Machine learning is emerging as a powerful tool for emulating electronic structure calculations. I will discuss recent work in building interatomic potentials relevant to chemistry, materials science, and biophysics applications. A key idea is active learning, in which the training data is iteratively collected to address weaknesses of the ML model. This approach can achieve a surprising level of transferability, as will be demonstrated with a case study for elemental aluminum.

About the speaker:
Kipton Barros has interests in computational physics, applied math, and computer science, and currently works in the Physics and Chemistry and Materials group at Los Alamos National Lab. A recent focus is applying machine learning to accelerate simulations and scientific discovery. Over the past few years, collaborations have spanned topics such as seismology, molecular dynamics simulation, fluid dynamics, and correlated electron physics.