Fronzi Marco, Amos Roger D, Kobayashi Rika
School of Chemical and Biomedical Engineering, University of Melbourne, Parkville, VIC 3010, Australia.
School of Mathematical and Physical Sciences, University of Technology Sydney, Ultimo, NSW 2007, Australia.
Nanomaterials (Basel). 2023 Jun 9;13(12):1832. doi: 10.3390/nano13121832.
We analyse the efficacy of machine learning (ML) interatomic potentials (IP) in modelling gold (Au) nanoparticles. We have explored the transferability of these ML models to larger systems and established simulation times and size thresholds necessary for accurate interatomic potentials. To achieve this, we compared the energies and geometries of large Au nanoclusters using VASP and LAMMPS and gained better understanding of the number of VASP simulation timesteps required to generate ML-IPs that can reproduce the structural properties. We also investigated the minimum atomic size of the training set necessary to construct ML-IPs that accurately replicate the structural properties of large Au nanoclusters, using the LAMMPS-specific heat of the Au147 icosahedral as reference. Our findings suggest that minor adjustments to a potential developed for one system can render it suitable for other systems. These results provide further insight into the development of accurate interatomic potentials for modelling Au nanoparticles through machine learning techniques.
我们分析了机器学习（ML）原子间势（IP）在模拟金（Au）纳米颗粒方面的功效。我们探索了这些ML模型对更大系统的可转移性，并确定了准确的原子间势所需的模拟时间和尺寸阈值。为了实现这一点，我们使用VASP和LAMMPS比较了大型金纳米团簇的能量和几何结构，并更好地理解了生成能够再现结构特性的ML-IP所需的VASP模拟时间步长数量。我们还以Au147二十面体的LAMMPS比热为参考，研究了构建能够准确复制大型金纳米团簇结构特性的ML-IP所需训练集的最小原子尺寸。我们的研究结果表明，对为一个系统开发的势进行微小调整可以使其适用于其他系统。这些结果为通过机器学习技术开发用于模拟金纳米颗粒的准确原子间势提供了进一步的见解。
