020

Nonlinear Function Inversion using k-vector

This work introduces a general numerical technique to invert one dimensi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.