We present a data-driven approach to efficiently approximate nonlinear transient dynamics in solid-state systems. Our proposed machine-learning model combines a dimensionality reduction stage with a nonlinear vector autoregression scheme. We report an outstanding time-series forecasting performance combined with an easy to deploy model and an inexpensive training routine. Our results are of great relevance as they have the potential to massively accelerate multi-physics simulation software and thereby guide to future development of solid-state based technologies.
@article{arxiv.2402.13685,
title = {Data-Driven Forecasting of Non-Equilibrium Solid-State Dynamics},
author = {Stefan Meinecke and Felix Köster and Dominik Christiansen and Kathy Lüdge and Andreas Knorr and Malte Selig},
journal= {arXiv preprint arXiv:2402.13685},
year = {2024}
}
Comments
The simulation code and the regression code is available on GitHub under MIT license (https://github.com/stmeinecke/derrom)