期刊
CHEMICAL COMMUNICATIONS
卷 56, 期 82, 页码 12407-12410出版社
ROYAL SOC CHEMISTRY
DOI: 10.1039/d0cc05258b
关键词
-
资金
- German Academic Exchange Service (DAAD)
- Defense Advanced Research Projects Agency (DARPA) [HR001120C0021]
- National Science Foundation [1928718, 2003237]
- Qualcomm
- Direct For Computer & Info Scie & Enginr [2003237] Funding Source: National Science Foundation
- Direct For Social, Behav & Economic Scie
- Divn Of Social and Economic Sciences [1928718] Funding Source: National Science Foundation
- Division Of Computer and Network Systems [2003237] Funding Source: National Science Foundation
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据