Parts | Days | Selection | Search | Updates | Downloads | Help
MM: Fachverband Metall- und Materialphysik
MM 31: Data Driven Materials Science: Big Data and Work Flows – Machine Learning
MM 31.10: Talk
Wednesday, March 29, 2023, 18:15–18:30, SCH A 251
Take Two: Δ-Machine Learning for Molecular Co-Crystals — •Simon Wengert1, Gábor Csányi2, Karsten Reuter1, and Johannes Theo Margraf1 — 1Fritz-Haber Institute, Berlin, Germany — 2University of Cambridge, Cambridge, United Kingdom
Co-crystals are a highly interesting material class, as varying their components and stoichiometry in principle allows tuning supramolecular assemblies towards desired physical properties. The in silico prediction of co-crystal structures represents a daunting task, however, as they span a vast search space and usually feature large unit-cells. This requires theoretical models that are accurate and fast to evaluate, a combination that can in principle be accomplished by modern machine-learned (ML) potentials trained on first-principles data. Crucially, these ML potentials need to account for the description of long-range interactions, which are essential for the stability and structure of molecular crystals. In this contribution, we present a strategy for developing Δ-ML potentials for co-crystals, which use a physical baseline model to describe long-range interactions. The applicability of this approach is demonstrated for co-crystals of variable composition consisting of an active pharmaceutical ingredient and various co-formers. We find that the Δ-ML approach offers a strong and consistent improvement over the density-functional tight binding baseline. Importantly, this even holds true when extrapolating beyond the scope of the training set as demonstrated via molecular dynamics simulations at ambient conditions.