2 papers
physics.app-ph2026
A Systematic Benchmark of Physics-Informed Neural Network Architectures for the Stiff Poisson-Nernst-Planck System: Adaptive LossWeighting and Multi-Scale Resolution
David Pankaczy, Conrard Giresse Tetsassi Feugmo
The Poisson Nernst Planck PNP system constitutes a canonical stiff coupled PDE problem where the charge density prefactor produces extreme coefficient ratios and the electric doubl…
cond-mat.mtrl-sci2026
Neural Spectral Element Methods for stiff multiphysics PDEs with electrochemical transport benchmarks
Conrard Giresse Tetsassi Feugmo, David Pankaczy
The Neural Spectral Element Method (NSEM) evaluates each network only at fixed Legendre-Gauss-Lobatto quadrature nodes and replaces all derivative calls with precomputed spectral d…