[HTML][HTML] Energy-conserving neural network for turbulence closure modeling

T van Gastelen, W Edeling, B Sanderse - Journal of Computational Physics, 2024 - Elsevier
In turbulence modeling, we are concerned with finding closure models that represent the
effect of the subgrid scales on the resolved scales. Recent approaches gravitate towards …

An extended neural ordinary differential equation network with grey system and its applications

F Zhang, X **ao, M Gao - Neurocomputing, 2024 - Elsevier
The neural ordinary differential equation (NODE) has attracted much attention for its
applicability in dynamic system modeling and continuous time series analysis. When the …

Physics-constrained coupled neural differential equations for one dimensional blood flow modeling

H Csala, A Mohan, D Livescu, A Arzani - Computers in Biology and …, 2025 - Elsevier
Background: Computational cardiovascular flow modeling plays a crucial role in
understanding blood flow dynamics. While 3D models provide acute details, they are …

a priori uncertainty quantification of reacting turbulence closure models using Bayesian neural networks

G Pash, M Hassanaly, S Yellapantula - Engineering Applications of …, 2025 - Elsevier
While many physics-based closure model forms have been posited for the sub-filter scale
(SFS) in large eddy simulation (LES), vast amounts of data available from direct numerical …

Machine-learned closure of URANS for stably stratified turbulence: connecting physical timescales & data hyperparameters of deep time-series models

MG Meena, D Liousas, AD Simin, A Kashi… - Machine Learning …, 2024 - iopscience.iop.org
Stably stratified turbulence (SST), a model that is representative of the turbulence found in
the oceans and atmosphere, is strongly affected by fine balances between forces and …

Enhancing Low-Order Discontinuous Galerkin Methods with Neural Ordinary Differential Equations for Compressible Navier--Stokes Equations

S Kang, EM Constantinescu - arxiv preprint arxiv:2310.18897, 2023 - arxiv.org
The growing computing power over the years has enabled simulations to become more
complex and accurate. While immensely valuable for scientific discovery and problem …