arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01674physics.chem-ph
收藏

通过结合监督和无监督机器学习来改善跨空间的分子力场

Improving Molecular Force Fields Across Configurational Space by Combining Supervised and Unsupervised Machine Learning

Gregory Fonseca, Igor Poltavsky, Valentin Vassilev-Galindo, Alexandre Tkatchenko

摘要:

原子配置的训练集是任何机器学习力场(MLFF)性能的关键,因此,训练集的选择决定了MLFF模型对预测分子模拟的适用性。然而,大多数原子参考数据集在配置空间(CS)上分布不均匀,因此随机选择训练集或根据数据的概率分布导致模型的准确性主要由参考数据中最常见的接近平衡的配置定义。在这项工作中,我们结合了无监督和有监督的ML方法,以绕过常见配置数据的固有偏差,有效地扩大了MLFF的适用范围,以充分发挥数据集的功能。为了实现这一目标,我们首先集群CS到子区域相似的几何形状和能量。我们在每个子区域上迭代测试给定的MLFF性能,并使用CS最不准确部分的代表填充模型的训练集。所提出的方法已被应用到一组小的有机分子和丙氨酸四肽,表现出高达两倍的减少,这些分子的力预测的均方根误差。这一结果适用于基于内核的方法(sGDML和GAP/SOAP模型)和深度神经网络(SchNet模型)。对于后者,所开发的方法同时提高了能量和力,绕过了采用混合能量/力损失函数时要做出的妥协。

英文摘要:

The training set of atomic configurations is key to the performance of any Machine Learning Force Field (MLFF) and, as such, the training set selection determines the applicability of the MLFF model for predictive molecular simulations. However, most atomistic reference datasets are inhomogeneously distributed across configurational space (CS), thus choosing the training set randomly or according to the probability distribution of the data leads to models whose accuracy is mainly defined by the most common close-to-equilibrium configurations in the reference data. In this work, we combine unsupervised and supervised ML methods to bypass the inherent bias of the data for common configurations, effectively widening the applicability range of MLFF to the fullest capabilities of the dataset. To achieve this goal, we first cluster the CS into subregions similar in terms of geometry and energetics. We iteratively test a given MLFF performance on each subregion and fill the training set of the model with the representatives of the most inaccurate parts of the CS. The proposed approach has been applied to a set of small organic molecules and alanine tetrapeptide, demonstrating an up to two-fold decrease in the root mean squared errors for force predictions of these molecules. This result holds for both kernel-based methods (sGDML and GAP/SOAP models) and deep neural networks (SchNet model). For the latter, the developed approach simultaneously improves both energy and forces, bypassing the compromise to be made when employing mixed energy/force loss functions.

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。

↑