An Improved Tandem Neural Network Architecture for Inverse Modeling of Multicomponent Reactive Transport in Porous Media
TLDR
The results show that TNNA‐AUS successfully reduces the inversion bias and improves the computational efficiency and inversion accuracy, compared with the global improvement strategy of adding training samples according to the prior distribution of model parameters.About:
This article is published in Water Resources Research.The article was published on 2021-11-10 and is currently open access. It has received 25 citations till now. The article focuses on the topics: Deep learning.read more
Citations
More filters
Journal ArticleDOI
An Integrated Inversion Framework for Heterogeneous Aquifer Structure Identification with Single-Sample Generative Adversarial Network
Chuanjun Zhan,Zhenxue Dai,Javier Samper,Shangxian Yin,Reza Ershadnia,Xiaoying Zhang,Yanwei Wang,Zhijie Yang,Xiaoyan Luan,Mohamad Reza Soltanian +9 more
TL;DR: In this paper , the authors developed an integrated inversion framework, which combines the geological single-sample generative adversarial network (GeoSinGAN), the deep octave convolution dense residual network (DOCRN), and the iterative local updating ensemble smoother (ILUES), named GeoSinGAN-DOCRN-ILUES, for more efficiently generating heterogeneous aquifer structures.
Journal ArticleDOI
An upscaling approach to predict mine water inflow from roof sandstone aquifers
Lulu Xu,Meifeng Cai,Shun Dong,Shangxian Yin,Ting Xiao,Zhenxue Dai,Yanwei Wang,Mohamad Reza Soltanian +7 more
TL;DR: Wang et al. as discussed by the authors developed a novel upscaling framework to predict roof water inflow by integrating the multiscale hydrogeological properties of roof aquifers, which can guide the development of methods for considering micropores and fractures simultaneously.
Journal ArticleDOI
An integrated experimental design framework for optimizing solute transport monitoring locations in heterogeneous sedimentary media
Zhenxue Dai,Ziqi Ma,Xiaoying Zhang,Junjun Chen,Reza Ershadnia,Xiaoyan Luan,Mohamad Reza Soltanian +6 more
TL;DR: In this article , an integrated framework is developed to guide the monitoring network optimization and duration selection for solute transport in heterogeneous sand tank experiments, which is designed based on entropy and data worth analysis.
Data‐Worth Analysis for Heterogeneous Subsurface Structure Identification With a Stochastic Deep Learning Framework
TL;DR: In this paper , the authors extended a recently developed stage-wise stochastic deep learning inversion framework by coupling it with nonisothermal flow and transport simulations to estimate subsurface structures.
References
More filters
Journal ArticleDOI
Coupling ensemble smoother and deep learning with generative adversarial networks to deal with non-Gaussianity in flow and transport data assimilation
TL;DR: Wang et al. as discussed by the authors proposed to couple ensemble smoother with multiple data assimilation (ES-MDA) with deep learning, which is able to reconstruct the channel structures and reduce the uncertainty of hydraulic head and contaminant concentration predictions.
Posted Content
Multiplexed Supercell Metasurface Design and Optimization with Tandem Residual Networks
Christopher Yeung,Christopher Yeung,Ju-Ming Tsai,Brian King,Benjamin Pham,David Ho,Julia Liang,Mark W. Knight,Aaswath Raman +8 more
TL;DR: This study demonstrates the feasibility of high-dimensional supercell inverse design with deep neural networks, which is applicable to complex nanophotonic structures composed of multiple subunit elements that exhibit coupling.
Journal ArticleDOI
An Adaptive Surrogate Modeling Based on Deep Neural Networks for Large-Scale Bayesian Inverse Problems
Liang Yan,Tao Zhou +1 more
TL;DR: This work presents an adaptive multi-fidelity surrogate modeling framework based on deep neural networks (DNNs), motivated by the facts that the DNNs can potentially handle functions with limited regularity and are powerful tools for high dimensional approximations.
Journal ArticleDOI
Reactive solute transport in an asymmetrical fracture–rock matrix system
Renjie Zhou,Hongbin Zhan +1 more
TL;DR: In this paper, the authors considered the transport problem in a single fracture-rock matrix system with asymmetric distribution of transport properties in the rock matrixes and developed mathematical models to analyze the spatio-temporal concentration and mass distribution in the fracture and rock matrix with the help of Laplace transform technique and de Hoog numerical inverse Laplace algorithm.
Journal ArticleDOI
Flexible and Modular Simultaneous Modeling of Flow and Reactive Transport in Rivers and Hyporheic Zones
TL;DR: A fully coupled model that captures the coupled flow and multicomponent reactive transport processes within both surface and subsurface domains and across their interface, hyporheicFoam, was developed using the open‐source computational platform OpenFOAM.