Enhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction

Nowadays, enhanced oil recovery using nanoparticles is considered an innovative approach to increase oil production. This paper focuses on predicting nanoparticles transport in porous media using machine learning techniques including random forest, gradient boosting regression, decision tree, and ar...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Budoor Alwated, Mohamed F. El-Amin
Formato:	article
Lenguaje:	EN
Publicado:	Yandy Scientific Press 2021
Materias:	enhanced oil recovery nanoparticles machine learning random forest artiﬁcial neural networks decision tree gradient boosting regression Engineering geology. Rock mechanics. Soil mechanics. Underground construction TA703-712 Geology QE1-996.5
Acceso en línea:	https://doaj.org/article/be6dd5985fb34eff82a92eb3a1389c52
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:be6dd5985fb34eff82a92eb3a1389c52
record_format	dspace
spelling	oai:doaj.org-article:be6dd5985fb34eff82a92eb3a1389c522021-11-08T07:10:45ZEnhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction10.46690/ager.2021.03.062208-598Xhttps://doaj.org/article/be6dd5985fb34eff82a92eb3a1389c522021-09-01T00:00:00Zhttps://www.yandy-ager.com/index.php/ager/article/view/334https://doaj.org/toc/2208-598XNowadays, enhanced oil recovery using nanoparticles is considered an innovative approach to increase oil production. This paper focuses on predicting nanoparticles transport in porous media using machine learning techniques including random forest, gradient boosting regression, decision tree, and artiﬁcial neural networks. Due to the lack of data on nanoparticles transport in porous media, this work generates artiﬁcial datasets using a numerical model that are validated against experimental data from the literature. Six experiments with different nanoparticles types with various physical features are selected to validate the numerical model. Therefore, the researchers produce six datasets from the experiments and create an additional dataset by combining all other datasets. Also, data preprocessing, correlation, and features importance methods are investigated using the Scikit-learn library. Moreover, hyperparameters tuning are optimized using the GridSearchCV algorithm. The performance of predictive models is evaluated using the mean absolute error, the R-squared correlation, the mean squared error, and the root mean squared error. The results show that the decision tree model has the best performance and highest accuracy in one of the datasets. On the other hand, the random forest model has the lowest root mean squared error and highest R-squared values in the rest of the datasets, including the combined dataset.Budoor AlwatedMohamed F. El-AminYandy Scientific Pressarticleenhanced oil recoverynanoparticlesmachine learningrandom forestartiﬁcial neural networksdecision treegradient boosting regressionEngineering geology. Rock mechanics. Soil mechanics. Underground constructionTA703-712GeologyQE1-996.5ENAdvances in Geo-Energy Research, Vol 5, Iss 3, Pp 297-317 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	enhanced oil recovery nanoparticles machine learning random forest artiﬁcial neural networks decision tree gradient boosting regression Engineering geology. Rock mechanics. Soil mechanics. Underground construction TA703-712 Geology QE1-996.5
spellingShingle	enhanced oil recovery nanoparticles machine learning random forest artiﬁcial neural networks decision tree gradient boosting regression Engineering geology. Rock mechanics. Soil mechanics. Underground construction TA703-712 Geology QE1-996.5 Budoor Alwated Mohamed F. El-Amin Enhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction
description	Nowadays, enhanced oil recovery using nanoparticles is considered an innovative approach to increase oil production. This paper focuses on predicting nanoparticles transport in porous media using machine learning techniques including random forest, gradient boosting regression, decision tree, and artiﬁcial neural networks. Due to the lack of data on nanoparticles transport in porous media, this work generates artiﬁcial datasets using a numerical model that are validated against experimental data from the literature. Six experiments with different nanoparticles types with various physical features are selected to validate the numerical model. Therefore, the researchers produce six datasets from the experiments and create an additional dataset by combining all other datasets. Also, data preprocessing, correlation, and features importance methods are investigated using the Scikit-learn library. Moreover, hyperparameters tuning are optimized using the GridSearchCV algorithm. The performance of predictive models is evaluated using the mean absolute error, the R-squared correlation, the mean squared error, and the root mean squared error. The results show that the decision tree model has the best performance and highest accuracy in one of the datasets. On the other hand, the random forest model has the lowest root mean squared error and highest R-squared values in the rest of the datasets, including the combined dataset.
format	article
author	Budoor Alwated Mohamed F. El-Amin
author_facet	Budoor Alwated Mohamed F. El-Amin
author_sort	Budoor Alwated
title	Enhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction
title_short	Enhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction
title_full	Enhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction
title_fullStr	Enhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction
title_full_unstemmed	Enhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction
title_sort	enhanced oil recovery by nanoparticles ﬂooding: from numerical modeling improvement to machine learning prediction
publisher	Yandy Scientific Press
publishDate	2021
url	https://doaj.org/article/be6dd5985fb34eff82a92eb3a1389c52
work_keys_str_mv	AT budooralwated enhancedoilrecoverybynanoparticlesfloodingfromnumericalmodelingimprovementtomachinelearningprediction AT mohamedfelamin enhancedoilrecoverybynanoparticlesfloodingfromnumericalmodelingimprovementtomachinelearningprediction
_version_	1718442941696966656

Enhanced oil recovery by nanoparticles ﬂooding: From numerical modeling improvement to machine learning prediction

Ejemplares similares