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

• Tác giả: Semen A Budennyy, Roman A Eremin, Innokentiy S Humonen, Aliaksei V Krautsou, Vladimir D Lazarev
• Ngôn ngữ: eng
• Ký hiệu phân loại: 341.733 +Disarmament
• Thông tin xuất bản: England : Scientific reports , 2025
• Bộ sưu tập: NCBI
• ID: 712242

Tóm tắt

Robust solutions combining computational chemistry and data-driven approaches are in high demand in 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 of data selection mechanisms on thermodynamic property assessments for chemically modified lead halide perovskite γ-CsPbI