Babaei Mahboobeh, Sadeghi Ali
Department of Physics, Shahid Beheshti University, Tehran, 1983969411, Iran.
School of Nano Science, Institute for Research in Fundamental Sciences (IPM), P.O. Box 19395-5531, Tehran, Iran.
Sci Rep. 2024 Dec 28;14(1):31395. doi: 10.1038/s41598-024-82990-8.
Machine learning interatomic potentials, as a modern generation of classical force fields, take atomic environments as input and predict the corresponding atomic energies and forces. We challenge the commonly accepted assumption that the contribution of an atom can be learned from the short-range local environment of that atom. We employ density functional theory calculations to quantify the decay of the induced electron density and electrostatic potential in response to local perturbations throughout insulating, semiconducting and metallic samples of different dimensionalities. Molecules and thin layers are shown to fail keeping such disturbances localized. Therefore, the learnability of local atomic contributions, which guarantees scalability and transferability of a machine learning interatomic potential, is questionable in the case of molecules and low-dimensional samples. Similarly, the induced electrostatic effects due to substituted impurities or vacancy sites in a crystalline bulk are weakly damped and remain significant beyond several interatomic distances. However, geometric deformations in bulks are practically local within the first neighbors and induce a Yukawa-type electrostatic potential that exponentially vanishes. The practical importance of this finding is that it limits the application of the machine learning interatomic potentials to conformational search or thermal properties of bulk materials and so on, where only purely geometrical deformations are involved. Once chemically impactful defects like aliovalent impurities or vacancies are present, the interatomic potentials trained on local environments need to be corrected for long-range effects.
机器学习原子间势作为新一代经典力场，以原子环境为输入并预测相应的原子能量和力。我们对一个普遍接受的假设提出质疑，即原子的贡献可以从该原子的短程局部环境中学习到。我们采用密度泛函理论计算来量化在不同维度的绝缘、半导体和金属样本中，感应电子密度和静电势对局部微扰的衰减情况。结果表明，分子和薄层无法将此类干扰局限在局部范围内。因此，在分子和低维样本的情况下，保证机器学习原子间势的可扩展性和可转移性的局部原子贡献的可学习性是值得怀疑的。同样，晶体块体中由于替代杂质或空位产生的感应静电效应衰减较弱，在几个原子间距之外仍很显著。然而，块体中的几何变形在第一近邻范围内实际上是局部的，并会诱导出指数衰减的汤川型静电势。这一发现的实际重要性在于，它将机器学习原子间势的应用限制在构象搜索或块体材料的热性质等仅涉及纯粹几何变形的方面。一旦存在像异价杂质或空位这样具有化学影响的缺陷，基于局部环境训练的原子间势就需要针对长程效应进行修正。
