Two-stage broad learning inversion framework for shear-wave velocity estimation

Xiao-Hui,Yang1,2,3; Peng,Han1,2,3; Zhentao,Yang1,2,3; Xiaofei,Chen1,2,3

2023-02-01

10.1190/GEO2022-0060.1

GEOPHYSICS   影响因子和分区

0016-8033

1942-2156

Shear-wave (S-wave) velocity is considered an essential parameter for the study of the earth, and Rayleigh wave inversion has been widely accepted and used to determine it. Given high -quality measured dispersion curves, the inversion performance depends on the applied optimization algorithm inside the inver-sion process. We propose a novel inversion framework to pro-mote efficient and accurate inversion, i.e., a two-stage broad learning inversion framework (TS-BL). The proposed TS-BL not only inherits the powerful mapping capability and simple con-figured structure of broad learning (BL) network but also makes two significant improvements to better acclimatize itself to Ray-leigh wave inversion. First, TS-BL adopts a two-stage inversion strategy to perform optimizing two times. It does not yield the same search space in the two inversion stages. In the first stage, because the inversion aims to find an approximation rather than the accurate value of model parameters, the difficulty in con-structing the mapping model is reduced by sacrificing accuracy. Then, an effective BL network can be established using smaller sample sizes. In the second stage, the search space becomes much narrower, commencing with the approximation results obtained in the prior stage. This helps the final BL network to easily and quickly model the actual relationship between measured dispersion curves and unknown model parameters. After that, the forward modeling of measurements rather than the validation data set is exploited for tuning the network's hyperparameters. The physical model is superior to the validation data set for se-lecting a suitable network complexity to adapt to the measured dispersion curves because the latter only describes an overall re-lationship. As a result, accurate S-wave velocities can be effi-ciently acquired by using the proposed TS-BL with a low cost of training samples. The efficiency and reliability of TS-BL have been demonstrated in numerical and field data examples.

SCI ; EI

英语

通讯

Key Special Project for Intro- duced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)[GML2019ZD0203] ; Shenzhen Key Laboratory of Deep Offshore Oil and Gas Exploration Technol- ogy[ZDSYS20190902093007855] ; Science and Tech- nology Program of Shenzhen["JCYJ20210324104602006","JCYJ20210324104801004"]

Geochemistry & Geophysics

Geochemistry & Geophysics

WOS:000944291200003

SOC EXPLORATION GEOPHYSICISTS - SEG

20230213358362

Curve fitting ; Dispersion (waves) ; Mapping ; Shear flow ; Shear waves ; Wave propagation

Surveying:405.3 ; Seismology:484 ; Fluid Flow, General:631.1 ; Numerical Methods:921.6 ; Mechanics:931.1

GEOSCIENCES

Web of Science

1.Shenzhen Key Laboratory of Deep Offshore Oil and Gas Exploration Technology, Southern University of Science and Technology, Shenzhen, 518055, China
2.Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), Guangzhou, 511458, China
3.Department of Earth and Space Sciences, Southern University of Science and Technology, Shenzhen, 518055, China

Xiao-Hui,Yang,Peng,Han,Zhentao,Yang,et al. Two-stage broad learning inversion framework for shear-wave velocity estimation[J]. GEOPHYSICS,2023,88(1):WA219-WA237.

Xiao-Hui,Yang,Peng,Han,Zhentao,Yang,&Xiaofei,Chen.(2023).Two-stage broad learning inversion framework for shear-wave velocity estimation.GEOPHYSICS,88(1),WA219-WA237.

Xiao-Hui,Yang,et al."Two-stage broad learning inversion framework for shear-wave velocity estimation".GEOPHYSICS 88.1(2023):WA219-WA237.