Deep convolutional encoder‐decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media

S Mo, Y Zhu, N Zabaras, X Shi… - Water Resources …, 2019 - Wiley Online Library
Surrogate strategies are used widely for uncertainty quantification of groundwater models in
order to improve computational efficiency. However, their application to dynamic multiphase …

Deep autoregressive neural networks for high‐dimensional inverse problems in groundwater contaminant source identification

S Mo, N Zabaras, X Shi, J Wu - Water Resources Research, 2019 - Wiley Online Library
Identification of a groundwater contaminant source simultaneously with the hydraulic
conductivity in highly heterogeneous media often results in a high‐dimensional inverse …

An analysis platform for multiscale hydrogeologic modeling with emphasis on hybrid multiscale methods

TD Scheibe, EM Murphy, X Chen, AK Rice… - …, 2015 - Wiley Online Library
One of the most significant challenges faced by hydrogeologic modelers is the disparity
between the spatial and temporal scales at which fundamental flow, transport, and reaction …

Adaptive sparse polynomial chaos expansions for uncertainty propagation and sensitivity analysis

G Blatman - 2009 - inis.iaea.org
Mathematical models are widely used in many science disciplines, such as physics, biology
and meteorology. They are aimed at better understanding and explaining real-world …

Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non‐Gaussian hydraulic conductivities

S Mo, N Zabaras, X Shi, J Wu - Water Resources Research, 2020 - Wiley Online Library
Inverse modeling for the estimation of non‐Gaussian hydraulic conductivity fields in
subsurface flow and solute transport models remains a challenging problem. This is mainly …

Efficient B ayesian experimental design for contaminant source identification

J Zhang, L Zeng, C Chen, D Chen… - Water Resources …, 2015 - Wiley Online Library
In this study, an efficient full Bayesian approach is developed for the optimal sampling well
location design and source parameters identification of groundwater contaminants. An …

Physics-informed CoKriging: A Gaussian-process-regression-based multifidelity method for data-model convergence

X Yang, D Barajas-Solano, G Tartakovsky… - Journal of …, 2019 - Elsevier
In this work, we propose a new Gaussian process regression (GPR)-based multifidelity
method: physics-informed CoKriging (CoPhIK). In CoKriging-based multifidelity methods, the …

Kernel principal component analysis for stochastic input model generation

X Ma, N Zabaras - Journal of Computational Physics, 2011 - Elsevier
Stochastic analysis of random heterogeneous media provides useful information only if
realistic input models of the material property variations are used. These input models are …

A sparse grid based Bayesian method for contaminant source identification

L Zeng, L Shi, D Zhang, L Wu - Advances in Water Resources, 2012 - Elsevier
In this study, an efficient Bayesian method based on the adaptive sparse grid interpolation is
used to solve the contaminant source identification problem. The unknown parameters that …

A meshfree peridynamic model for brittle fracture in randomly heterogeneous materials

Y Fan, H You, X Tian, X Yang, X Li, N Prakash… - Computer Methods in …, 2022 - Elsevier
In this work we aim to develop a unified mathematical framework and a reliable
computational approach to model the brittle fracture in heterogeneous materials with …