SFMMoE: A Semi-Empirical Descriptor-Augmented Multi-Expert Graph Neural Network for Accurate Prediction of Singlet Fission Properties

Efficient identification of singlet fission (SF) candidates remains a significant challenge in the development of high-performance organic photovoltaic materials due to the high computational cost of accurately evaluating excited-state energetics. Here, we present SFMMoE, a graph neural network (GNN...

Full description

Saved in:

Bibliographic Details
Main Author:	Jihang Zhai (22620326) (author)
Other Authors:	Danyang Xiong (12962632) (author), Yueqing Zhang (2931549) (author), Yaru Shi (2497831) (author), Yu-cheng Gu (9655208) (author), Xinmeng Chen (5796239) (author), Shan He (121220) (author), Xiao He (223527) (author), Lianrui Hu (1486087) (author)
Published:	2025
Subjects:	Medicine Sociology Infectious Diseases Biological Sciences not elsewhere classified Physical Sciences not elsewhere classified Information Systems not elsewhere classified mean square error integrating multitask learning http :// tech hop message passing graph neural network facilitate broader access cost virtual screening 04 ev across t2 </ sub t1 </ sub s1 </ sub gap2 </ sub gap1 </ sub five key excited accurately evaluating excited high computational cost e </ >< sub – 2δ work demonstrates state properties state energetics singlet fission significant challenge semiempirical methods prediction accuracy multiexpert multigating molecular graphs model achieves freely available expert specialization enabling large empirical descriptor chemical accuracy candidates remains augmented multi accurate prediction
Tags:	Add Tag No Tags, Be the first to tag this record!

SFMMoE: A Semi-Empirical Descriptor-Augmented Multi-Expert Graph Neural Network for Accurate Prediction of Singlet Fission Properties

Similar Items