A Machine-Learning Surrogate Model for ab initio Electronic Correlations at Extreme Conditions

2021/04/07 by Tobias Dornheim, Zhandos Moldabekov, Dornheim, Tobias +4
Earth and Planetary Sciences · Physics and Astronomy · #Atomic and Subatomic Physics Research #Computational Physics (physics.comp-ph) #FOS: Physical sciences #High-pressure geophysics and materials #Quantum, superfluid, helium dynamics #physics.comp-ph

paper · pdf · doi:10.48550/arxiv.2104.02941

arxiv created 2021/04/07 · openalex publication_date 2021/04/07 · arxiv updated 2021/04/08 · openalex created_date 2021/04/13 · openalex updated_date 2026/07/28

Abstract

The electronic structure in matter under extreme conditions is a challenging complex system prevalent in astrophysical objects and highly relevant for technological applications. We show how machine-learning surrogates in terms of neural networks have a profound impact on the efficient modeling of matter under extreme conditions. We demonstrate the utility of a surrogate model that is trained on ab initio quantum Monte Carlo data for various applications in the emerging field of warm dense matter research.

Citations

• Path integrals in the theory of condensed helium

Related

• Machine learning for many-body physics: efficient solution of dynamical mean-field theory
• Machine Learning Electronic Structure Methods Based On The One-Electron Reduced Density Matrix
• Neural networks in quantum many-body physics: a hands-on tutorial
• Equivariant Electronic Hamiltonian Prediction with Many-Body Message Passing
• Learning Density Functionals from Noisy Quantum Data