4.8 Article

Making thermodynamic models of mixtures predictive by machine learning: matrix completion of pair interactions

期刊

CHEMICAL SCIENCE
卷 13, 期 17, 页码 4854-4862

出版社

ROYAL SOC CHEMISTRY
DOI: 10.1039/d1sc07210b

关键词

-

资金

  1. Carl Zeiss Foundation
  2. Bundesministerium fur Wirtscha. und Energie (BMWi)
  3. Defense Advanced Research Projects Agency (DARPA) [HR001120C0021]
  4. National Science Foundation [2047418, 1928718, 2003237, 2007719]
  5. Department of Energy [DE-SC0022331]
  6. U.S. Department of Energy (DOE) [DE-SC0022331] Funding Source: U.S. Department of Energy (DOE)
  7. Direct For Computer & Info Scie & Enginr [2003237, 2047418, 2007719] Funding Source: National Science Foundation
  8. Direct For Social, Behav & Economic Scie [1928718] Funding Source: National Science Foundation
  9. Division Of Computer and Network Systems [2003237] Funding Source: National Science Foundation
  10. Divn Of Social and Economic Sciences [1928718] Funding Source: National Science Foundation
  11. Div Of Information & Intelligent Systems [2047418, 2007719] Funding Source: National Science Foundation

向作者/读者索取更多资源

This study combines machine learning and classical thermodynamic models to predict the thermodynamic properties of mixtures. By embedding machine learning methods into classical models, the predictive accuracy is significantly improved, and a complete set of parameters for all binary systems is obtained.
Predictive models of thermodynamic properties of mixtures are paramount in chemical engineering and chemistry. Classical thermodynamic models are successful in generalizing over (continuous) conditions like temperature and concentration. On the other hand, matrix completion methods (MCMs) from machine learning successfully generalize over (discrete) binary systems; these MCMs can make predictions without any data for a given binary system by implicitly learning commonalities across systems. In the present work, we combine the strengths from both worlds in a hybrid approach. The underlying idea is to predict the pair-interaction energies, as they are used in basically all physical models of liquid mixtures, by an MCM. As an example, we embed an MCM into UNIQUAC, a widely-used physical model for the Gibbs excess energy. We train the resulting hybrid model in a Bayesian machine-learning framework on experimental data for activity coefficients in binary systems of 1146 components from the Dortmund Data Bank. We thereby obtain, for the first time, a complete set of UNIQUAC parameters for all binary systems of these components, which allows us to predict, in principle, activity coefficients at arbitrary temperature and composition for any combination of these components, not only for binary but also for multicomponent systems. The hybrid model even outperforms the best available physical model for predicting activity coefficients, the modified UNIFAC (Dortmund) model.

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。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据