Hybridizing physical and data-driven prediction methods for physicochemical properties
2020
Jirasek, Fabian | Bamler, Robert | Mandt, Stephan
We present a generic way to hybridize physical and data-driven methods for predicting physicochemical properties. The approach ‘distills’ the physical method's predictions into a prior model and combines it with sparse experimental data using Bayesian inference. We apply the new approach to predict activity coefficients at infinite dilution and obtain significant improvements compared to the physical and data-driven baselines and established ensemble methods from the machine learning literature.
显示更多 [+] 显示较少 [-]AGROVOC关键词
书目信息
出版者
Cambridge University Press
语言
英语
注释
Nal-ap-2-clean
类型
Journal Article; Text
2024-02-27
MODS