Answers are grounded in this paper and cite their sources.
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 CsPbI 3 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 molecular dynamics simulations of a CsPbI 3 slab. The resulting model yields stable and reliable trajectories for both slab and bulk, reproducing the experimentally observed phase transitions of CsPbI 3 . We demonstrate that pairwise dispersion methods (TS/D3) mispredict the correct phase of CsPbI 3 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. Through a local analysis of the rotational driving forces acting on PbI 6 octahedra, we show that this discrepancy can be traced to the strong sensitivity of Cs and I atomic forces to the treatment 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.
No takes yet. Share an insight, caveat, or question.
Knysh et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: