Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

LARGE SCALE RANDOMIZED LEARNING GUIDED BY PHYSICAL LAWS WITH APPLICATIONS IN FULL WAVEFORM INVERSION

Abstract: 

The rapid convergence rate, high fidelity learning outcome and low computational cost are key targets in solving the learning problem of the complex physical system. Guided
by physical laws of wave propagation, in full waveform inversion (FWI), we learn the subsurface images through optimizing the media velocity model in a large scale non-linear problem. In this paper, we combine randomized subsampling techniques with a second-order optimization algorithm to propose the Sub-Sampled Newton (SSN) method for learning velocity model of FWI. By incorporating the curvature information, SSN preserves comparable convergence rate to Newtons method and significantly reduces the iteration cost by approximating the Hessian matrix through a non-uniform subsampling scheme. The numerical experiments demonstrate that the proposed SSN method has a faster convergence rate, and achieves a more accurate velocity model in terms of mean squared error than commonly used methods.

up
0 users have voted:

Paper Details

Authors:
Rui Xie, Fangyu Li, Zengyan Wang, WenZhan Song
Submitted On:
18 November 2018 - 4:23pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Fangyu Li
Paper Code:
1208
Document Year:
2018
Cite

Document Files

GlobalSIP2018_FWI 16.07.19.pdf

(18)

Subscribe

[1] Rui Xie, Fangyu Li, Zengyan Wang, WenZhan Song, "LARGE SCALE RANDOMIZED LEARNING GUIDED BY PHYSICAL LAWS WITH APPLICATIONS IN FULL WAVEFORM INVERSION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3680. Accessed: Jul. 17, 2019.
@article{3680-18,
url = {http://sigport.org/3680},
author = {Rui Xie; Fangyu Li; Zengyan Wang; WenZhan Song },
publisher = {IEEE SigPort},
title = {LARGE SCALE RANDOMIZED LEARNING GUIDED BY PHYSICAL LAWS WITH APPLICATIONS IN FULL WAVEFORM INVERSION},
year = {2018} }
TY - EJOUR
T1 - LARGE SCALE RANDOMIZED LEARNING GUIDED BY PHYSICAL LAWS WITH APPLICATIONS IN FULL WAVEFORM INVERSION
AU - Rui Xie; Fangyu Li; Zengyan Wang; WenZhan Song
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3680
ER -
Rui Xie, Fangyu Li, Zengyan Wang, WenZhan Song. (2018). LARGE SCALE RANDOMIZED LEARNING GUIDED BY PHYSICAL LAWS WITH APPLICATIONS IN FULL WAVEFORM INVERSION. IEEE SigPort. http://sigport.org/3680
Rui Xie, Fangyu Li, Zengyan Wang, WenZhan Song, 2018. LARGE SCALE RANDOMIZED LEARNING GUIDED BY PHYSICAL LAWS WITH APPLICATIONS IN FULL WAVEFORM INVERSION. Available at: http://sigport.org/3680.
Rui Xie, Fangyu Li, Zengyan Wang, WenZhan Song. (2018). "LARGE SCALE RANDOMIZED LEARNING GUIDED BY PHYSICAL LAWS WITH APPLICATIONS IN FULL WAVEFORM INVERSION." Web.
1. Rui Xie, Fangyu Li, Zengyan Wang, WenZhan Song. LARGE SCALE RANDOMIZED LEARNING GUIDED BY PHYSICAL LAWS WITH APPLICATIONS IN FULL WAVEFORM INVERSION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3680