Quantum-mechanically accurate reactive molecular dynamics (MD) at the scale of billions of atoms has been achieved for the heterogeneous catalytic system of H2/Pt(111) using the FLARE Bayesian force field. This achievement provides accelerated time-to-solution from first principles, with Bayesian active learning enabling efficient and autonomous training of the machine learning model. The resulting model is then deployed in LAMMPS on GPUs using the Kokkos performance portability library. The Bayesian force field provides quantitative uncertainty of predictions on every atomic environment, critical for detecting configurations in large reactive simulations that are outside of the training set. Scaling benchmarks were performed using real-application MD of the H2/Pt(111) heterogeneous catalysis on the Summit supercomputer, with simulations reaching 0.5 trillion atoms on 4556 GPU nodes.
@article{arxiv.2204.12573,
title = {Micron-scale heterogeneous catalysis with Bayesian force fields from first principles and active learning},
author = {Anders Johansson and Yu Xie and Cameron J. Owen and Jin Soo Lim and Lixin Sun and Jonathan Vandermause and Boris Kozinsky},
journal= {arXiv preprint arXiv:2204.12573},
year = {2022}
}