Machine learning foundation interaction models for digital twins of materials

Discovery and understanding of next-generation materials requires a challenging combination of the high accuracy of first-principles calculations with the ability to reach large size and time scales. We pursue a multi-tier development strategy in which machine learning algorithms are combined with exact physical symmetries and constraints to significantly accelerate computations of electronic structure and atomistic dynamics. First, current DFT approximations fall short of the required accuracy and efficiency for predictive calculations of defect properties, band gaps, stability and electrochemical potentials of materials for energy storage and conversion. To advance the capability of DFT we introduce non-local charge density descriptors that satisfy exact scaling constraints and learn exchange functionals called CIDER. These models are orders of magnitude faster in self-consistent calculations for solids than hybrid functionals but similar in accuracy. On a different level, we accelerate MD simulations by using machine learning to construct generalized potential and free energy functions with arbitrary nonlinear dependence on external fields and temperature. This framework enables learning and prediction of dielectric and vibrational response properties and coarse-grained free energies. We demonstrate these methods via first principles ML MD simulations of dynamics of phase transformations, heterogeneous reactions, ferroelectric transitions, nuclear quantum effects, and soft materials.