Abstract
<jats:p>We present an end-to-end, AI-powered platform for high-throughput molecular dynamics (MD) simulation of liquid electrolytes and complex formulations. At its core is MU-PFF, a many-body polarizable force field (PFF) whose functional form follows the well-validated polarizable force field, but whose parameters are produced entirely by an automated machine-learning pipeline rather than by hand. We assemble a quantum-chemistry (QC) dataset of roughly 106 molecules and molecular complexes and train a single message-passing neural network (MPNN) to predict the complete parameter set—partial charges, atomic polarizabilities, bonded (bond, bend, torsion) terms, and the repulsion–dispersion (van der Waals) parameters—directly from molecular structure. Parameterization that traditionally takes weeks of expert effort per chemistry is reduced to a single forward pass, yielding a universal PFF that transfers across solvents, salts and additives. Coupled to automated system building and trajectory analysis (MU-MDSuiteTM), the platform reproduces experimental electrolyte properties with high fidelity: density error below 0.02 g/cm3, lithium-electrolyte ionic conductivity of approximately 1.5 mS/cm in quantitative agreement with measurement, and salt/additive solubility predicted to within 10%. We further demonstrate extended capabilities, including additive solubility by thermodynamic integration and electric-double-layer (EDL) simulation under applied potential.</jats:p>