Δ-Machine Learning of Triplet Excitation Energies in Organic Chromophores

Abstract

Here, we report Δ-machine learning approch for predicting triplet excitation energies (T1) of diverse organic chromohores by combining high quality reference data with quantum chemical calculations. A directed message passing neural network corrects TDDFT, ΔSCF and xTB/sTDA prediction to achieve near chemical accuracy while substantially reducing computational cost. Notably, Δ-ML corrected xTB/sTDA predictions close to TD-DFT quality, enabling rapid high-throughput screening of T1 energies.