Machine Learning-Driven Ionic Liquids as Electrolytes for the Advancement of High-Voltage Dual-Ion Battery

In light of escalating energy demands, the development of advanced energy storage systems to mitigate the intermittency of renewable energy sources is imperative. In this process, dual-ion batteries (DIBs) have emerged as a promising alternative to the post Li-ion batteries (LIBs) era, offering low-cost, high voltage, and safety. Ionic liquids (ILs) in graphite-based DIBs show potential; however, only a few organic-moiety-based cation-intercalation studies have been reported until now for various reasons. To overcome these challenges, we used machine learning (ML) to predict the suitability of cation intercalation into the graphite anode. We considered the suitability of 880 cations in terms of intercalations into the anode following different staging mechanisms. To understand the extent of interactions between the cation and graphitic anode, local and global feature relations were investigated using various tools. Using the ML, we report here voltages of ∼500 graphite-based DIBs having low-to-high voltage. The predicted voltages are further verified using the available experimental reports. The ML-predicted voltage database can serve as a guidepost for experimental researchers to find the optimum IL-based electrolytes to enhance the fabrication of cost-effective dual-ion-based electrochemical devices.