Artificial neural network approach for modelling of mercury ions removal from water using functionalized CNTs with deep eutectic solvent

Seef Saadi Fiyadh, Mohamed Khalid Alomar, Wan Zurina Binti Jaafar, Mohammed Abdulhakim Alsaadi, Sabah Saadi Fayaed, Suhana Binti Koting, Sai Hin Lai, Ming Fai Chow, Ali Najah Ahmed, Ahmed El-Shafie

Research output: Contribution to journalArticle

Abstract

Multi-walled carbon nanotubes (CNTs) functionalized with a deep eutectic solvent (DES) were utilized to remove mercury ions from water. An artificial neural network (ANN) technique was used for modelling the functionalized CNTs adsorption capacity. The amount of adsorbent dosage, contact time, mercury ions concentration and pH were varied, and the effect of parameters on the functionalized CNT adsorption capacity is observed. The (NARX) network, (FFNN) network and layer recurrent (LR) neural network were used. The model performance was compared using different indicators, including the root mean square error (RMSE), relative root mean square error (RRMSE), mean absolute percentage error (MAPE), mean square error (MSE), correlation coefficient (R2) and relative error (RE). Three kinetic models were applied to the experimental and predicted data; the pseudo second-order model was the best at describing the data. The maximum RE, R2 and MSE were 9.79%, 0.9701 and 1.15 × 10−3, respectively, for the NARX model; 15.02%, 0.9304 and 2.2 × 10−3 for the LR model; and 16.4%, 0.9313 and 2.27 × 10−3 for the FFNN model. The NARX model accurately predicted the adsorption capacity with better performance than the FFNN and LR models.

Original languageEnglish
Article number4206
JournalInternational journal of molecular sciences
Volume20
Issue number17
DOIs
Publication statusPublished - 01 Sep 2019

Fingerprint

Carbon Nanotubes
Mercury
eutectics
Eutectics
Adsorption
Carbon nanotubes
carbon nanotubes
Ions
Neural networks
Water
Mean square error
water
ions
root-mean-square errors
adsorption
Mercury (metal)
Recurrent neural networks
ion concentration
adsorbents
correlation coefficients

All Science Journal Classification (ASJC) codes

  • Catalysis
  • Molecular Biology
  • Spectroscopy
  • Computer Science Applications
  • Physical and Theoretical Chemistry
  • Organic Chemistry
  • Inorganic Chemistry

Cite this

Fiyadh, Seef Saadi ; Alomar, Mohamed Khalid ; Jaafar, Wan Zurina Binti ; Alsaadi, Mohammed Abdulhakim ; Fayaed, Sabah Saadi ; Koting, Suhana Binti ; Lai, Sai Hin ; Chow, Ming Fai ; Ahmed, Ali Najah ; El-Shafie, Ahmed. / Artificial neural network approach for modelling of mercury ions removal from water using functionalized CNTs with deep eutectic solvent. In: International journal of molecular sciences. 2019 ; Vol. 20, No. 17.
@article{e3613ae20bf34fbeb771dfb19b217d36,
title = "Artificial neural network approach for modelling of mercury ions removal from water using functionalized CNTs with deep eutectic solvent",
abstract = "Multi-walled carbon nanotubes (CNTs) functionalized with a deep eutectic solvent (DES) were utilized to remove mercury ions from water. An artificial neural network (ANN) technique was used for modelling the functionalized CNTs adsorption capacity. The amount of adsorbent dosage, contact time, mercury ions concentration and pH were varied, and the effect of parameters on the functionalized CNT adsorption capacity is observed. The (NARX) network, (FFNN) network and layer recurrent (LR) neural network were used. The model performance was compared using different indicators, including the root mean square error (RMSE), relative root mean square error (RRMSE), mean absolute percentage error (MAPE), mean square error (MSE), correlation coefficient (R2) and relative error (RE). Three kinetic models were applied to the experimental and predicted data; the pseudo second-order model was the best at describing the data. The maximum RE, R2 and MSE were 9.79{\%}, 0.9701 and 1.15 × 10−3, respectively, for the NARX model; 15.02{\%}, 0.9304 and 2.2 × 10−3 for the LR model; and 16.4{\%}, 0.9313 and 2.27 × 10−3 for the FFNN model. The NARX model accurately predicted the adsorption capacity with better performance than the FFNN and LR models.",
author = "Fiyadh, {Seef Saadi} and Alomar, {Mohamed Khalid} and Jaafar, {Wan Zurina Binti} and Alsaadi, {Mohammed Abdulhakim} and Fayaed, {Sabah Saadi} and Koting, {Suhana Binti} and Lai, {Sai Hin} and Chow, {Ming Fai} and Ahmed, {Ali Najah} and Ahmed El-Shafie",
year = "2019",
month = "9",
day = "1",
doi = "10.3390/ijms20174206",
language = "English",
volume = "20",
journal = "International Journal of Molecular Sciences",
issn = "1661-6596",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "17",

}

Artificial neural network approach for modelling of mercury ions removal from water using functionalized CNTs with deep eutectic solvent. / Fiyadh, Seef Saadi; Alomar, Mohamed Khalid; Jaafar, Wan Zurina Binti; Alsaadi, Mohammed Abdulhakim; Fayaed, Sabah Saadi; Koting, Suhana Binti; Lai, Sai Hin; Chow, Ming Fai; Ahmed, Ali Najah; El-Shafie, Ahmed.

In: International journal of molecular sciences, Vol. 20, No. 17, 4206, 01.09.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Artificial neural network approach for modelling of mercury ions removal from water using functionalized CNTs with deep eutectic solvent

AU - Fiyadh, Seef Saadi

AU - Alomar, Mohamed Khalid

AU - Jaafar, Wan Zurina Binti

AU - Alsaadi, Mohammed Abdulhakim

AU - Fayaed, Sabah Saadi

AU - Koting, Suhana Binti

AU - Lai, Sai Hin

AU - Chow, Ming Fai

AU - Ahmed, Ali Najah

AU - El-Shafie, Ahmed

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Multi-walled carbon nanotubes (CNTs) functionalized with a deep eutectic solvent (DES) were utilized to remove mercury ions from water. An artificial neural network (ANN) technique was used for modelling the functionalized CNTs adsorption capacity. The amount of adsorbent dosage, contact time, mercury ions concentration and pH were varied, and the effect of parameters on the functionalized CNT adsorption capacity is observed. The (NARX) network, (FFNN) network and layer recurrent (LR) neural network were used. The model performance was compared using different indicators, including the root mean square error (RMSE), relative root mean square error (RRMSE), mean absolute percentage error (MAPE), mean square error (MSE), correlation coefficient (R2) and relative error (RE). Three kinetic models were applied to the experimental and predicted data; the pseudo second-order model was the best at describing the data. The maximum RE, R2 and MSE were 9.79%, 0.9701 and 1.15 × 10−3, respectively, for the NARX model; 15.02%, 0.9304 and 2.2 × 10−3 for the LR model; and 16.4%, 0.9313 and 2.27 × 10−3 for the FFNN model. The NARX model accurately predicted the adsorption capacity with better performance than the FFNN and LR models.

AB - Multi-walled carbon nanotubes (CNTs) functionalized with a deep eutectic solvent (DES) were utilized to remove mercury ions from water. An artificial neural network (ANN) technique was used for modelling the functionalized CNTs adsorption capacity. The amount of adsorbent dosage, contact time, mercury ions concentration and pH were varied, and the effect of parameters on the functionalized CNT adsorption capacity is observed. The (NARX) network, (FFNN) network and layer recurrent (LR) neural network were used. The model performance was compared using different indicators, including the root mean square error (RMSE), relative root mean square error (RRMSE), mean absolute percentage error (MAPE), mean square error (MSE), correlation coefficient (R2) and relative error (RE). Three kinetic models were applied to the experimental and predicted data; the pseudo second-order model was the best at describing the data. The maximum RE, R2 and MSE were 9.79%, 0.9701 and 1.15 × 10−3, respectively, for the NARX model; 15.02%, 0.9304 and 2.2 × 10−3 for the LR model; and 16.4%, 0.9313 and 2.27 × 10−3 for the FFNN model. The NARX model accurately predicted the adsorption capacity with better performance than the FFNN and LR models.

UR - http://www.scopus.com/inward/record.url?scp=85071762876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071762876&partnerID=8YFLogxK

U2 - 10.3390/ijms20174206

DO - 10.3390/ijms20174206

M3 - Article

C2 - 31466219

AN - SCOPUS:85071762876

VL - 20

JO - International Journal of Molecular Sciences

JF - International Journal of Molecular Sciences

SN - 1661-6596

IS - 17

M1 - 4206

ER -