Soft Interphases Design of Aqueous Zinc Metal Battery Driven by Quantifiable Descriptor

Aqueous zinc metal batteries (AZMBs) face persistent challenges from interfacial instability including dendrite growth and side reactions, yet a critical obstacle lies in the mismatch between anode‐side assessments and actual full‐cell cycling performance. Through explainable machine learning analysis, this study introduces a physically motivated Metal Anode/Electrolyte Interphase Descriptor (MAEID) that unifies three critical parameters, including transference number, relative exchange current density, and elastic modulus, into one predictive metric. Within the present dataset, standalone leave‐one‐out cross‐validation (LOOCV) analysis shows that MAEID provides stronger predictive capability than individual single‐parameter descriptors for full‐cell capacity retention. Guided by this descriptor, a soft solid electrolyte interphase (SSEI) based on a polyacrylic acid complex was designed, achieving a high Zn 2+ transference number of 0.84 with low elastic modulus of 4.1 MPa, and suitable exchange current density. When evaluated under practical anode‐free conditions, the SSEI‐enabled cell sustained over 1800 stable cycles without capacity decay. This work establishes a data‐driven paradigm shifting from empirical single‐parameter optimization to rational multi‐parameter synergy, offering a generalizable framework for designing high‐performance interphases in metal battery systems.