Machine Learning of Reactive Potentials

In the past two decades, machine learning potentials (MLPs) have driven significant developments in chemical, biological and material sciences. The construction and training of MLPs enables fast and accurate simulations and analysis on thermodynamic and kinetic properties. This review focuses on the applications of MLPs to reaction systems with consideration of bond breaking and formation. We review the development of MLP models, primarily with neural network and kernel-based algorithms, and recent applications of reactive MLPs (RMLPs) to systems at different scales. We will show how RMLPs are constructed and how they speed up the calculation of reactive dynamics and facilitate study of reaction trajectories, reaction rates, free energy calculations, and many other calculations. Different data sampling strategies applied in building RMLPs are also discussed with a focus on how to collect structures for rare events and how to further improve the performance with active learning.