Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
HL: Fachverband Halbleiterphysik
HL 3: Focus Session: Machine Learning of semiconductor properties and spectra
HL 3.6: Vortrag
Montag, 17. März 2025, 12:15–12:30, H17
Mechanical Properties of Hybrid Perovskites study using explainable Machine Learning — •Yuxuan Yao1,2, Dan Han3, and Harald Oberhofer2 — 1Chair for Theoretical Chemistry, Technical University of Munich — 2Chair for Theoretical Physics VII, University of Bayreuth — 3School of Materials Science and Engineering, Jilin University
Lead-based halide perovskite photovoltaics are of great interest for use in optoelectronic devices due to the high power conversion efficiency and low cost. 2D hybrid organic and inorganic perovskites (HOIPs) have been utilized as capping layers on top of 3D perovskites to increase the stability. On top of that, soft and stable HOIPs are an attractive material for use in flexible electronic devices. We utilize explainable machine learning (ML) techniques to accelerate the in silico prediction of elasticities of 2D perovskites, based on their Young's moduli. Our ML models allow us to distinguish between stiff and nonstiff HOIPs and to extract the materials' features most strongly influencing their elasticities. The Pb-halogen-Pb bond angle and the cations' steric effect indices (STEI) emerge as the dominant physical feature with an inverse correlation to the structural non-stiffness. The deformation of the octahedra strongly affects the material's mechanical properties, which allows us to perform the transferability test from single-layered to multi-layered 2D perovskites. Overall, our work thus points the way towards future design efforts of HOIPs with regards to their elasticity.
Keywords: Explainable Machine Learning; Perovskites; Mechanical Properties