Skip to main navigation Skip to search Skip to main content

OPTIMAL TRANSPORT WITH A NEW PREPROCESSING FOR DEEP-LEARNING FULL WAVEFORM INVERSION

  • Hao Zhang*
  • , Jianwei Ma
  • *Corresponding author for this work
  • School of Mathematics, Harbin Institute of Technology
  • Peking University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Full waveform inversion (FWI) has been implemented using deep learning techniques as an analogue recurrent neural network for geophysics. However, the cycle-skipping issue, from which the conventional FWI suffers, troubles the deep-learning aided FWI as well if the least-square loss function is used to measure the misfit between observed and synthetic data. We propose to use a Wasserstein distance loss function combined with a newly designed preprocessing transform, named integration affine scaling, for the inversion. This transform transfers the seismograms into probability densities, and significantly improves the inversion results. Numerical results show that the proposed method outperforms its counterparts in mitigating cycle-skipping, in comparison with other loss functions including the least-square, the absolute, and the quadratic Wasserstein distance losses.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PublisherIEEE Computer Society
Pages1446-1450
Number of pages5
ISBN (Electronic)9781665496209
DOIs
StatePublished - 2022
Externally publishedYes
Event29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France
Duration: 16 Oct 202219 Oct 2022

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference29th IEEE International Conference on Image Processing, ICIP 2022
Country/TerritoryFrance
CityBordeaux
Period16/10/2219/10/22

Keywords

  • Optimal transport
  • deep learning
  • full waveform inversion
  • integration affine transform
  • loss functions

Fingerprint

Dive into the research topics of 'OPTIMAL TRANSPORT WITH A NEW PREPROCESSING FOR DEEP-LEARNING FULL WAVEFORM INVERSION'. Together they form a unique fingerprint.

Cite this