Chloé Gauvin-Ndiaye | Searcharxiv

arXiv2024

Mott Transition and Volume Law Entanglement with Neural Quantum States

The interplay between delocalisation and repulsive interactions can cause electronic systems to undergo a Mott transition between a metal and an insulator. Here we use neural network hidden fermion determinantal states (HFDS) to uncover this transition in the disordered, fully-connected Hubbard model. Whilst dynamical mean-field theory (DMFT) provides exact solutions to physical observables of the model in the thermodynamic limit, our method allows us to directly access the wave function for finite system sizes well beyond the reach of exact diagonalisation. We demonstrate how HFDS are able to obtain more accurate results in the metallic regime and in the vicinity of the transition than calculations based on a Matrix Product State (MPS) ansatz, for which the volume law of entanglement exhibited by the system is prohibitive. We use the HFDS method to calculate the energy and double occupancy, the quasi-particle weight and the energy gap and, importantly, the amplitudes of the wave function which provide a novel insight into this model. Our work paves the way for the study of strongly correlated electron systems with neural quantum states.

cond-mat.str-el↗

arXiv2023

Prediction of Large Magnetic Moment Materials With Graph Neural Networks and Random Forests

Magnetic materials are crucial components of many technologies that could drive the ecological transition, including electric motors, wind turbine generators and magnetic refrigeration systems. Discovering materials with large magnetic moments is therefore an increasing priority. Here, using state-of-the-art machine learning methods, we scan the Inorganic Crystal Structure Database (ICSD) of hundreds of thousands of existing materials to find those that are ferromagnetic and have large magnetic moments. Crystal graph convolutional neural networks (CGCNN), materials graph network (MEGNet) and random forests are trained on the Materials Project database that contains the results of high-throughput DFT predictions. For random forests, we use a stochastic method to select nearly one hundred relevant descriptors based on chemical composition and crystal structure. This gives results that are comparable to those of neural networks. The comparison between these different machine learning approaches gives an estimate of the errors for our predictions on the ICSD database. Validating our final predictions by comparisons with available experimental data, we found 15 materials that are likely to have large magnetic moments and have not been yet studied experimentally.

cond-mat.mtrl-sci↗