ACS Sustainable Chemistry & Engineering, Год журнала: 2025, Номер unknown
Опубликована: Янв. 16, 2025
To accurately and reasonably describe the influence of molecular structure, charge characteristics, other intrinsic properties on Henry's Law Constant (HLC), we have designed Multiscale Group Contribution Descriptor-Machine Learning (MGC-ML) model based revised group contribution method─the weighted contribution. This method extracts first-order descriptors using approach then utilizes a machine learning to impact structure electronic characteristics target properties. Experimental results demonstrate that this not only ensures theoretical reliability but also exhibits exceptionally high predictive accuracy with smaller amount data fewer features. Considering combines chemical principles data-driven approaches, it is likely be proven reasonable effective in addressing more general objectives complex systems.
Язык: Английский