Work

Data-driven forecasting of nonequilibrium solid-state dynamics

Year: 2023

Type: article

Abstract: 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 multiphysics simulation software and thereby guide the future development of solid-state-based technologies.

Source: Physical review. B./Physical review. B

DOI: 10.1103/physrevb.107.184306

Authors: Stefan Meinecke, Felix Köster, Dominik Christiansen, Kathy Lüdge, Andreas Knorr, Malte Selig

Institutions: Technische Universität Berlin, Technische Universität Ilmenau

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: green

Funders: Deutsche Forschungsgemeinschaft, Technische Universität Berlin

Awards: G1372011745, Plasmonkontrolle mit THz Pulsen, G5363326558, SFB 951: Hybrid Inorganic/Organic Systems (HIOS) for OptoElectronics, G7737404518