A machine learning approach to light-induced order-disorder phase transitions: large-scale long-time simulations with it ab initio accuracy.

Data for the paper 'Scalable machine learning approach to light induced order disorder phase transitions with ab initio accuracy' DOI https://doi.org/10.1038/s41524-025-01614-5 The folder contains: - a folder 'figures' with python scripts to reproduce all Figures and Supplementary Figures of the paper. - a folder 'software' with the list of all software used and their respective versions. - a folder 'GAP_potentials' with all the GAP training sets, input files and potentials used in the paper. - a folder 'example_files' containing some examples of input and output files for the various calculations that we have performed in the paper (ab initio force calculations, ab initio phonon calculations, GAP phonon calculations, molecular dynamics)