Leveraging machine learning in porous media

M Delpisheh, B Ebrahimpour, A Fattahi… - Journal of Materials …, 2024 - pubs.rsc.org
The emergence of artificial intelligence (AI) and, more particularly, machine learning (ML),
has had a significant impact on engineering and the fundamental sciences, resulting in …

Physics-informed graph convolutional neural network for modeling fluid flow and heat convection

JZ Peng, Y Hua, YB Li, ZH Chen, WT Wu, N Aubry - Physics of Fluids, 2023 - pubs.aip.org
This paper introduces a novel surrogate model for two-dimensional adaptive steady-state
thermal convection fields based on deep learning technology. The proposed model aims to …

Propagating input uncertainties into parameter uncertainties and model prediction uncertainties—A review

K Abdi, B Celse, K McAuley - The Canadian Journal of …, 2024 - Wiley Online Library
A review of uncertainty quantification techniques is provided for a variety of situations
involving uncertainties in model inputs (independent variables). The situations of interest are …

Leak detection and localization in water distribution networks using conditional deep convolutional generative adversarial networks

MM Rajabi, P Komeilian, X Wan, R Farmani - Water Research, 2023 - Elsevier
This paper explores the use of 'conditional convolutional generative adversarial
networks'(CDCGAN) for image-based leak detection and localization (LD&L) in water …

Physics-informed graph convolutional neural network for modeling geometry-adaptive steady-state natural convection

JZ Peng, N Aubry, YB Li, M Mei, ZH Chen… - International Journal of …, 2023 - Elsevier
This paper presents a novel deep learning-based surrogate model for steady-state natural
convection problem with variable geometry. Traditional deep learning based surrogate …

A physics-informed neural networks modeling with coupled fluid flow and heat transfer–Revisit of natural convection in cavity

Z Hashemi, M Gholampour, MC Wu, TY Liu… - … Communications in Heat …, 2024 - Elsevier
The physics-informed neural networks (PINNs) method offers a mesh-free approach for
solving partial differential equations, converting the task into an optimization problem based …

Dynamic compact thermal models for skin temperature prediction of portable electronic devices based on convolution and fitting methods

H Liu, J Yu, R Wang - International Journal of Heat and Mass Transfer, 2023 - Elsevier
In most portable electronic devices, besides the temperature of multiple heat sources, ie
junction temperature, the temperature of the enclosure, ie skin temperature, should also be …

A mixed pressure-velocity formulation to model flow in heterogeneous porous media with physics-informed neural networks

F Lehmann, M Fahs, A Alhubail, H Hoteit - Advances in Water Resources, 2023 - Elsevier
Abstract Current implementations of Physics Informed Neural Networks (PINNs) can
experience convergence problems in simulating fluid flow in porous media with highly …

[HTML][HTML] Predicting multiphase flow behavior of methane in shallow unconfined aquifers using conditional deep convolutional generative adversarial network

R Ershadnia, F Moeini, SA Hosseini, Z Dai… - Journal of …, 2024 - Elsevier
Numerical modeling is an essential tool for geoscience applications involving multiphase
flow behavior. Performing numerical simulation is, however, computationally intensive due …

Modeling transient natural convection in heterogeneous porous media with Convolutional Neural Networks

AG Virupaksha, T Nagel, F Lehmann, MM Rajabi… - International Journal of …, 2024 - Elsevier
Abstract Convolutional Neural Networks (CNNs) are gaining significant attention in
applications related to coupled flow and transfer processes in porous media, especially …