Machine Learning Reveals Composition Dependent Thermal Stability in Halide Perovskites
This work addresses the challenge of identifying stable perovskite compositions for photovoltaics, offering a faster analysis method, though it is incremental as it applies existing ML techniques to new data.
The study tackled the unpredictable thermal stability of halide perovskites by applying machine learning to high-throughput photoluminescence experiments, revealing an anti-correlation between Cs content and stability with model accuracies over 75%.
Halide perovskites exhibit unpredictable properties in response to environmental stressors, due to several composition-dependent degradation mechanisms. In this work, we apply data visualization and machine learning (ML) techniques to reveal unexpected correlations between composition, temperature, and material properties while using high throughput, in situ environmental photoluminescence (PL) experiments. Correlation heatmaps show the strong influence of Cs content on film degradation, and dimensionality reduction visualization methods uncover clear composition-based data clusters. An extreme gradient boosting algorithm (XGBoost) effectively forecasts PL features for ten perovskite films with both composition-agnostic (>85% accuracy) and composition-dependent (>75% accuracy) model approaches, while elucidating the relative feature importance of composition (up to 99%). This model validates a previously unseen anti-correlation between Cs content and material thermal stability. Our ML-based framework can be expanded to any perovskite family, significantly reducing the analysis time currently employed to identify stable options for photovoltaics.