79 citations · 92 across the 11 of their papers we have counts for
11 papers
Neural Networks with Local Converging Inputs (NNLCI) for Solving Conservation Laws, Part II: 2D Problems
Haoxiang Huang, Yingjie Liu, Vigor Yang
In our prior work [arXiv:2109.09316], neural network methods with inputs based on domain of dependence and a converging sequence were introduced for solving one dimensional conserv…
Neural Networks with Inputs Based on Domain of Dependence and A Converging Sequence for Solving Conservation Laws, Part I: 1D Riemann Problems
Haoxiang Huang, Yingjie Liu, Vigor Yang
Recent research works for solving partial differential equations (PDEs) with deep neural networks (DNNs) have demonstrated that spatiotemporal function approximators defined by aut…
Common kernel-smoothed proper orthogonal decomposition (CKSPOD): An efficient reduced-order model for emulation of spatiotemporally evolving flow dynamics
Yu-Hung Chang, Xingjian Wang, Liwei Zhang +4
In the present study, we propose a new surrogate model, called common kernel-smoothed proper orthogonal decomposition (CKSPOD), to efficiently emulate the spatiotemporal evolution…
Thermal interface conductance between aluminum and aluminum oxide: A rigorous test of atomistic level theories
Murali Gopal Muraleedharan, Kiarash Gordiz, Shenghong Ju +3
We report the first ever accurate theoretical prediction of thermal conductance of any material interface. Thermal interfacial conductance of aluminum (Al)-sapphire (α-Al2O3) inter…
Kernel-smoothed proper orthogonal decomposition (KSPOD)-based emulation for prediction of spatiotemporally evolving flow dynamics
Yu-Hung Chang, Liwei Zhang, Xingjian Wang +5
This interdisciplinary study, which combines machine learning, statistical methodologies, high-fidelity simulations, and flow physics, demonstrates a new process for building an ef…
Data-Driven Analysis and Common Proper Orthogonal Decomposition (CPOD)-Based Spatio-Temporal Emulator for Design Exploration
Shiang-Ting Yeh, Xingjian Wang, Chih-Li Sung +5
The present study proposes a data-driven framework trained with high-fidelity simulation results to facilitate decision making for combustor designs. At its core is a surrogate mod…