Machine Learning-Assisted Discovery of High-Voltage Organic Materials for Rechargeable Batteries

Organic redox compounds are rich in elements and structural diversity, which are an ideal choice for lithium-ion batteries. However, most organic cathode materials show a trade-off between specific capacity and voltage, limiting energy density. By increasing the redox potential of cathode materials, the balance between redox potential and specific capacity can be broken to increase energy density. In this work, we use machine learning to train materials with different redox potentials to predict novel polymers with ideal potentials. In situ computer vision and infrared spectroscopy monitor the reaction in real time. We also theoretically studied the concentration-dependent yields by providing a depletion-force model. This work provides a new solution to material research flow, including training, prediction, synthesis, examination, and analysis, accelerating high-capacity organic cathode material discovery.

Automated summary

This study uses machine learning to train materials with different redox potentials to predict novel polymers with ideal potentials, breaking the balance between redox potential and specific capacity to increase energy density. In situ computer vision and infrared spectroscopy monitor the reaction in real time. Theoretical studies on concentration-dependent yields were also conducted by providing a depletion-force model.