arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.17595cond-mat.mtrl-sci
收藏

用于机器学习力场的基于密度的长程静电描述符

Density-Based Long-Range Electrostatic Descriptors for Machine Learning Force Fields

Carolin Faller, Merzuk Kaltak, Georg Kresse

AI总结:

提出一种保持平移旋转对称、可纳入长程静电作用的密度型MLFF描述符,并在NaCl等材料上验证其相对短程描述符的显著改进。

摘要:

本研究提出了一种用于机器学习力场(MLFF)的长程描述符,它保持平移和旋转对称性,类似于短程描述符,同时能够纳入长程静电相互作用。所提出的描述符基于原子密度表示,在结构上类似于经典的以原子为中心的短程描述符,因此可以直接集成到机器学习方案中。我们通过与长距离等变(LODE)描述符进行比较分析,证明了模型的有效性。在一个仅含静电相互作用的玩具模型中,我们的模型实现了低于0.1%的误差,虽差于LODE,但仍然非常好。对于真实材料,我们对液态NaCl、岩盐NaCl和固态氧化锆进行了测试。对于NaCl,本描述符对短程密度描述符作出了改进,将误差降低了2到3倍,并接近消息传递网络。然而,对于固态氧化锆,本方法未观察到改进,而消息传递网络将误差降低了近2到3倍。本文还简要讨论了当前模型可能存在的不足。

英文摘要:

This study presents a long-range descriptor for machine learning force fields (MLFFs) that maintains translational and rotational symmetry, similar to short-range descriptors while being able to incorporate long-range electrostatic interactions. The proposed descriptor is based on an atomic density representation and is structurally similar to classical short-range atom-centered descriptors, making it straightforward to integrate into machine learning schemes. The effectiveness of our model is demonstrated through comparative analysis with the long-distance equivariant (LODE) descriptor. In a toy model with purely electrostatic interactions, our model achieves errors below 0.1%, worse than LODE but still very good. For real materials, we perform tests for liquid NaCl, rock salt NaCl, and solid zirconia. For NaCl, the present descriptors improve on short-range density descriptors, reducing errors by a factor of two to three and coming close to message-passing networks. However, for solid zirconia, no improvements are observed with the present approach, while message-passing networks reduce the error by almost a factor of two to three. Possible shortcomings of the present model are briefly discussed.

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。

↑