7 papers
TorchNEP: Ultra-Efficient and Accurate Training of Neuroevolution Potentials
Yong-Chao Wu, Xiaoya Chang, Tero Mäkinen +5
Neuroevolution Potential (NEP) is one of the most efficient machine-learned interatomic potential frameworks for large-scale atomistic simulations. However, its original training s…
NEPMaker: Active learning of neuroevolution machine learning potential for large cells
Junjie Wang, Shuning Pan, Haoting Zhang +4
Machine learning potentials (MLPs) achieve near first-principles accuracy but often fail for atomic environments outside the training distribution. Active learning can mitigate thi…
GPU-MetaD: Full-Life-Cycle GPU Accelerated Metadynamics with Machine Learning Potentials
Haoting Zhang, Qiuhan Jia, Zhennan Zhang +6
Large-scale molecular dynamics simulations with high accuracy have been increasingly popular for their capability to bridge the gap between atomistic modeling and mesoscale phenome…
GPUMDkit: A User-Friendly Toolkit for GPUMD and NEP
Zihan Yan, Denan Li, Xin Wu +20
Machine-learned interatomic potentials have revolutionized molecular dynamics simulations by providing quantum-mechanical accuracy at empirical-potential speeds. The graphics proce…
NEP-CG and NEP-AACG: Efficient coarse-grained and multiscale all-atom-coarse-grained neuroevolution potentials
Zheyong Fan, Wenjun Zhang, Zhenhao Zhang +3
Machine-learned coarse-grained (CG) models often suffer from noisy training data, limiting their accuracy and transferability. We propose a method to generate low-noise training da…
qNEP: A highly efficient neuroevolution potential with dynamic charges for large-scale atomistic simulations
Zheyong Fan, Benrui Tang, Esmée Berger +13
Although electrostatics can be incorporated into machine-learned interatomic potentials, existing approaches are computationally very demanding, limiting large-scale, long-time sim…