arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.01417physics.comp-ph
收藏

为纳米团簇构建机器学习力场

Building machine learning force fields for nanoclusters

Claudio Zeni, Kevin Rossi, Aldo Glielmo, Ádám Fekete, Nicola Gaston, Francesca Baletto, Alessandro De Vita

摘要:

我们评估高斯过程(GP)回归作为一种技术来模拟金属纳米团簇中的原子间力,通过分析一组19个原子的Ni团簇结构上的2-体,3-体和多体核函数的性能。我们发现,2体GP内核未能提供忠实的力估计,尽管成功的散装镍系统。然而,即使对于小的训练数据集,三体核和多体核都在$\sim$ 0.1 eV/ $\textÅ$平均误差内预测力,并且即使在样品外、高温结构上也实现高精度。虽然在相同结构上的训练和测试总是提供令人满意的准确性,但在不同结构上的交叉测试会导致更高的预测误差,从而造成外推问题。这可以通过在包含多个结构的数据库上进行异构训练来解决,从而在通用性和整体准确性之间实现良好的权衡。从以这种方式训练的三体核开始,我们建立了一个有效的非参数三体力场,可以按照新开发的方案准确预测有限温度下的结构特性[Glielmo et al. PRB 97,184307(2018)]。我们用它来评估镍$_{19}$纳米团簇的热稳定性在一个完整的从头计算的分数成本。

英文摘要:

We assess Gaussian process (GP) regression as a technique to model interatomic forces in metal nanoclusters by analysing the performance of 2-body, 3-body and many-body kernel functions on a set of 19-atom Ni cluster structures. We find that 2-body GP kernels fail to provide faithful force estimates, despite succeeding in bulk Ni systems. However, both 3- and many-body kernels predict forces within a $\sim$0.1 eV/$\textÅ$ average error even for small training datasets, and achieve high accuracy even on out-of-sample, high temperature, structures. While training and testing on the same structure always provides satisfactory accuracy, cross-testing on dissimilar structures leads to higher prediction errors, posing an extrapolation problem. This can be cured using heterogeneous training on databases that contain more than one structure, which results in a good trade-off between versatility and overall accuracy. Starting from a 3-body kernel trained this way, we build an efficient non-parametric 3-body force field that allows accurate prediction of structural properties at finite temperatures, following a newly developed scheme [Glielmo et al. PRB 97, 184307 (2018)]. We use this to assess the thermal stability of Ni$_{19}$ nanoclusters at a fractional cost of full ab initio calculations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑