Learning a reactive potential for silica-water through uncertainty attribution

• Published in: Nature communications Vol. 15; no. 1; pp. 6030 - 10
• Main Authors: Roy, Swagata, Dürholt, Johannes P., Asche, Thomas S., Zipoli, Federico, Gómez-Bombarelli, Rafael
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 17.07.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301/1034/1035; 639/638/440/950; Acidity; Aqueous solutions; Catalysts; Chemical reactions; Clusters; Dimerization; Dynamic characteristics; Geology; Humanities and Social Sciences; Ionization; Machine learning; Molecular clusters; Molecular dynamics; multidisciplinary; Reactivity; Science; Science (multidisciplinary); Silica; Silicates; Silicon dioxide; Simulation; Uncertainty; Water; Zeolites
• DOI: 10.1038/s41467-024-50407-9
• ISSN: 2041-1723

The reactivity of silicates in aqueous solution is relevant to various chemistries ranging from silicate minerals in geology, to the C-S-H phase in cement, nanoporous zeolite catalysts, or highly porous precipitated silica. While simulations of chemical reactions can provide insight at the molecular level, balancing accuracy and scale in reactive simulations in the condensed phase is a challenge. Here, we demonstrate how a machine-learning reactive interatomic potential trained on PaiNN architecture can accurately capture silicate-water reactivity. The model was trained on a dataset comprising 400,000 energies and forces of molecular clusters at the ω B97X-D3/def2-TZVP level. To ensure the robustness of the model, we introduce a general active learning strategy based on the attribution of the model uncertainty, that automatically isolates uncertain regions of bulk simulations to be calculated as small-sized clusters. The potential reproduces static and dynamic properties of liquid water and solid crystalline silicates, despite having been trained exclusively on cluster data. Furthermore, we utilize enhanced sampling simulations to recover the self-ionization reactivity of water accurately, and the acidity of silicate oligomers, and lastly study the silicate dimerization reaction in a water solution at neutral conditions and find that the reaction occurs through a flanking mechanism. Accurate molecular dynamics of silicate reactivity in aqueous solution at large length and time scale is required to decipher silica condensation. Here, authors developed a potential with a new active learning method to capture silica-water interactions.