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 discuss two ways by which physical-chemical ideas can be integrated into a machine-learning framework.
One way involves using physical priors, such as smoothness or symmetry of the structure-property relations, to inform the mathematical structure of a generic ML approximation. The other entails a deeper level of integration, in which explicit physics-based models and approximations are built into the model architecture.
I will discuss several examples of the application of these ideas, from the calculation of excited states of molecules to the design of high-entropy alloys for catalysis, emphasizing both the accuracy and the interpretability that can be achieved with a hybrid modeling approach.