Version 3 2024-01-29, 01:19Version 3 2024-01-29, 01:19
Version 2 2024-01-29, 01:10Version 2 2024-01-29, 01:10
Version 1 2023-07-23, 20:48Version 1 2023-07-23, 20:48
dataset
posted on 2024-01-29, 01:19authored byJi QiJi Qi, Tsz Wai Ko, Brandon C. Wood, Tuan Anh Pham, Shyue Ping Ong
All data required to reproduce the DIRECT sampling results in the manuscript "Robust Training of Machine Learning Interatomic Potentials with Dimensionality Reduction and Stratified Sampling".
It contains the below data:
Training, validation, and test data as well as model parameters of M3GNet-MS and M3GNet-DIRECT universal potentials.
Training and test data as well as model parameters of MTP-AL and MTP-DIRECT for Ti-H.
Pre-processed M3GNet structural features of the 1.3 million structures in MPF.2021.2.8.All and the 274,000 M3GNet MD structures of Ti-H.