TY - JOUR
T1 - Predicting glass structure by physics-informed machine learning
AU - Bødker, Mikkel L.
AU - Bauchy, Mathieu
AU - Du, Tao
AU - Mauro, John C.
AU - Smedskjaer, Morten M.
N1 - Publisher Copyright:
© 2022, The Author(s).
PY - 2022/12
Y1 - 2022/12
N2 - Machine learning (ML) is emerging as a powerful tool to predict the properties of materials, including glasses. Informing ML models with knowledge of how glass composition affects short-range atomic structure has the potential to enhance the ability of composition-property models to extrapolate accurately outside of their training sets. Here, we introduce an approach wherein statistical mechanics informs a ML model that can predict the non-linear composition-structure relations in oxide glasses. This combined model offers an improved prediction compared to models relying solely on statistical physics or machine learning individually. Specifically, we show that the combined model accurately both interpolates and extrapolates the structure of Na2O–SiO2 glasses. Importantly, the model is able to extrapolate predictions outside its training set, which is evidenced by the fact that it is able to predict the structure of a glass series that was kept fully hidden from the model during its training.
AB - Machine learning (ML) is emerging as a powerful tool to predict the properties of materials, including glasses. Informing ML models with knowledge of how glass composition affects short-range atomic structure has the potential to enhance the ability of composition-property models to extrapolate accurately outside of their training sets. Here, we introduce an approach wherein statistical mechanics informs a ML model that can predict the non-linear composition-structure relations in oxide glasses. This combined model offers an improved prediction compared to models relying solely on statistical physics or machine learning individually. Specifically, we show that the combined model accurately both interpolates and extrapolates the structure of Na2O–SiO2 glasses. Importantly, the model is able to extrapolate predictions outside its training set, which is evidenced by the fact that it is able to predict the structure of a glass series that was kept fully hidden from the model during its training.
UR - http://www.scopus.com/inward/record.url?scp=85138220858&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85138220858&partnerID=8YFLogxK
U2 - 10.1038/s41524-022-00882-9
DO - 10.1038/s41524-022-00882-9
M3 - Article
AN - SCOPUS:85138220858
SN - 2057-3960
VL - 8
JO - npj Computational Materials
JF - npj Computational Materials
IS - 1
M1 - 192
ER -