A Wrong Ground-State Structure of HfO2 Predicted by Machine-Learning Interatomic Potentials Based on the Perdew−Burke−Ernzerhof Functional

Abstract Machine-learning interatomic potentials (MLIPs) have become powerful tools for material simulations. Many MLIPs are trained based on density functional theory (DFT) datasets generated with the Perdew−Burke−Ernzerhof (PBE) exchange−correlation functional. Using a PBE-based MLIP for HfO2, we identify a low-energy I41/amd structure, which is predicted to be more stable than the well-known ground-state structure, the monoclinic P21/c structure. Since experiments show clearly that HfO2 takes the P21/c structure as the ground state, this is obviously a wrong prediction. Unfortunately, the same prediction is also made by widely used PBE-based foundation models, such as NequIP-OAM-L and MatterSim-v1-5M. Comparisons among different DFT functionals in this work show that PBE exhibits stabilization of low-density structures containing sixfold Hf−O octahedral units, such as the I41/amd and Pbcn phases, leading to incorrect energetic ordering. The error also affects the calculated energy landscapes and barrier heights along ferroelectric HfO2 polarization switching paths when there are large lattice relaxations. Fortunately, the error can be largely suppressed by other functionals such as PBEsol and local density approximation. Our study serves as a warning about the impact of errors in exchange−correlation functional approximations on the reliability of MLIP simulations of crystal structures and phase transitions.

Authors

Institutions

Publication Details

Journal
Chemistry of Materials
Published
2026-11-17
DOI
https://doi.org/10.1021/acs.chemmater.6c01853
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Wrong Ground-State Structure of HfO2 Predicted by Machine-Learning Interatomic Potentials Based on the Perdew−Burke−Ernzerhof Functional

Jinchen Wei, Shuqi Tang, Shiyou Chen, Menglin Huang et al.
2 links
Chemistry of Materials
Machine Learning in Materials Science
article

A Wrong Ground-State Structure of HfO2 Predicted by Machine-Learning Interatomic Potentials Based on the Perdew−Burke−Ernzerhof Functional

Jinchen Wei, Shuqi Tang, Shiyou Chen, Menglin Huang, Yihan Zhang, Junjie Zhou, Kang Wang
article en

Abstract

Abstract Machine-learning interatomic potentials (MLIPs) have become powerful tools for material simulations. Many MLIPs are trained based on density functional theory (DFT) datasets generated with the Perdew−Burke−Ernzerhof (PBE) exchange−correlation functional. Using a PBE-based MLIP for HfO2, we identify a low-energy I41/amd structure, which is predicted to be more stable than the well-known ground-state structure, the monoclinic P21/c structure. Since experiments show clearly that HfO2 takes the P21/c structure as the ground state, this is obviously a wrong prediction. Unfortunately, the same prediction is also made by widely used PBE-based foundation models, such as NequIP-OAM-L and MatterSim-v1-5M. Comparisons among different DFT functionals in this work show that PBE exhibits stabilization of low-density structures containing sixfold Hf−O octahedral units, such as the I41/amd and Pbcn phases, leading to incorrect energetic ordering. The error also affects the calculated energy landscapes and barrier heights along ferroelectric HfO2 polarization switching paths when there are large lattice relaxations. Fortunately, the error can be largely suppressed by other functionals such as PBEsol and local density approximation. Our study serves as a warning about the impact of errors in exchange−correlation functional approximations on the reliability of MLIP simulations of crystal structures and phase transitions.

Chemistry of Materials
Fudan University (CN)
National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality, National Key Research and Development Program of China
Machine Learning in Materials Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon