Mainz 2026 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
A: Fachverband Atomphysik
A 34: Correlation Phenomena
A 34.2: Vortrag
Donnerstag, 5. März 2026, 14:45–15:00, N 25
Graph neural network models for predicting local electronic properties of disordered correlated electron systems — •Konrad Koenigsmann1, Ho Jang1, Peter Schauss2, and Gia-Wei Chern1 — 1Department of Physics, University of Virginia, 382 McCormick Road, Charlottesville, VA 22904, USA — 2Institut für Quantenphysik, Universität Hamburg, Luruper Chaussee 149, 22761 Hamburg, Germany
The rapid development of machine learning (ML) methods has opened up many new avenues of research in the field of condensed matter physics by bridging the tradeoff between efficiency and accuracy that is inherent to many numerical methods used for multiscale simulations. Here, we present a scalable ML model that can predict local and short-range electronic and spin properties of disordered correlated electron systems. A novel feature of our model is the use of a graph neural network (GNN). While GNNs have achieved considerable success in a number of fields including quantum chemistry and materials science, their applications in condensed matter physics remain largely unexplored. We tested the model by training on small-system-size determinant quantum Monte Carlo (DQMC) simulations of the square-lattice Anderson-Hubbard model, a paradigmatic system for studying the interplay between disorder and correlations. We find that the model is able to reasonably predict the local and short-range electronic and spin properties of the system. Our results demonstrate the potential and effectiveness of using GNNs for multiscale modeling of disordered correlated electron and other condensed matter systems.
Keywords: Graph neural network; Disordered correlated electronic systems; Determinant Quantum Monte Carlo; Machine learning; Hubbard model