Cargando…

Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions

[Image: see text] There currently exist no quantitative methods to determine the appropriate conditions for solid-state synthesis. This not only hinders the experimental realization of novel materials but also complicates the interpretation and understanding of solid-state reaction mechanisms. Here,...

Descripción completa

Detalles Bibliográficos
Autores principales: Huo, Haoyan, Bartel, Christopher J., He, Tanjin, Trewartha, Amalie, Dunn, Alexander, Ouyang, Bin, Jain, Anubhav, Ceder, Gerbrand
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2022
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9407029/
https://www.ncbi.nlm.nih.gov/pubmed/36032555
http://dx.doi.org/10.1021/acs.chemmater.2c01293
_version_ 1784774264819286016
author Huo, Haoyan
Bartel, Christopher J.
He, Tanjin
Trewartha, Amalie
Dunn, Alexander
Ouyang, Bin
Jain, Anubhav
Ceder, Gerbrand
author_facet Huo, Haoyan
Bartel, Christopher J.
He, Tanjin
Trewartha, Amalie
Dunn, Alexander
Ouyang, Bin
Jain, Anubhav
Ceder, Gerbrand
author_sort Huo, Haoyan
collection PubMed
description [Image: see text] There currently exist no quantitative methods to determine the appropriate conditions for solid-state synthesis. This not only hinders the experimental realization of novel materials but also complicates the interpretation and understanding of solid-state reaction mechanisms. Here, we demonstrate a machine-learning approach that predicts synthesis conditions using large solid-state synthesis data sets text-mined from scientific journal articles. Using feature importance ranking analysis, we discovered that optimal heating temperatures have strong correlations with the stability of precursor materials quantified using melting points and formation energies (ΔG(f), ΔH(f)). In contrast, features derived from the thermodynamics of synthesis-related reactions did not directly correlate to the chosen heating temperatures. This correlation between optimal solid-state heating temperature and precursor stability extends Tamman’s rule from intermetallics to oxide systems, suggesting the importance of reaction kinetics in determining synthesis conditions. Heating times are shown to be strongly correlated with the chosen experimental procedures and instrument setups, which may be indicative of human bias in the data set. Using these predictive features, we constructed machine-learning models with good performance and general applicability to predict the conditions required to synthesize diverse chemical systems.
format Online
Article
Text
id pubmed-9407029
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-94070292022-08-26 Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions Huo, Haoyan Bartel, Christopher J. He, Tanjin Trewartha, Amalie Dunn, Alexander Ouyang, Bin Jain, Anubhav Ceder, Gerbrand Chem Mater [Image: see text] There currently exist no quantitative methods to determine the appropriate conditions for solid-state synthesis. This not only hinders the experimental realization of novel materials but also complicates the interpretation and understanding of solid-state reaction mechanisms. Here, we demonstrate a machine-learning approach that predicts synthesis conditions using large solid-state synthesis data sets text-mined from scientific journal articles. Using feature importance ranking analysis, we discovered that optimal heating temperatures have strong correlations with the stability of precursor materials quantified using melting points and formation energies (ΔG(f), ΔH(f)). In contrast, features derived from the thermodynamics of synthesis-related reactions did not directly correlate to the chosen heating temperatures. This correlation between optimal solid-state heating temperature and precursor stability extends Tamman’s rule from intermetallics to oxide systems, suggesting the importance of reaction kinetics in determining synthesis conditions. Heating times are shown to be strongly correlated with the chosen experimental procedures and instrument setups, which may be indicative of human bias in the data set. Using these predictive features, we constructed machine-learning models with good performance and general applicability to predict the conditions required to synthesize diverse chemical systems. American Chemical Society 2022-08-05 2022-08-23 /pmc/articles/PMC9407029/ /pubmed/36032555 http://dx.doi.org/10.1021/acs.chemmater.2c01293 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 Huo, Haoyan
Bartel, Christopher J.
He, Tanjin
Trewartha, Amalie
Dunn, Alexander
Ouyang, Bin
Jain, Anubhav
Ceder, Gerbrand
Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions
title Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions
title_full Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions
title_fullStr Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions
title_full_unstemmed Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions
title_short Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions
title_sort machine-learning rationalization and prediction of solid-state synthesis conditions
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9407029/
https://www.ncbi.nlm.nih.gov/pubmed/36032555
http://dx.doi.org/10.1021/acs.chemmater.2c01293
work_keys_str_mv AT huohaoyan machinelearningrationalizationandpredictionofsolidstatesynthesisconditions
AT bartelchristopherj machinelearningrationalizationandpredictionofsolidstatesynthesisconditions
AT hetanjin machinelearningrationalizationandpredictionofsolidstatesynthesisconditions
AT trewarthaamalie machinelearningrationalizationandpredictionofsolidstatesynthesisconditions
AT dunnalexander machinelearningrationalizationandpredictionofsolidstatesynthesisconditions
AT ouyangbin machinelearningrationalizationandpredictionofsolidstatesynthesisconditions
AT jainanubhav machinelearningrationalizationandpredictionofsolidstatesynthesisconditions
AT cedergerbrand machinelearningrationalizationandpredictionofsolidstatesynthesisconditions