Fig. 3
From: Identifying an efficient, thermally robust inorganic phosphor host via machine learning
Machine learning predicted Debye temperature against calculated bandgap. a Machine learning predicted Debye temperature (ΘD,SVR) against the density functional theory calculated bandgap (Eg,DFT) for 2071 compounds predicted. The darker regions occur where there are overlapping data. Classes of common phosphor hosts are highlighted, including b borates and sulfides, c nitrides and (oxy)halides, d silicates and fluorides, and e aluminates and phosphates
