Cargando…

Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning

[Image: see text] The application of machine learning to predict materials properties measured by experiments are valuable yet difficult due to the limited amount of experimental data. In this work, we use a multifidelity random forest model to learn the experimental formation enthalpy of materials...

Descripción completa

Detalles Bibliográficos
Autores principales: Gong, Sheng, Wang, Shuo, Xie, Tian, Chae, Woo Hyun, Liu, Runze, Shao-Horn, Yang, Grossman, Jeffrey C.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2022
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9516701/
https://www.ncbi.nlm.nih.gov/pubmed/36186569
http://dx.doi.org/10.1021/jacsau.2c00235
_version_ 1784798765522092032
author Gong, Sheng
Wang, Shuo
Xie, Tian
Chae, Woo Hyun
Liu, Runze
Shao-Horn, Yang
Grossman, Jeffrey C.
author_facet Gong, Sheng
Wang, Shuo
Xie, Tian
Chae, Woo Hyun
Liu, Runze
Shao-Horn, Yang
Grossman, Jeffrey C.
author_sort Gong, Sheng
collection PubMed
description [Image: see text] The application of machine learning to predict materials properties measured by experiments are valuable yet difficult due to the limited amount of experimental data. In this work, we use a multifidelity random forest model to learn the experimental formation enthalpy of materials with prediction accuracy higher than the Perdew–Burke–Ernzerhof (PBE) functional with linear correction, PBEsol, and meta-generalized gradient approximation (meta-GGA) functionals (SCAN and r(2)SCAN), and it outperforms the hotly studied deep neural network-based representation learning and transfer learning. We then use the model to calibrate the DFT formation enthalpy in the Materials Project database and discover materials with underestimated stability. The multifidelity model is also used as a data-mining approach to find how DFT deviates from experiments by explaining the model output.
format Online
Article
Text
id pubmed-9516701
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-95167012022-09-29 Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning Gong, Sheng Wang, Shuo Xie, Tian Chae, Woo Hyun Liu, Runze Shao-Horn, Yang Grossman, Jeffrey C. JACS Au [Image: see text] The application of machine learning to predict materials properties measured by experiments are valuable yet difficult due to the limited amount of experimental data. In this work, we use a multifidelity random forest model to learn the experimental formation enthalpy of materials with prediction accuracy higher than the Perdew–Burke–Ernzerhof (PBE) functional with linear correction, PBEsol, and meta-generalized gradient approximation (meta-GGA) functionals (SCAN and r(2)SCAN), and it outperforms the hotly studied deep neural network-based representation learning and transfer learning. We then use the model to calibrate the DFT formation enthalpy in the Materials Project database and discover materials with underestimated stability. The multifidelity model is also used as a data-mining approach to find how DFT deviates from experiments by explaining the model output. American Chemical Society 2022-09-09 /pmc/articles/PMC9516701/ /pubmed/36186569 http://dx.doi.org/10.1021/jacsau.2c00235 Text en © 2022 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Gong, Sheng
Wang, Shuo
Xie, Tian
Chae, Woo Hyun
Liu, Runze
Shao-Horn, Yang
Grossman, Jeffrey C.
Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning
title Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning
title_full Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning
title_fullStr Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning
title_full_unstemmed Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning
title_short Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning
title_sort calibrating dft formation enthalpy calculations by multifidelity machine learning
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9516701/
https://www.ncbi.nlm.nih.gov/pubmed/36186569
http://dx.doi.org/10.1021/jacsau.2c00235
work_keys_str_mv AT gongsheng calibratingdftformationenthalpycalculationsbymultifidelitymachinelearning
AT wangshuo calibratingdftformationenthalpycalculationsbymultifidelitymachinelearning
AT xietian calibratingdftformationenthalpycalculationsbymultifidelitymachinelearning
AT chaewoohyun calibratingdftformationenthalpycalculationsbymultifidelitymachinelearning
AT liurunze calibratingdftformationenthalpycalculationsbymultifidelitymachinelearning
AT shaohornyang calibratingdftformationenthalpycalculationsbymultifidelitymachinelearning
AT grossmanjeffreyc calibratingdftformationenthalpycalculationsbymultifidelitymachinelearning