A two-level ML approach using graph neural network potentials and direct energy predictors maps thermodynamic stability across (Cs/FA)Pb(Br/I)3 and (Cs/FA)Sn(Br/I)3 compositions, finding narrower stable regions for Sn-based systems with peak stability at high iodine content.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Charting the thermodynamic stability of hybrid perovskite alloys with machine learning
A two-level ML approach using graph neural network potentials and direct energy predictors maps thermodynamic stability across (Cs/FA)Pb(Br/I)3 and (Cs/FA)Sn(Br/I)3 compositions, finding narrower stable regions for Sn-based systems with peak stability at high iodine content.