Abstract

Machine-learning techniques are often applied to perform “end-to-end” predictions, that is to make a black-box estimate of a property of interest using only a coarse description of the corresponding inputs. In contrast, atomic-scale modeling of matter is most useful when it allows to gather a mechanistic insight into the microscopic processes that underlie the behavior of molecules and materials. In this talk I will provide an overview of the progress that has been made combining these two philosophies, using data-driven techniques to build surrogate models of the quantum mechanical behavior of atoms, enabling “bottom-up” simulations that reveal the behavior of matter in realistic conditions with uncompromising accuracy. I will show that data-driven modeling can be rooted in a mathematically rigorous and physically-motivated symmetry-adapted framework, and discuss the benefits of taking a well-principled approach. I will present several examples demonstrating how the combination of machine-learning and atomistic simulations can offer useful insights on the behavior of complex systems, and discuss the challenges towards an integrated modeling framework in which physics-driven and data-driven steps can be combined to improve the accuracy, the computational efficiency and the transferability of predictions, from interatomic potentials to electronic-structure properties.