Nanoscale slip length prediction with machine learning tools

Abstract This work incorporates machine learning (ML) techniques, such as multivariate regression, the multi-layer perceptron, and random forest to predict the slip length at the nanoscale. Data points are collected both from our simulation data and data from the literature, and comprise Molecular D...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Filippos Sofos, Theodoros E. Karakasidis
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/42a0d2d89ab94a18bd3f2b823ffb3de8
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:42a0d2d89ab94a18bd3f2b823ffb3de8
record_format dspace
spelling oai:doaj.org-article:42a0d2d89ab94a18bd3f2b823ffb3de82021-12-02T16:04:13ZNanoscale slip length prediction with machine learning tools10.1038/s41598-021-91885-x2045-2322https://doaj.org/article/42a0d2d89ab94a18bd3f2b823ffb3de82021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-91885-xhttps://doaj.org/toc/2045-2322Abstract This work incorporates machine learning (ML) techniques, such as multivariate regression, the multi-layer perceptron, and random forest to predict the slip length at the nanoscale. Data points are collected both from our simulation data and data from the literature, and comprise Molecular Dynamics simulations of simple monoatomic, polar, and molecular liquids. Training and test points cover a wide range of input parameters which have been found to affect the slip length value, concerning dynamical and geometrical characteristics of the model, along with simulation parameters that constitute the simulation conditions. The aim of this work is to suggest an accurate and efficient procedure capable of reproducing physical properties, such as the slip length, acting parallel to simulation methods. Non-linear models, based on neural networks and decision trees, have been found to achieve better performance compared to linear regression methods. After the model is trained on representative simulation data, it is capable of accurately predicting the slip length values in regions between or in close proximity to the input data range, at the nanoscale. Results also reveal that, as channel dimensions increase, the slip length turns into a size-independent material property, affected mainly by wall roughness and wettability.Filippos SofosTheodoros E. KarakasidisNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Filippos Sofos
Theodoros E. Karakasidis
Nanoscale slip length prediction with machine learning tools
description Abstract This work incorporates machine learning (ML) techniques, such as multivariate regression, the multi-layer perceptron, and random forest to predict the slip length at the nanoscale. Data points are collected both from our simulation data and data from the literature, and comprise Molecular Dynamics simulations of simple monoatomic, polar, and molecular liquids. Training and test points cover a wide range of input parameters which have been found to affect the slip length value, concerning dynamical and geometrical characteristics of the model, along with simulation parameters that constitute the simulation conditions. The aim of this work is to suggest an accurate and efficient procedure capable of reproducing physical properties, such as the slip length, acting parallel to simulation methods. Non-linear models, based on neural networks and decision trees, have been found to achieve better performance compared to linear regression methods. After the model is trained on representative simulation data, it is capable of accurately predicting the slip length values in regions between or in close proximity to the input data range, at the nanoscale. Results also reveal that, as channel dimensions increase, the slip length turns into a size-independent material property, affected mainly by wall roughness and wettability.
format article
author Filippos Sofos
Theodoros E. Karakasidis
author_facet Filippos Sofos
Theodoros E. Karakasidis
author_sort Filippos Sofos
title Nanoscale slip length prediction with machine learning tools
title_short Nanoscale slip length prediction with machine learning tools
title_full Nanoscale slip length prediction with machine learning tools
title_fullStr Nanoscale slip length prediction with machine learning tools
title_full_unstemmed Nanoscale slip length prediction with machine learning tools
title_sort nanoscale slip length prediction with machine learning tools
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/42a0d2d89ab94a18bd3f2b823ffb3de8
work_keys_str_mv AT filippossofos nanoscalesliplengthpredictionwithmachinelearningtools
AT theodorosekarakasidis nanoscalesliplengthpredictionwithmachinelearningtools
_version_ 1718385267484655616