Chinese Journal of Chemical Engineering ›› 2021, Vol. 29 ›› Issue (3): 227-239.doi: 10.1016/j.cjche.2020.10.044

Previous Articles    

Machine learning for molecular thermodynamics

Jiaqi Ding1, Nan Xu1, Manh Tien Nguyen2, Qi Qiao2, Yao Shi1,3, Yi He1,4, Qing Shao2   

  1. 1 College of Chemical and Biological Engineering, Zhejiang University, Hangzhou 310027, China;
    2 Chemical and Materials Engineering Department, University of Kentucky, Lexington, KY 40506, USA;
    3 Key Laboratory of Biomass Chemical Engineering of Ministry of Education, Zhejiang University, Hangzhou 310027, China;
    4 Department of Chemical Engineering, University of Washington, Seattle, WA 98195, USA
  • Received:2020-08-21 Revised:2020-10-02 Online:2021-03-28 Published:2021-05-13
  • Contact: Yi He, Qing Shao;
  • Supported by:
    Jiaqi Ding, Nan Xu, Dr. Yao Shi and Dr. Yi He acknowledge financial supports from the National Natural Science Foundation of China (21676245 and 51933009), the National Key Research and Development Program of China (2017YFB0702502), and the Leading Innovative and Entrepreneur Team Introduction Program of Zhejiang (2019R01006). Manh Tien Nguyen, Dr. Qi Qiao and Dr. Qing Shao thank the financial support provided by the Startup Funds of the University of Kentucky.

Abstract: Thermodynamic properties of complex systems play an essential role in developing chemical engineering processes. It remains a challenge to predict the thermodynamic properties of complex systems in a wide range and describe the behavior of ions and molecules in complex systems. Machine learning emerges as a powerful tool to resolve this issue because it can describe complex relationships beyond the capacity of traditional mathematical functions. This minireview will summarize some fundamental concepts of machine learning methods and their applications in three aspects of the molecular thermodynamics using several examples. The first aspect is to apply machine learning methods to predict the thermodynamic properties of a broad spectrum of systems based on known data. The second aspect is to integer machine learning and molecular simulations to accelerate the discovery of materials. The third aspect is to develop machine learning force field that can eliminate the barrier between quantum mechanics and all-atom molecular dynamics simulations. The applications in these three aspects illustrate the potential of machine learning in molecular thermodynamics of chemical engineering. We will also discuss the perspective of the broad applications of machine learning in chemical engineering.

Key words: Machine learning, Thermodynamic properties, Molecular engineering, Molecular simulation, Force field