Density Functional Theory–Machine Learning-Assisted Insightful Identification of Next-Generation High-Voltage Organic Dual-Ion Batteries

Organic dual-ion batteries (ODIBs) combine the sustainability of organic materials with the cost-effectiveness and ecofriendliness of dual-ion battery systems. To overcome the large material space and vast combinations of anode, cathode, and electrolyte possibilities, we developed a machine learning model to predict cell voltages for diverse p-type and n-type organic electrode materials. The model demonstrated high accuracy and reliability, validated through repeated k-fold cross-validation, density functional theory (DFT) calculations, and experimental data. Key molecular features, such as functional groups, cyclic cores, ring size, and heteroatoms, were identified as critical components. By interpreting feature contributions, we established a clear connection between the underlying molecular chemistry and predicted voltage outputs, offering insights into feature selection and design principles. This work offers practical insights for experimental researchers to identify optimal salts and organic material pairings, accelerating the development of high-performance, sustainable ODIBs. By integrating machine learning with chemistry-driven design, we provide a scalable pathway to advance next-generation battery technologies.