Detail

MS25: Materials Science-Focused Benchmark Data Set for Machine Learning Interatomic Potentials

Maxson, Tristan; Soyemi, Ademola; Zhang, Xinglong; Chen, Benjamin Wei Jie; Szilvasi, Tibor

Year

2025

Source Name

74d6b3d9-c33c-47c4-9c9a-c14ca773d3c8

License

Creative Commons Attribution 4.0

Contacts

Maxson, Tristan (tgmaxson@gmail.com) Szilvási, Tibor (tszilvasi@ua.edu)

DOI

10.18126/6w8c-by76 View on Datacite
Here we provide the following zipped to facilitate easy downloading.
  • Analysis.zip: Additional analysis scripts and minor datasets used to validate observable properties. ~11 MB
  • Speed.zip: The LAMMPS input for performing our speed tests for each MLIP. ~55 KB
The datasets are provided unzipped as the file size is quite large and only particular datasets may be of interest. - Datasets/: The database of datasets used in the benchmark with 3 splits. ~3.8 GB Please note that the Zr-O dataset is derived from the referenced work by Waters et. al with permission. - Waters, M. J.; Rondinelli, J. M. Benchmarking Structural Evolution Methods for Training of Machine Learned Interatomic Potentials. J. Phys.: Condens. Matter 2022, 34 (38), 385901