[1Fa01-05] Data-driven research and development focused on data generation/storage/analysis: Data-Driven Surface Science Division's Session

[1Fa02] Data storage and analysis for optimal design of electrochemical energy storage devices

*Kosuke Kawai¹ (1. Waseda University)

Electrochemical energy storage devices constitute complex systems with various components. Optimizing each parameter through trial and error is required to maximize device performance. However, as the number of parameters subject to optimization increases, the volume of experimental data grows exponentially, where a portion of the data is usually left unutilized. Furthermore, identifying optimal points within a multi-dimensional parameter space is generally challenging for humans. In the first part of this presentation, we discuss the material design of MXene, two-dimensional carbides/nitrides under investigation as an electrode material for electrochemical capacitors, based on an interpretation approach independent of machine learning models. In the latter part, the accumulation of charge/discharge curves of rechargeable lithium-ion batteries and a method to predict device performance by using supervised machine learning will be introduced.