3 papers
physics.flu-dyn2026
Finite basis physics-informed neural networks with hard constraints for viscous fluid flow in highly perforated domains
Jeeeun Lee, Denis Korolev, Miro Duhovic +1
In this work, viscous fluid flow governed by the Stokes equations in highly perforated domains is studied using physics-informed neural networks (PINNs). Perforated microstructures…
math.OC2026
Layerwise goal-oriented adaptivity for neural ODEs: an optimal control perspective
Michael Hintermüller, Michael Hintermüller, Michael Hinze +1
In this work, we propose a novel layerwise adaptive construction method for neural network architectures. Our approach is based on a goal--oriented dual-weighted residual technique…
cs.LG2025
Hybrid machine learning based scale bridging framework for permeability prediction of fibrous structures
Denis Korolev, Tim Schmidt, Dinesh K. Natarajan +4
This study introduces a hybrid machine learning-based scale-bridging framework for predicting the permeability of fibrous textile structures. By addressing the computational challe…