Molecular dynamics simulations are an invaluable tool in numerous scientific fields. However, the ubiquitous classical force fields cannot describe reactive systems, and quantum molecular dynamics are too computationally demanding to treat large systems or long timescales. Reactive force fields based on physics or machine learning can be used to bridge the gap in time and length scales, but these force fields require substantial effort to construct and are highly specific to given chemical composition and application. The extreme flexibility of machine learning models promises to yield reactive force fields that provide a more general description of chemical bonding. However, a significant limitation of machine learning models is the use of element-specific features, leading to models that scale poorly with the number of elements. This work introduces the Gaussian multi-pole (GMP) featurization scheme that utilizes physically-relevant multi-pole expansions of the electron density around atoms to yield feature vectors that interpolate between element types and have a fixed dimension regardless of the number of elements present. We combine GMP with neural networks to directly compare it to the widely-used Behler-Parinello symmetry functions for the MD17 dataset, revealing that it exhibits improved accuracy and computational efficiency. Further, we demonstrate that GMP-based models can achieve chemical accuracy for the QM9 dataset, and their accuracy remains reasonable even when extrapolating to new elements. Finally, we test GMP-based models for the Open Catalysis Project (OCP) dataset, revealing comparable performance and improved learning rates when compared to graph convolutional deep learning models. The results indicate that this featurization scheme fills a critical gap in the construction of efficient and transferable reactive force fields.
翻译:分子动态模拟是众多科学领域的宝贵工具。然而,无处不在的古典力场无法描述反应系统,量分子动态在计算上要求过高,无法处理大型系统或长期时间尺度。基于物理或机器学习的再反应力场可用于弥合时间和长度尺度的差距,但这些力场需要做出大量努力来构建,并且对于特定化学构成和应用非常具体。机器学习模型的极端灵活性将产生反应力场,从而更全面地描述化学联结。然而,机器学习模型的一个重大局限性是使用元素特定特性,导致模型与元素数量相比规模差的模型。这项工作引入了高斯-多极(GMP)的预变电力场,利用物理的多极电密度扩大来生成元素类型和化学特性矢量,而不论现有元素的数量如何。我们将GMP与神经改进网络结合起来,直接将它与广泛使用的Behler-Paryello 直径直径模型进行比较,导致与元素数量相较的模型的可比较。 这项工作引入了高精度多极-波(GMP) 预测的精确度模型,最终的精确度计算数据模型可以显示数据。