Cover Image

A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon

The adsorption of dyes using 39 adsorbents (16 kinds of agro-wastes) were modeled using random forest (RF), decision tree (DT), and gradient boosting (GB) models based on 350 sets of adsorption experimental data. In addition, the correlation between variables and their importance was applied. After...

Full description

Saved in:
Bibliographic Details
Main Authors: Moosavi, Seyedehmaryam, Manta, Otilia, El-Badry, Yaser A., Hussein, Enas E., El-Bahy, Zeinhom M., Mohd Fawzi, Noor fariza Binti, Urbonavicius, Jaunius, Moosavi, Seyed Mohammad Hossein
Format: Article
Published: MDPI 2021
Subjects:
QC Physics
QD Chemistry
Online Access:http://eprints.um.edu.my/33885/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.33885
record_format eprints
spelling my.um.eprints.338852022-07-18T07:07:20Z http://eprints.um.edu.my/33885/ A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon Moosavi, Seyedehmaryam Manta, Otilia El-Badry, Yaser A. Hussein, Enas E. El-Bahy, Zeinhom M. Mohd Fawzi, Noor fariza Binti Urbonavicius, Jaunius Moosavi, Seyed Mohammad Hossein QC Physics QD Chemistry The adsorption of dyes using 39 adsorbents (16 kinds of agro-wastes) were modeled using random forest (RF), decision tree (DT), and gradient boosting (GB) models based on 350 sets of adsorption experimental data. In addition, the correlation between variables and their importance was applied. After comprehensive feature selection analysis, five important variables were selected from nine variables. The RF with the highest accuracy (R-2 = 0.9) was selected as the best model for prediction of adsorption capacity of agro-waste using the five selected variables. The results suggested that agro-waste characteristics (pore volume, surface area, agro-waste pH, and particle size) accounted for 50.7% contribution for adsorption efficiency. The pore volume and surface area are the most important influencing variables among the agro-waste characteristics, while the role of particle size was inconspicuous. The accurate ability of the developed models' prediction could significantly reduce experimental screening efforts, such as predicting the dye removal efficiency of agro-waste activated carbon according to agro-waste characteristics. The relative importance of variables could provide a right direction for better treatments of dyes in the real wastewater. MDPI 2021-10 Article PeerReviewed Moosavi, Seyedehmaryam and Manta, Otilia and El-Badry, Yaser A. and Hussein, Enas E. and El-Bahy, Zeinhom M. and Mohd Fawzi, Noor fariza Binti and Urbonavicius, Jaunius and Moosavi, Seyed Mohammad Hossein (2021) A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon. Nanomaterials, 11 (10). ISSN 2079-4991, DOI https://doi.org/10.3390/nano11102734 <https://doi.org/10.3390/nano11102734>. 10.3390/nano11102734
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic QC Physics
QD Chemistry
spellingShingle QC Physics
QD Chemistry
Moosavi, Seyedehmaryam
Manta, Otilia
El-Badry, Yaser A.
Hussein, Enas E.
El-Bahy, Zeinhom M.
Mohd Fawzi, Noor fariza Binti
Urbonavicius, Jaunius
Moosavi, Seyed Mohammad Hossein
A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon
description The adsorption of dyes using 39 adsorbents (16 kinds of agro-wastes) were modeled using random forest (RF), decision tree (DT), and gradient boosting (GB) models based on 350 sets of adsorption experimental data. In addition, the correlation between variables and their importance was applied. After comprehensive feature selection analysis, five important variables were selected from nine variables. The RF with the highest accuracy (R-2 = 0.9) was selected as the best model for prediction of adsorption capacity of agro-waste using the five selected variables. The results suggested that agro-waste characteristics (pore volume, surface area, agro-waste pH, and particle size) accounted for 50.7% contribution for adsorption efficiency. The pore volume and surface area are the most important influencing variables among the agro-waste characteristics, while the role of particle size was inconspicuous. The accurate ability of the developed models' prediction could significantly reduce experimental screening efforts, such as predicting the dye removal efficiency of agro-waste activated carbon according to agro-waste characteristics. The relative importance of variables could provide a right direction for better treatments of dyes in the real wastewater.
format Article
author Moosavi, Seyedehmaryam
Manta, Otilia
El-Badry, Yaser A.
Hussein, Enas E.
El-Bahy, Zeinhom M.
Mohd Fawzi, Noor fariza Binti
Urbonavicius, Jaunius
Moosavi, Seyed Mohammad Hossein
author_facet Moosavi, Seyedehmaryam
Manta, Otilia
El-Badry, Yaser A.
Hussein, Enas E.
El-Bahy, Zeinhom M.
Mohd Fawzi, Noor fariza Binti
Urbonavicius, Jaunius
Moosavi, Seyed Mohammad Hossein
author_sort Moosavi, Seyedehmaryam
title A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon
title_short A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon
title_full A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon
title_fullStr A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon
title_full_unstemmed A study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon
title_sort study on machine learning methods' application for dye adsorption prediction onto agricultural waste activated carbon
publisher MDPI
publishDate 2021
url http://eprints.um.edu.my/33885/
_version_ 1739828478956535808
score 13.211869

Similar Items