3 papers
physics.flu-dyn2026
A physics-constrained machine-learning sub-grid-scale modeling approach for turbulent premixed flames
Seung Won Suh, Jonathan F. MacArt, Luke N. Olson +1
A physics-embedded training framework is used to close the sub-grid-scale dynamics of turbulent premixed flames. The trained model augments the resolved flow equations and is train…
cs.MS2025
MIRGE: An Array-Based Computational Framework for Scientific Computing
Matthias Diener, Matthew J. Smith, Michael T. Campbell +6
MIRGE is a computational approach for scientific computing based on NumPy-like array computation, but using lazy evaluation to recast computation as data-flow graphs, where nodes r…
cs.LG2024
A TVD neural network closure and application to turbulent combustion
Seung Won Suh, Jonathan F MacArt, Luke N Olson +1
Trained neural networks (NN) have attractive features for closing governing equations. There are many methods that are showing promise, but all can fail in cases when small errors…