Machine learning assisted synthesis of lithium-ion batteries cathode materials. (July 2022)

• Record Type: Journal Article
• Authors: Liow, Chi Hao; Kang, Hyeonmuk; Kim, Seunggu; Na, Moony; Lee, Yongju; Baucour, Arthur; Bang, Kihoon; Shim, Yoonsu; Choe, Jacob; Hwang, Gyuseong; Cho, Seongwoo; Park, Gun; Yeom, Jiwon; Agar, Joshua C.; Yuk, Jong Min; Shin, Jonghwa; Lee, Hyuck Mo; Byon, Hye Ryung; Cho, EunAe; Hong, Seungbum
• Is Part Of: Nano energy. Volume 98(2022)
• Publication Date: 2022-07
• Subjects: Lithium-ion batteries -- NCM cathode -- Inverse design -- Machine learning -- Design-to-device pipeline; Nanoscience -- Periodicals; Nanotechnology -- Periodicals; Nanostructured materials -- Periodicals; Power resources -- Technological innovations -- Periodicals; Nanoscience; Nanostructured materials; Nanotechnology; Power resources -- Technological innovations; Periodicals; 621.042
• DOI: 10.1016/j.nanoen.2022.107214
• Languages: English
• ISSNs: 2211-2855

Abstract

Abstract: Optimizing synthesis parameters is crucial in fabricating an ideal cathode material; however, the design space is too vast to be fully explored using an Edisonian approach. Here, by clustering eleven domain-expert-derived-descriptors from literature, we use an inverse design surrogate model to build up the experimental parameters-property relationship. Without struggling with the trial-and-error method, the model enables design variables prediction that serves as an effective strategy for cathode retrosynthesis. More importantly, not only did we overcome the data scarcity problem, but the machine learning model has guided us to achieve cathode with high discharge capacity and Coulombic efficiency of 209.5 mAh/g and 86%, respectively. This work demonstrates an inverse design-to-device pipeline with unprecedented potential to accelerate the discovery of high-energy-density cathodes. Graphical Abstract: ga1 Highlights: Inverse-design surrogate model is employed for discharge capacity prediction of lithium-ion batteries cathode materials. Statistical imputation technique is exploited to solve the missing values and inconsistency in training data. The proposed method enables the realization of high discharge capacity of 209.5 mAh/g with 86% coulombic efficiency. We identified eleven descriptors from literature and reverse-engineered the synthesis parameters with high accuracy.