Predicting the dissolution kinetics of silicate glasses using machine learning

N. M. Anoop Krishnan, Sujith Mangalathu, Morten Mattrup Smedskjær, Adama Tandia, Henry Burton, Mathieu Bauchy

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

19 Citationer (Scopus)

Resumé

Predicting the dissolution rates of silicate glasses in aqueous conditions is a complex task as the underlying mechanism(s) remain poorly understood and the dissolution kinetics can depend on a large number of intrinsic and extrinsic factors. Here, we assess the potential of data-driven models based on machine learning to predict the dissolution rates of various aluminosilicate glasses exposed to a wide range of solution pH values, from acidic to caustic conditions. Four classes of machine learning methods are investigated, namely, linear regression, support vector machine regression, random forest, and artificial neural network. We observe that, although linear methods all fail to describe the dissolution kinetics, the artificial neural network approach offers excellent predictions, even for untrained data, thanks to its inherent ability to handle non-linear data. We further note that the predictive ability of simpler methods, such as linear regression, could be improved using additional physics-based constraints. Such methods, called as physics-informed machine learning can be used to extrapolate the behavior of untrained compositions as well. Overall, we suggest that a more extensive use of machine learning approaches could significantly accelerate the design of novel glasses with tailored properties.

OriginalsprogEngelsk
TidsskriftJournal of Non-Crystalline Solids
Vol/bind487
Sider (fra-til)37-45
Antal sider9
ISSN0022-3093
DOI
StatusUdgivet - 1 maj 2018

Fingerprint

Silicates
machine learning
Learning systems
silicates
dissolving
Dissolution
regression analysis
Glass
Kinetics
glass
kinetics
Linear regression
Physics
Neural networks
Caustics
physics
Aluminosilicates
Support vector machines
alkalies
predictions

Citer dette

Krishnan, N. M. Anoop ; Mangalathu, Sujith ; Smedskjær, Morten Mattrup ; Tandia, Adama ; Burton, Henry ; Bauchy, Mathieu. / Predicting the dissolution kinetics of silicate glasses using machine learning. I: Journal of Non-Crystalline Solids. 2018 ; Bind 487. s. 37-45.
@article{535c36bfa46e4b3bbd07c8adcb678d34,
title = "Predicting the dissolution kinetics of silicate glasses using machine learning",
abstract = "Predicting the dissolution rates of silicate glasses in aqueous conditions is a complex task as the underlying mechanism(s) remain poorly understood and the dissolution kinetics can depend on a large number of intrinsic and extrinsic factors. Here, we assess the potential of data-driven models based on machine learning to predict the dissolution rates of various aluminosilicate glasses exposed to a wide range of solution pH values, from acidic to caustic conditions. Four classes of machine learning methods are investigated, namely, linear regression, support vector machine regression, random forest, and artificial neural network. We observe that, although linear methods all fail to describe the dissolution kinetics, the artificial neural network approach offers excellent predictions, even for untrained data, thanks to its inherent ability to handle non-linear data. We further note that the predictive ability of simpler methods, such as linear regression, could be improved using additional physics-based constraints. Such methods, called as physics-informed machine learning can be used to extrapolate the behavior of untrained compositions as well. Overall, we suggest that a more extensive use of machine learning approaches could significantly accelerate the design of novel glasses with tailored properties.",
author = "Krishnan, {N. M. Anoop} and Sujith Mangalathu and Smedskj{\ae}r, {Morten Mattrup} and Adama Tandia and Henry Burton and Mathieu Bauchy",
year = "2018",
month = "5",
day = "1",
doi = "10.1016/j.jnoncrysol.2018.02.023",
language = "English",
volume = "487",
pages = "37--45",
journal = "Journal of Non-Crystalline Solids",
issn = "0022-3093",
publisher = "Elsevier",

}

Predicting the dissolution kinetics of silicate glasses using machine learning. / Krishnan, N. M. Anoop; Mangalathu, Sujith; Smedskjær, Morten Mattrup; Tandia, Adama; Burton, Henry; Bauchy, Mathieu.

I: Journal of Non-Crystalline Solids, Bind 487, 01.05.2018, s. 37-45.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Predicting the dissolution kinetics of silicate glasses using machine learning

AU - Krishnan, N. M. Anoop

AU - Mangalathu, Sujith

AU - Smedskjær, Morten Mattrup

AU - Tandia, Adama

AU - Burton, Henry

AU - Bauchy, Mathieu

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Predicting the dissolution rates of silicate glasses in aqueous conditions is a complex task as the underlying mechanism(s) remain poorly understood and the dissolution kinetics can depend on a large number of intrinsic and extrinsic factors. Here, we assess the potential of data-driven models based on machine learning to predict the dissolution rates of various aluminosilicate glasses exposed to a wide range of solution pH values, from acidic to caustic conditions. Four classes of machine learning methods are investigated, namely, linear regression, support vector machine regression, random forest, and artificial neural network. We observe that, although linear methods all fail to describe the dissolution kinetics, the artificial neural network approach offers excellent predictions, even for untrained data, thanks to its inherent ability to handle non-linear data. We further note that the predictive ability of simpler methods, such as linear regression, could be improved using additional physics-based constraints. Such methods, called as physics-informed machine learning can be used to extrapolate the behavior of untrained compositions as well. Overall, we suggest that a more extensive use of machine learning approaches could significantly accelerate the design of novel glasses with tailored properties.

AB - Predicting the dissolution rates of silicate glasses in aqueous conditions is a complex task as the underlying mechanism(s) remain poorly understood and the dissolution kinetics can depend on a large number of intrinsic and extrinsic factors. Here, we assess the potential of data-driven models based on machine learning to predict the dissolution rates of various aluminosilicate glasses exposed to a wide range of solution pH values, from acidic to caustic conditions. Four classes of machine learning methods are investigated, namely, linear regression, support vector machine regression, random forest, and artificial neural network. We observe that, although linear methods all fail to describe the dissolution kinetics, the artificial neural network approach offers excellent predictions, even for untrained data, thanks to its inherent ability to handle non-linear data. We further note that the predictive ability of simpler methods, such as linear regression, could be improved using additional physics-based constraints. Such methods, called as physics-informed machine learning can be used to extrapolate the behavior of untrained compositions as well. Overall, we suggest that a more extensive use of machine learning approaches could significantly accelerate the design of novel glasses with tailored properties.

U2 - 10.1016/j.jnoncrysol.2018.02.023

DO - 10.1016/j.jnoncrysol.2018.02.023

M3 - Journal article

VL - 487

SP - 37

EP - 45

JO - Journal of Non-Crystalline Solids

JF - Journal of Non-Crystalline Solids

SN - 0022-3093

ER -