Matches in SemOpenAlex for { <https://semopenalex.org/work/W4246016556> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4246016556 abstract "Phosphorescence is commonly utilized for applications including light-emitting diodes and photovoltaics. Machine learning (ML) approaches trained on <i>ab-initio</i> 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 <i>ab-initio</i> 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." @default.
- W4246016556 created "2022-05-12" @default.
- W4246016556 creator A5003874504 @default.
- W4246016556 creator A5005773965 @default.
- W4246016556 creator A5021344986 @default.
- W4246016556 creator A5045395248 @default.
- W4246016556 creator A5056150849 @default.
- W4246016556 creator A5069355971 @default.
- W4246016556 creator A5070900242 @default.
- W4246016556 creator A5078126229 @default.
- W4246016556 creator A5081624801 @default.
- W4246016556 date "2021-06-30" @default.
- W4246016556 modified "2023-09-27" @default.
- W4246016556 title "Predicting Phosphorescence Energies and Inferring Wavefunction Localization with Machine Learning" @default.
- W4246016556 doi "https://doi.org/10.33774/chemrxiv-2021-4xbpv-v3" @default.
- W4246016556 hasPublicationYear "2021" @default.
- W4246016556 type Work @default.
- W4246016556 citedByCount "0" @default.
- W4246016556 crossrefType "posted-content" @default.
- W4246016556 hasAuthorship W4246016556A5003874504 @default.
- W4246016556 hasAuthorship W4246016556A5005773965 @default.
- W4246016556 hasAuthorship W4246016556A5021344986 @default.
- W4246016556 hasAuthorship W4246016556A5045395248 @default.
- W4246016556 hasAuthorship W4246016556A5056150849 @default.
- W4246016556 hasAuthorship W4246016556A5069355971 @default.
- W4246016556 hasAuthorship W4246016556A5070900242 @default.
- W4246016556 hasAuthorship W4246016556A5078126229 @default.
- W4246016556 hasAuthorship W4246016556A5081624801 @default.
- W4246016556 hasBestOaLocation W42460165561 @default.
- W4246016556 hasConcept C113603373 @default.
- W4246016556 hasConcept C119857082 @default.
- W4246016556 hasConcept C121332964 @default.
- W4246016556 hasConcept C159467904 @default.
- W4246016556 hasConcept C181500209 @default.
- W4246016556 hasConcept C181817918 @default.
- W4246016556 hasConcept C184779094 @default.
- W4246016556 hasConcept C185592680 @default.
- W4246016556 hasConcept C186370098 @default.
- W4246016556 hasConcept C2781442258 @default.
- W4246016556 hasConcept C33062035 @default.
- W4246016556 hasConcept C41008148 @default.
- W4246016556 hasConcept C50644808 @default.
- W4246016556 hasConcept C62520636 @default.
- W4246016556 hasConcept C91881484 @default.
- W4246016556 hasConceptScore W4246016556C113603373 @default.
- W4246016556 hasConceptScore W4246016556C119857082 @default.
- W4246016556 hasConceptScore W4246016556C121332964 @default.
- W4246016556 hasConceptScore W4246016556C159467904 @default.
- W4246016556 hasConceptScore W4246016556C181500209 @default.
- W4246016556 hasConceptScore W4246016556C181817918 @default.
- W4246016556 hasConceptScore W4246016556C184779094 @default.
- W4246016556 hasConceptScore W4246016556C185592680 @default.
- W4246016556 hasConceptScore W4246016556C186370098 @default.
- W4246016556 hasConceptScore W4246016556C2781442258 @default.
- W4246016556 hasConceptScore W4246016556C33062035 @default.
- W4246016556 hasConceptScore W4246016556C41008148 @default.
- W4246016556 hasConceptScore W4246016556C50644808 @default.
- W4246016556 hasConceptScore W4246016556C62520636 @default.
- W4246016556 hasConceptScore W4246016556C91881484 @default.
- W4246016556 hasLocation W42460165561 @default.
- W4246016556 hasOpenAccess W4246016556 @default.
- W4246016556 hasPrimaryLocation W42460165561 @default.
- W4246016556 hasRelatedWork W2003364926 @default.
- W4246016556 hasRelatedWork W2007567767 @default.
- W4246016556 hasRelatedWork W2073087343 @default.
- W4246016556 hasRelatedWork W2083441840 @default.
- W4246016556 hasRelatedWork W2181072655 @default.
- W4246016556 hasRelatedWork W2325686876 @default.
- W4246016556 hasRelatedWork W2332136779 @default.
- W4246016556 hasRelatedWork W3157383236 @default.
- W4246016556 hasRelatedWork W4231339334 @default.
- W4246016556 hasRelatedWork W4241083693 @default.
- W4246016556 isParatext "false" @default.
- W4246016556 isRetracted "false" @default.
- W4246016556 workType "article" @default.