Publications Repository - Helmholtz-Zentrum Dresden-Rossendorf
2 PublicationsMachine Learning-Driven Structure Prediction for Iron Hydrides
Tahmasbi, H.; Ramakrishna, K.; Lokamani, M.; Cangi, A.
We created a computational workflow to analyze the potential energy surface (PES) of materials using machine-learned interatomic potentials in conjunction with the minima hopping algorithm. We demonstrate this method by producing a versatile machine-learned interatomic potential for iron hydride via a neural network using an iterative training process to explore its energy landscape under different pressures. To evaluate the accuracy and comprehend the intricacies of the PES, we conducted comprehensive crystal structure predictions using our neural network-based potential paired with the minima hopping approach. The predictions spanned pressures ranging from ambient to 100 GPa. Our results reproduce the experimentally verified global minimum structures such as \textit{dhcp}, \textit{hcp}, and \textit{fcc}, corroborating previous findings. Furthermore, our in-depth exploration of the iron hydride PES at different pressures has revealed complex alterations and stacking faults in these phases, leading to the identification of several new low-enthalpy structures. This investigation has not only confirmed the presence of regions of established FeH configurations but has also highlighted the efficacy of using data-driven, extensive structure prediction methods to uncover the multifaceted PES of materials.
Related publications
-
Data publication: Machine Learning-Driven Structure Prediction for Iron Hydrides
ROBIS: 38894 HZDR-primary research data are used by this (Id 37800) publication -
Data publication: Machine Learning-Driven Structure Prediction for Iron Hydrides
RODARE: 2778 HZDR-primary research data are used by this (Id 37800) publication
-
Contribution to WWW
https://arxiv.org/abs/2311.06010
DOI: 10.48550/arXiv.2311.06010
arXiv: 2311.06010 -
Physical Review Materials 8(2024), 033803
DOI: 10.1103/PhysRevMaterials.8.033803
Downloads
- Open Access Version from arxiv.org
- Secondary publication expected from 21.03.2025
Permalink: https://www.hzdr.de/publications/Publ-37800