Pair-distribution-function guided optimization of fingerprints for atom-centered neural network potentials
Pair-distribution-function guided optimization of fingerprints for atom-centered neural network potentials
复制标题
DOI：
10.1063/5.0007391
复制
发表时间：
2020-06-14
影响因子：
4.4
通讯作者：
Henkelman, Graeme
中科院分区：
文献类型：
--
作者：
Li, Lei;Li, Hao;Henkelman, Graeme
原子为中心的神经网络（ANN）的潜力已经显示出在计算模拟的承诺，并被认为是有效的和足够准确的描述系统，涉及键的形成和断裂。发展ANN潜力的关键步骤是将原子坐标表示为神经网络的合适输入，通常被描述为指纹。人工神经网络潜力的准确性和效率强烈依赖于这些指纹的选择。在这里，我们提出了一个原子指纹的优化策略，以提高性能的人工神经网络潜力。具体地，一组指纹被优化以在f（*）g空间中拟合一组预先选择的模板函数，其中f和g是每种类型的原子间相互作用的指纹和配对分布函数（例如，一对或三体）。有了这样的优化策略，我们已经开发了一个人工神经网络的潜力，表现出显着的改善，基于标准模板功能的Pd13H2纳米粒子系统。我们进一步证明，人工神经网络潜力可以与自适应动力学蒙特卡罗方法，它有严格的要求，光滑的潜力。这里提出的算法有利于开发更好的人工神经网络潜力，这可以扩大其在计算模拟中的应用。
Atom-centered neural network (ANN) potentials have shown promise in computational simulations and are recognized as both efficient and sufficiently accurate to describe systems involving bond formation and breaking. A key step in the development of ANN potentials is to represent atomic coordinates as suitable inputs for a neural network, commonly described as fingerprints. The accuracy and efficiency of the ANN potentials depend strongly on the selection of these fingerprints. Here, we propose an optimization strategy of atomic fingerprints to improve the performance of ANN potentials. Specifically, a set of fingerprints is optimized to fit a set of pre-selected template functions in the f(*)g space, where f and g are the fingerprint and the pair distribution function for each type of interatomic interaction (e.g., a pair or 3-body). With such an optimization strategy, we have developed an ANN potential for the Pd13H2 nanoparticle system that exhibits a significant improvement to the one based upon standard template functions. We further demonstrate that the ANN potential can be used with the adaptive kinetic Monte Carlo method, which has strict requirements for the smoothness of the potential. The algorithm proposed here facilitates the development of better ANN potentials, which can broaden their application in computational simulations.