Machine learning potential for calcium silicate hydrates with broad compositional and structural diversity

<p dir="ltr"><a href="" target="_blank">Calcium silicate hydrate (</a>C–S–H), the primary hydration product of cement, governs the strength and durability of concrete but remains difficult to model due to its chemical heterogeneity and disordered nanostructure. <a href="" target="_blank">Machine learning potentials (MLPs) offer a route to extend quantum accuracy to large-scale simulations, yet progress has been limited by the absence of representative datasets. </a>Here, we present a stoichiometry-generalizable MLP, CSH-MLP, trained on a broad and representative dataset containing over 50,000 DFT-labeled configurations, which is derived from nearly 700 distinct C–S–H compositions spanning diverse compositions, defects, and hydration states.

CSH-MLP reproduces structural, dynamic, and mechanical properties with near-DFT accuracy, resolves long-standing discrepancies with high-pressure X-ray diffraction, and transfers reliably to large, disordered, and nanoporous models beyond its training set. Achieving substantially higher computational efficiency than ReaxFF, CSH-MLP enables simulations at scales and timescales previously inaccessible to quantum-mechanical methods.