What does this research mean for the field?

Machine learning models can accurately predict the properties of Mn4+-doped phosphors based on their composition, outperforming previous studies. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

March 1, 2026Open Access

Composition-based machine learning for predicting and designing Mn 4+ -doped phosphors

Key Points

The aim is to explore composition-property relations in Mn<sup>4+</sup>-doped phosphors using machine learning.
Collected the largest experimental dataset of Mn<sup>4+</sup>-doped phosphors.
Applied machine learning algorithms to analyze the dataset.
Developed models to predict properties based on composition.
Models significantly outperform previous studies in predictive accuracy.
Showed strong agreement with experimental results.

Abstract

We collect the largest experimental dataset and apply machine learning to study composition–property relations in Mn 4+ -doped phosphors. The resulting models outperform prior studies and show good agreement with experimental data.

Composition-based machine learning for predicting and designing Mn 4+ -doped phosphors

Key Points

Abstract

Cite This Study