Improving Aqueous Metal Salt Interactions Using Machine-Learned Interatomic Potentials.

Accurate modeling of aqueous metal salt solutions is essential for understanding processes relevant to environmental safety, energy storage, and separation technologies. Trace metals such as As³⁺ at low concentrations pose significant health and environmental risks. They are challenging to simulate due to limitations in both classical force fields (CFFs), which lack accuracy, and ab initio methods, which are restricted to short trajectories. In this study, we develop machine-learned interatomic potentials (MLIPs) to model aqueous AsCl₃ and MgCl₂ using the NequIP/Allegro equivariant graph neural network architecture trained on ab initio molecular dynamics (AIMD) and density functional theory data. Our MLIP models accurately reproduce ab initio energies and forces while capturing solvation structure, ion diffusion, and hydration dynamics more effectively than CFFs (AMBER and UFF models). Our MLIPs achieve energy MAEs < 1 meV/atom and force RMSEs < 40 meV/Å, while providing an O(10⁴) speedup over AIMD. These MLIPs offer a reliable and efficient alternative for modeling trace metal speciation and transport, with implications for improved separation and environmental processes.