Humic substance coagulation: Artificial neural network simulation

Mohammed Al-Abri, Khalid Al Anezi, Akram Dakheel, Nidal Hilal

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

This paper investigates the use of backpropagation neural network (BPNN) to predict humic substance (HS) UV absorbance experimental results. The studied experimental sets include HS and heavy metal agglomeration, HS coagulation using polyelectrolytes and HS and heavy metal coagulation using polyelectrolytes. BPNN simulation showed high prediction accuracy where regression coefficient (R) was > 0.95 for all simulations. Lower and higher than optimum training data input reduces BPNN reliability due to under training or over-fitting. The number of neurons study showed that a lower number of neurons led to under training, while a higher number of neurons resulted in the network memorizing the input dataset.

Original languageEnglish
Pages (from-to)153-157
Number of pages5
JournalDesalination
Volume253
Issue number1-3
DOIs
Publication statusPublished - Apr 2010

Fingerprint

Humic Substances
humic substance
Coagulation
coagulation
artificial neural network
Backpropagation
Neurons
Neural networks
Heavy Metals
Polyelectrolytes
Heavy metals
simulation
heavy metal
agglomeration
absorbance
Agglomeration
prediction

Keywords

  • ANN
  • Humic acid
  • Polymer coagulation
  • Prediction

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Mechanical Engineering
  • Chemistry(all)
  • Materials Science(all)
  • Water Science and Technology

Cite this

Humic substance coagulation : Artificial neural network simulation. / Al-Abri, Mohammed; Al Anezi, Khalid; Dakheel, Akram; Hilal, Nidal.

In: Desalination, Vol. 253, No. 1-3, 04.2010, p. 153-157.

Research output: Contribution to journalArticle

Al-Abri, Mohammed ; Al Anezi, Khalid ; Dakheel, Akram ; Hilal, Nidal. / Humic substance coagulation : Artificial neural network simulation. In: Desalination. 2010 ; Vol. 253, No. 1-3. pp. 153-157.
@article{0364f5c564aa4f41922e9124cfabdb6c,
title = "Humic substance coagulation: Artificial neural network simulation",
abstract = "This paper investigates the use of backpropagation neural network (BPNN) to predict humic substance (HS) UV absorbance experimental results. The studied experimental sets include HS and heavy metal agglomeration, HS coagulation using polyelectrolytes and HS and heavy metal coagulation using polyelectrolytes. BPNN simulation showed high prediction accuracy where regression coefficient (R) was > 0.95 for all simulations. Lower and higher than optimum training data input reduces BPNN reliability due to under training or over-fitting. The number of neurons study showed that a lower number of neurons led to under training, while a higher number of neurons resulted in the network memorizing the input dataset.",
keywords = "ANN, Humic acid, Polymer coagulation, Prediction",
author = "Mohammed Al-Abri and {Al Anezi}, Khalid and Akram Dakheel and Nidal Hilal",
year = "2010",
month = "4",
doi = "10.1016/j.desal.2009.11.014",
language = "English",
volume = "253",
pages = "153--157",
journal = "Desalination",
issn = "0011-9164",
publisher = "Elsevier",
number = "1-3",

}

TY - JOUR

T1 - Humic substance coagulation

T2 - Artificial neural network simulation

AU - Al-Abri, Mohammed

AU - Al Anezi, Khalid

AU - Dakheel, Akram

AU - Hilal, Nidal

PY - 2010/4

Y1 - 2010/4

N2 - This paper investigates the use of backpropagation neural network (BPNN) to predict humic substance (HS) UV absorbance experimental results. The studied experimental sets include HS and heavy metal agglomeration, HS coagulation using polyelectrolytes and HS and heavy metal coagulation using polyelectrolytes. BPNN simulation showed high prediction accuracy where regression coefficient (R) was > 0.95 for all simulations. Lower and higher than optimum training data input reduces BPNN reliability due to under training or over-fitting. The number of neurons study showed that a lower number of neurons led to under training, while a higher number of neurons resulted in the network memorizing the input dataset.

AB - This paper investigates the use of backpropagation neural network (BPNN) to predict humic substance (HS) UV absorbance experimental results. The studied experimental sets include HS and heavy metal agglomeration, HS coagulation using polyelectrolytes and HS and heavy metal coagulation using polyelectrolytes. BPNN simulation showed high prediction accuracy where regression coefficient (R) was > 0.95 for all simulations. Lower and higher than optimum training data input reduces BPNN reliability due to under training or over-fitting. The number of neurons study showed that a lower number of neurons led to under training, while a higher number of neurons resulted in the network memorizing the input dataset.

KW - ANN

KW - Humic acid

KW - Polymer coagulation

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=76049092125&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76049092125&partnerID=8YFLogxK

U2 - 10.1016/j.desal.2009.11.014

DO - 10.1016/j.desal.2009.11.014

M3 - Article

AN - SCOPUS:76049092125

VL - 253

SP - 153

EP - 157

JO - Desalination

JF - Desalination

SN - 0011-9164

IS - 1-3

ER -