Physics-Informed Neural Network Surrogate for Oxygen Vacancy Dynamics in epitaxial $\mathrm{SrTi}{\mathrm{O}}_3$ on Si memristors via Dynamic Spectral Optimization

Rodion Podorozhny, Nikoleta Theodoropoulou, Jelena Tešić

Physics-informed neural networks (PINNs) offer a promising framework for modeling semiconductor devices, yet standard architectures struggle with severe numerical stiffness and mul…