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 pote...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 Na_(2)O–SiO_(2)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.展开更多
基金This work was supported by the Independent Research Fund Denmark(grant no.7017-00019)the Elite Research Travel Grant awarded to M.L.B.by the Danish Ministry of Higher Education and Science(grant no.9095-00019A)M.B.acknowledges funding from the National Science Foundation under the grants DMR-1944510,DMR-1928538,and CMMI-1826420.
文摘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 Na_(2)O–SiO_(2)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.