Accelerating high-throughput phonon calculations via machine learning universal potentials
Authors:
- Huiju LeeHLHuiju Lee
- Vinay I. HegdeVHVinay I. Hegde
- Chris WolvertonCWChris Wolverton
- Yi XiaYXYi Xia
- 7 March 2025
- journal article
- Published by Elsevier in Materials Today Physics
- Vol. 53
Abstract
No abstract availableAll Related Versions
Funding Information
- National Science Foundation (2138296, 2138307, 2137603, 2138286, 2138259, DMR-2317008)
- Computer and Information Science and Engineering Office of Advanced Cyberinfrastructure (OAC-2311203)
- National Science Foundation Division of Materials Research (2317008)
This publication has 37 references indexed in Scilit:
- Predicting Lattice Vibrational Frequencies Using Deep Graph Neural NetworksACS Omega, 2022
- E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentialsNature Communications, 2022
- Quantum chemical accuracy from density functional approximations via machine learningNature Communications, 2020
- Exploring Two-Dimensional Materials Thermodynamic Stability via Machine LearningACS Applied Materials & Interfaces, 2019
- Reproducibility of vibrational free energy by different methodsComputational Materials Science, 2018
- How Chemical Composition Alone Can Predict Vibrational Free Energies and Entropies of SolidsChemistry of Materials, 2017
- Predicting the Thermodynamic Stability of Solids Combining Density Functional Theory and Machine LearningChemistry of Materials, 2017
- The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energiesnpj Computational Materials, 2015
- Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD)JOM, 2013
- Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis setComputational Materials Science, 1996