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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of hydrology (Amsterdam) Jg. 631; S. 130819
Hauptverfasser: Deng, Yaping, Kang, Xueyuan, Ma, Haichun, Qian, Jiazhong, Ma, Lei, Luo, Qiankun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.03.2024
Schlagworte:
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-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•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 data, are employed in the inversion framework to improve the estimation accuracy of fracture networks. Characterization of fracture network is essential for understanding groundwater flow and solute transport, as well as waste storage. Deep-learning based ensemble smoother methods have proven to be effective in estimating hydraulic parameters in porous media. Compared to porous media, fracture fields are highly heterogeneous and typically non-Gaussian distributed, making the estimation of the fracture field from sparse borehole data extremely difficult. In this paper, we developed a joint hydrogeophysical inversion framework to improve the characterization of fracture networks. We first trained a convolutional variational autoencoder (CVAE) network to parameterize the fracture field, and then integrated with the ensemble smoother with multiple data assimilation (ESMDA) method to infer the fracture distribution by incorporating multiple datasets. Two numerical cases with different complexity were considered to assess the ability of the proposed joint inversion framework. The results show that the proposed hydrogeophyscial inversion framework can capture the main features of the fracture field. By integrating both the pressure and SP data, the fracture field can be reconstructed with an improved accuracy and reduced estimation uncertainty.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0022-1694
DOI:10.1016/j.jhydrol.2024.130819