Machine-learning for electronic structure

Atomic-scale simulations of materials and condensed-matter systems have been transformed by the application of machine learning potentials, that facilitate and reduce greatly the computational cost for predicting their structure and (thermo)dynamics. In order to also determine functional properties, and more in general to extend further the scope of these simulations, it is desirable to develop machine-learning models that target quantities that are more intimately connected with the electronic structure -- the charge density, the electron density of states, the electronic excitations.

I will present a few examples of this kind of models, and discuss in particular how to construct "hybrid" frameworks that combine data-driven elements with physically-motivated components. For example, I will demonstrate the use of a model of the ground-state electronic density of states to perform simulations at finite electron temperature, and the use of a minimal-basis Hamiltonian as an intermediate step in a model architecture targeting excited-state properties.