Characterization of discrete fracture networks with deep-learning based hydrogeophysical inversion

•A deep-learning based parameterization method is utilized to map high-dimensional fracture parameters space into low-dimensional latent variables.•A joint inversion framework (CVAE-ESMDA) is developed to characterize the fracture networks.•Multiple data types, including pressure and self-potential...

Full description

Bibliographic Details

Published in:	Journal of hydrology (Amsterdam) Vol. 631; p. 130819
Main Authors:	Deng, Yaping, Kang, Xueyuan, Ma, Haichun, Qian, Jiazhong, Ma, Lei, Luo, Qiankun
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.03.2024
Subjects:	Convolutional variational autoencoder Data assimilation data collection Deep learning Fracture network groundwater flow Hydrogeophysical inversion solutes uncertainty Deep learning Hydrogeophysical inversion Fracture network Convolutional variational autoencoder Data assimilation
ISSN:	0022-1694
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!