Skip to content

Repository associated with article "A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors"

Notifications You must be signed in to change notification settings

JakubMartinka/Fulvene-ML-FSSH

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Fulvene-ML-FSSH

Preprint:

  • Jakub Martinka, Lina Zhang, Yi-Fan Hou, Mikołaj Martyka, Jiří Pittner*, Mario Barbatti*, Pavlo O. Dral*. A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors. 2025. Preprint on : https://doi.org/10.26434/chemrxiv-2025-wzkst.

Code and data

  • This repository contains a Jupyter notebook with Supporting Information as well as data in .csv or .txt format.
  • trainnacs.py contains code, which was used for phase correction of the data set.
  • Training and test sets, as well as models, are saved on FigShare: https://doi.org/10.6084/m9.figshare.28877672
  • Trajectories in H5MD format (exceeding 10 GB) can be provided upon request due to their size.

About

Repository associated with article "A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors"

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published