Predicting the capacitance of carbon-based electric double layer capacitors by machine learning

Haiping Su; Sen Lin; Shengwei Deng; Cheng Lian; Yazhuo Shang; Honglai Liu

doi:10.1039/c9na00105k

Predicting the capacitance of carbon-based electric double layer capacitors by machine learning

Nanoscale Adv. 2019 Apr 25;1(6):2162-2166. doi: 10.1039/c9na00105k. eCollection 2019 Jun 11.

Authors

Haiping Su¹, Sen Lin², Shengwei Deng³, Cheng Lian¹, Yazhuo Shang¹, Honglai Liu¹

Affiliations

¹ State Key Laboratory of Chemical Engineering, Shanghai Engineering Research Center of Hierarchical Nanomaterials, School of Chemistry and Molecular Engineering, East China University of Science and Technology Shanghai 200237 PR China hlliu@ecust.edu.cn liancheng@ecust.edu.cn.
² National Engineering Research Center for Integrated Utilization of Salt Lake Resources, East China University of Science and Technology Shanghai 200237 China.
³ College of Chemical Engineering, Zhejiang University of Technology Hangzhou 310014 China.

Abstract

Machine learning (ML) methods were applied to predict the capacitance of carbon-based supercapacitors. Hundreds of published experimental datasets are collected for training ML models to identify the relative importance of seven electrode features. This present method could be used to predict and screen better carbon electrode materials.