Automated training of neural-network interatomic potentials

Neural-network interatomic potentials (NNIPs) have transformed atomistic simulations, by enabling molecular dynamics simulations with near ab initio accuracy at reduced computational costs and improved scalability. Despite these advances, crafting NNIPs remains a complex task, demanding specialized expertise in both machine learning and electronic structure calculations. Here, we introduce an automated, open-source, and user-friendly workflow that streamlines the creation of accurate NNIPs. Our approach integrates density-functional theory with classical molecular dynamics to systematically explore the potential energy landscape using random distortions, strain, interfaces, neutral vacancies, clusters, and molecular dynamics trajectories at varied temperatures and pressures. We leverage active learning combined with on-the-fly calibration of committee disagreement against true errors to ensure reliability. The method is validated on the fully automated training of a NNIP for a diverse set of carbon allotropes, reaching state-of-the-art accuracy and data efficiency. This platform democratizes NNIP development, empowering users to achieve high-precision simulations with minimal human intervention.