Hoffmann Marco, Hayer Nicolas, Kohns Maximilian, Jirasek Fabian, Hasse Hans
Laboratory of Engineering Thermodynamics, RPTU Kaiserslautern, Erwin-Schrödinger-Str. 44, 67663 Kaiserslautern, Germany.
Phys Chem Chem Phys. 2024 Jul 17;26(28):19390-19397. doi: 10.1039/d4cp01492h.
Molecular simulations enable the prediction of physicochemical properties of mixtures based on pair-interaction models of the pure components and combining rules to describe the unlike interactions. However, if no adjustment to experimental data is made, the existing combining rules often do not yield sufficiently accurate predictions of mixture data. To address this problem, adjustable binary parameters describing the pair interactions in mixtures ( + ) are used. In this work, we present the first method for predicting for unstudied mixtures based on a matrix completion method (MCM) from machine learning (ML). Considering molecular simulations of Henry's law constants as an example, we demonstrate that for unstudied mixtures can be predicted with high accuracy. Using the predicted significantly increases the accuracy of the Henry's law constant predictions compared to using the default = 1. Our approach is generic and can be transferred to molecular simulations of other mixture properties and even to combining rules in equations of state, granting predictive access to the description of unlike intermolecular interactions.
分子模拟能够基于纯组分的对相互作用模型和描述异类相互作用的组合规则来预测混合物的物理化学性质。然而，如果不对实验数据进行调整，现有的组合规则往往无法对混合物数据做出足够准确的预测。为了解决这个问题，使用了描述混合物中对相互作用的可调二元参数（ + ）。在这项工作中，我们提出了第一种基于机器学习（ML）的矩阵补全方法（MCM）来预测未研究混合物的 的方法。以亨利定律常数的分子模拟为例，我们证明可以高精度地预测未研究混合物的 。与使用默认的 = 1相比，使用预测的 显著提高了亨利定律常数预测的准确性。我们的方法具有通用性，可以转移到其他混合物性质的分子模拟中，甚至可以应用于状态方程中的组合规则，从而能够对异类分子间相互作用的描述进行预测。
