Machine learning potentials (MLPs) achieve near first-principles accuracy but often fail for atomic environments outside the training distribution. Active learning can mitigate this limitation; however, its application to large-scale simulations is hindered by the prohibitive cost of labeling entire configurations. Here, we develop a D-optimality-driven active learning framework for the neuroevolution potential (NEP) implemented within the GPUMD package, named NEPMaker. Extrapolative atomic environments are identified on-the-fly and embedded into locally periodic structures, where boundary atoms are optimized to remain close to the training distribution. This strategy enables large-scale simulations to directly contribute to dataset construction, significantly reducing extrapolation errors while improving model robustness and transferability. The proposed framework provides a scalable route for constructing reliable machine learning potentials in complex materials systems, including those involving defects, interfaces, and phase transitions.
@article{arxiv.2604.13848,
title = {NEPMaker: Active learning of neuroevolution machine learning potential for large cells},
author = {Junjie Wang and Shuning Pan and Haoting Zhang and Qiuhan Jia and Chi Ding and Zheyong Fan and Jian Sun},
journal= {arXiv preprint arXiv:2604.13848},
year = {2026}
}