Elucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning
Abstract Prediction of material behavior using machine learning (ML) requires consistent, accurate, and, representative large data for training. However, such consistent and reliable experimental datasets are not always available for materials. To address this challenge, we synergistically integrate...
Guardado en:
Autores principales: | , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2020
|
Materias: | |
Acceso en línea: | https://doaj.org/article/fd3045a55ad34dad90972c487c16a063 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:fd3045a55ad34dad90972c487c16a063 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:fd3045a55ad34dad90972c487c16a0632021-12-02T15:09:32ZElucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning10.1038/s41598-020-78368-12045-2322https://doaj.org/article/fd3045a55ad34dad90972c487c16a0632020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-78368-1https://doaj.org/toc/2045-2322Abstract Prediction of material behavior using machine learning (ML) requires consistent, accurate, and, representative large data for training. However, such consistent and reliable experimental datasets are not always available for materials. To address this challenge, we synergistically integrate ML with high-throughput reactive molecular dynamics (MD) simulations to elucidate the constitutive relationship of calcium–silicate–hydrate (C–S–H) gel—the primary binding phase in concrete formed via the hydration of ordinary portland cement. Specifically, a highly consistent dataset on the nine elastic constants of more than 300 compositions of C–S–H gel is developed using high-throughput reactive simulations. From a comparative analysis of various ML algorithms including neural networks (NN) and Gaussian process (GP), we observe that NN provides excellent predictions. To interpret the predicted results from NN, we employ SHapley Additive exPlanations (SHAP), which reveals that the influence of silicate network on all the elastic constants of C–S–H is significantly higher than that of water and CaO content. Additionally, the water content is found to have a more prominent influence on the shear components than the normal components along the direction of the interlayer spaces within C–S–H. This result suggests that the in-plane elastic response is controlled by water molecules whereas the transverse response is mainly governed by the silicate network. Overall, by seamlessly integrating MD simulations with ML, this paper can be used as a starting point toward accelerated optimization of C–S–H nanostructures to design efficient cementitious binders with targeted properties.Gideon A. LyngdohHewenxuan LiMohd ZakiN. M. Anoop KrishnanSumanta DasNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-15 (2020) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Gideon A. Lyngdoh Hewenxuan Li Mohd Zaki N. M. Anoop Krishnan Sumanta Das Elucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning |
description |
Abstract Prediction of material behavior using machine learning (ML) requires consistent, accurate, and, representative large data for training. However, such consistent and reliable experimental datasets are not always available for materials. To address this challenge, we synergistically integrate ML with high-throughput reactive molecular dynamics (MD) simulations to elucidate the constitutive relationship of calcium–silicate–hydrate (C–S–H) gel—the primary binding phase in concrete formed via the hydration of ordinary portland cement. Specifically, a highly consistent dataset on the nine elastic constants of more than 300 compositions of C–S–H gel is developed using high-throughput reactive simulations. From a comparative analysis of various ML algorithms including neural networks (NN) and Gaussian process (GP), we observe that NN provides excellent predictions. To interpret the predicted results from NN, we employ SHapley Additive exPlanations (SHAP), which reveals that the influence of silicate network on all the elastic constants of C–S–H is significantly higher than that of water and CaO content. Additionally, the water content is found to have a more prominent influence on the shear components than the normal components along the direction of the interlayer spaces within C–S–H. This result suggests that the in-plane elastic response is controlled by water molecules whereas the transverse response is mainly governed by the silicate network. Overall, by seamlessly integrating MD simulations with ML, this paper can be used as a starting point toward accelerated optimization of C–S–H nanostructures to design efficient cementitious binders with targeted properties. |
format |
article |
author |
Gideon A. Lyngdoh Hewenxuan Li Mohd Zaki N. M. Anoop Krishnan Sumanta Das |
author_facet |
Gideon A. Lyngdoh Hewenxuan Li Mohd Zaki N. M. Anoop Krishnan Sumanta Das |
author_sort |
Gideon A. Lyngdoh |
title |
Elucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning |
title_short |
Elucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning |
title_full |
Elucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning |
title_fullStr |
Elucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning |
title_full_unstemmed |
Elucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning |
title_sort |
elucidating the constitutive relationship of calcium–silicate–hydrate gel using high throughput reactive molecular simulations and machine learning |
publisher |
Nature Portfolio |
publishDate |
2020 |
url |
https://doaj.org/article/fd3045a55ad34dad90972c487c16a063 |
work_keys_str_mv |
AT gideonalyngdoh elucidatingtheconstitutiverelationshipofcalciumsilicatehydrategelusinghighthroughputreactivemolecularsimulationsandmachinelearning AT hewenxuanli elucidatingtheconstitutiverelationshipofcalciumsilicatehydrategelusinghighthroughputreactivemolecularsimulationsandmachinelearning AT mohdzaki elucidatingtheconstitutiverelationshipofcalciumsilicatehydrategelusinghighthroughputreactivemolecularsimulationsandmachinelearning AT nmanoopkrishnan elucidatingtheconstitutiverelationshipofcalciumsilicatehydrategelusinghighthroughputreactivemolecularsimulationsandmachinelearning AT sumantadas elucidatingtheconstitutiverelationshipofcalciumsilicatehydrategelusinghighthroughputreactivemolecularsimulationsandmachinelearning |
_version_ |
1718387853758562304 |