Predicting phosphorescence energies and inferring wavefunction localization with machine learning

• Published in: Chemical science (Cambridge) 2021-08, Vol.12 (3), p.127-1217
• Main Authors: Sifain, Andrew E, Lystrom, Levi, Messerly, Richard A, Smith, Justin S, Nebgen, Benjamin, Barros, Kipton, Tretiak, Sergei, Lubbers, Nicholas, Gifford, Brendan J
• Format: Article
• Language: English
• Subjects: Atomic properties; Chemical fingerprinting; Chemistry; Density; Energy; Energy gap; Extensibility; Histograms; INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; Light emitting diodes; Localization; Machine learning; Modelling; Neural networks; Organic chemistry; Parity; Phosphorescence; Photovoltaic cells; Potential energy; Spin transition; Test sets; Training; Wave functions
• ISSN: 2041-6520; 2041-6539
• DOI: 10.1039/d1sc02136b

Phosphorescence is commonly utilized for applications including light-emitting diodes and photovoltaics. Machine learning (ML) approaches trained on ab initio datasets of singlet-triplet energy gaps may expedite the discovery of phosphorescent compounds with the desired emission energies. However, we show that standard ML approaches for modeling potential energy surfaces inaccurately predict singlet-triplet energy gaps due to the failure to account for spatial localities of spin transitions. To solve this, we introduce localization layers in a neural network model that weight atomic contributions to the energy gap, thereby allowing the model to isolate the most determinative chemical environments. Trained on the singlet-triplet energy gaps of organic molecules, we apply our method to an out-of-sample test set of large phosphorescent compounds and demonstrate the substantial improvement that localization layers have on predicting their phosphorescence energies. Remarkably, the inferred localization weights have a strong relationship with the ab initio spin density of the singlet-triplet transition, and thus infer localities of the molecule that determine the spin transition, despite the fact that no direct electronic information was provided during training. The use of localization layers is expected to improve the modeling of many localized, non-extensive phenomena and could be implemented in any atom-centered neural network model. We address phosphorescence, a localized phenomenon, by building localization layers into a DNN model of singlet-triplet energy gaps. These layers improve model performance and simultaneously infer the location of spin excitations within molecules.