Carbonyl‐Modulated Lowest Unoccupied Molecular Orbital Energy Directs Machine Learning‐Assisted Screening of Electrolyte Additives Toward Ultra‐Stable Zinc Metal Anodes

ABSTRACT The commercialization of aqueous zinc‐ion batteries has long been hindered by side reactions stemming from zinc anode interfacial instability. Organic molecular additives offer an effective solution. Here, using lowest unoccupied molecular orbital (LUMO) energy and solubility as dual screening criteria, a novel high‐precision Organic Molecular Attention Prediction Graph Neural Network is developed to enable high‐throughput screening of organic additives. Through Shapley Additive exPlana