Bridging Surface Dynamics and Phase Transitions in CsPbI3 Perovskite With Machine-Learning Force Fields and Dispersion Interactions

This dataset supports the publication "Bridging Surface Dynamics and Phase Transitions in CsPbI3 Perovskite With Machine-Learning Force Fields and Dispersion Interactions". The accompanying manuscript studies slab-to-bulk transferability in machine-learning force fields for CsPbI3, with a focus on surface dynamics, phase transitions, and the role of dispersion interactions. Abstract: In the rapidly evolving field of machine learning (ML) for atomistic simulations of materials and molecules, achieving transferability across different systems remains a key challenge. In this contribution, we demonstrate a case of transfer learning in which an ML model trained exclusively on surface slab data of the cubic (α) phase of CsPbI3 perovskite can reproduce the key features of the dynamic behavior for different phases of the bulk material. Using an equivariant message-passing network (MACE) architecture, we construct an efficient ML force field trained on a dataset obtained from ab initio molecular dynamics simulations of a CsPbI3 slab. The resulting model yields stable and reliable trajectories for both slab and bulk, reproducing the experimentally observed phase transitions of CsPbI3. We demonstrate that pairwise dispersion methods (TS/D3) mispredict the correct phase of CsPbI3 bulk at ambient conditions, while more advanced approaches (MBD-NL/rVV10) recover both the experimentally observed phase sequence with increasing temperature (orthorhombic–tetragonal–cubic) and the corresponding phase-transition temperatures. The main source of this discrepancy is the crucial dependence of Cs forces on the level of description of van der Waals (vdW) dispersion. Overall, our results demonstrate that surface–slab datasets augmented with an accurate treatment of vdW dispersion provide a robust foundation for constructing transferable machine-learning force fields that consistently describe both surface and bulk behavior across multiple length scales.