14 citations · 21 across the 4 of their papers we have counts for
4 papers
A Gaussian-based spatially weighted loss formulation for Physics-Informed Neural Networks with Shocks
Kheir-eddine Otmani, Abdelhalim Azzouz, Nourelhouda Groun +1
Physics-informed neural networks (PINNs) often struggle to resolve shocks because smooth neural representations and globally averaged residual losses tend to underemphasize localiz…
Accelerating high order discontinuous Galerkin solvers through a clustering-based viscous/turbulent-inviscid domain decomposition
Kheir-Eddine Otmani, Andrés Mateo-Gabín, Gonzalo Rubio +1
We explore the unsupervised clustering technique introduced in [25] to identify viscous/turbulent from inviscid regions in incompressible flows. The separation of regions allows so…
Machine learning adaptation for laminar and turbulent flows: applications to high order discontinuous Galerkin solvers
Kenza Tlales, Kheir-Eddine Otmani, Gerasimos Ntoukas +2
We present a machine learning-based mesh refinement technique for steady and unsteady flows. The clustering technique proposed by Otmani et al. arXiv:2207.02929 [physics.flu-dyn] i…
towards a robust detection of viscous and turbulent flow regions using unsupervised machine learning
Kheir-Eddine Otmani, Gerasimos Ntoukas, Esteban Ferrer
We propose an invariant feature space for the detection of viscous dominated and turbulent regions (i.e., boundary layers and wakes). The developed methodology uses the principal i…