Published February 9, 2026
| Version 1.0.0
Dataset
Open
Data set for: "Environment-adaptive machine-learned force fields for materials under extreme conditions: hafnium and hafnium dioxide polymorphs"
Authors/Creators
-
1.
Massachusetts Institute of Technology
Description
This repository archives the training datasets and Environment-Adaptive Proper Orthogonal Descriptor (EA-POD) machine-learned interatomic potentials (MLIPs) for hafnium and hafnium dioxide.
More information about input scripts to train custom potentials and benchmarks between EA-POD and other state-of-the-art MLIPs can be found in: https://github.com/cesmix-mit/EAPOD-HfO
Files
Files
(60.2 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:491299f62ed31e76b7bf1e7def25ecd2
|
22.9 MB | Download |
|
md5:12571cb988c668b67aac3553d788162c
|
183.5 kB | Download |
|
md5:cda88770ed53d73a98ba4884592d5f5b
|
1.0 kB | Download |
|
md5:8a9d4e18d8d0cbe9b413a5746a7c3c58
|
36.9 MB | Download |
|
md5:e4b509a6aa5b1820849948f7afeef50e
|
234.2 kB | Download |
|
md5:7972853dea9992eed94bdf8d0af105d1
|
1.1 kB | Download |
Additional details
Related works
- Is described by
- Journal article: 10.1103/PhysRevB.110.064101 (DOI)
- Journal article: 10.1103/PhysRevB.107.144103 (DOI)
- Is published in
- Journal article: 10.1038/s41524-026-01984-4 (DOI)
Funding
- United States Department of Energy
- DE-NA0003965
- United States Air Force Office of Scientific Research
- FA9550-22-1-0356
Software
- Repository URL
- https://github.com/cesmix-mit/EAPOD-HfO