Machine learning for exciton dynamics: Qy trajectories

*The embed functionality can only be used for non commercial purposes… more *The embed functionality can only be used for non commercial purposes. In order to maintain its sustainability, all mass use of content by commercial or not for profit companies must be done in agreement with figshare. Description In this folder we report the data of our paper, recently posted on the arXiv. In particular we provide the energy gap trajectories for each BChl of monomer A of the Fenna-Matthews-Olson (FMO) complex. These were computed using QM/MM and TDDFT, and then they were predicted using multi layer perceptrons with different methods to select the training data ( Random, Correlation, Frobenius and Taxicab).


Link to Full Article: Machine learning for exciton dynamics: Qy trajectories