Comparative Analyses of Data Driven Machine Learning Models for TADF Emitters

Bhattacharyya, Kalishankar

doi:10.26434/chemrxiv-2023-zj3tv

Cited by 1 publication

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently ML has been used to predict TADF emitters and their optimized devices by predicting the best EQEs. , These works focus on the device performances of the RGB gamut emitting materials and source data from literature to form large data sets. Using large data sets, numbering in tens or hundreds of thousands of molecules, has led to advanced ML models propelling related fields such as drug discovery. , However, large data sets are often obtained from the literature using complex text mining algorithms, resulting in potentially redundant or even incorrect values in the data sets. − …”

Section: Introductionmentioning

confidence: 99%

Predicting Emission Wavelengths in Benzobisoxazole-Based OLEDs with Gradient Boosted Ensemble Models

Tannir,

Pan,

Josephs

et al. 2024

J. Phys. Chem. A

View full text Add to dashboard Cite

We demonstrate the use of gradient-boosted ensemble models that accurately predict emission wavelengths in benzobis [1,2-d:4,5-d′]oxazole (BBO) based fluorescent emitters. We have curated a database of 50 molecules from previously published data by the Jeffries-EL group using density functional theory (DFT) computed ground and excited state features. We consider two machine learning (ML) models based on (i) whole cruciform molecules and (ii) their constituent fragment molecules. Both ML models provide accurate predictions with root-meansquare errors between 30 and 36 nm, competitive with state-of-theart deep learning models trained on orders of magnitude more molecules, and this accuracy holds even when tested on four new BBO emitters unseen by the models. We also provide an interpretable feature importance analysis and discuss the relevant relationships between DFT and changes in predicted emission wavelength.

show abstract