Impact of crystal structure symmetry in training datasets on GNN-based energy assessments for chemically disordered CsPbI3

• DOI: 10.1038/s41598-025-92669-3
• Publication Date: 2025-03-14T10:39:22Z
• Authors: Aliaksei V. Krautsou; Innokentiy S. Hum...; Vladimir D. Lazarev; Roman A. Eremin; Semen A. Budennyy
• Keywords: Crystal (programming language)

Robust solutions combining computational chemistry and data-driven approaches are in high demand various areas of materials science. For instance, such methods can use machine learning models trained on a limited dataset to make structure-to-property predictions over large search spaces. This paper examines the impact data selection mechanisms thermodynamic property assessments for chemically modified lead halide perovskite γ-CsPbI3 non-perovskite δ-CsPbI3. disordered states these phases, complete composition/configuration spaces built by adding Cd or Zn substitutions Pb Br I comprise 2,946,709 2,995,462 inequivalent spatial arrangements substituents, respectively. Using properties 1162 entries evaluated means density functional theory, we implement independent procedures training graph neural networks (GNNs). In each them, is constructed depending defect contents presence low- high-symmetry structures. The results show that symmetries structures significantly influence quality subsequent GNNs' result twofold increase errors due preferential