Δ-Machine Learning of Triplet Excitation Energies in Organic Chromophores

Key Points

• The study aims to develop a machine learning approach for predicting triplet excitation energies in organic chromophores.
• Utilized high-quality reference data combined with quantum chemical calculations.
• Employed a directed message passing framework for the prediction model.
• Achieved accurate predictions of triplet excitation energies (T1).
• Demonstrated improved performance over traditional methods in diverse organic chromophores.