TechnoRep - Faculty of Technology and Metallurgy Repository
University of Belgrade - Faculty of Technology and Metallurgy
    • English
    • Српски
    • Српски (Serbia)
  • English 
    • English
    • Serbian (Cyrillic)
    • Serbian (Latin)
  • Login
View Item 
  •   TechnoRep
  • Tehnološko-metalurški fakultet
  • Radovi istraživača / Researchers’ publications (TMF)
  • View Item
  •   TechnoRep
  • Tehnološko-metalurški fakultet
  • Radovi istraživača / Researchers’ publications (TMF)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study

Authorized Users Only
2013
Authors
Antanasijević, Davor
Pocajt, Viktor
Povrenović, Dragan
Perić-Grujić, Aleksandra
Ristić, Mirjana
Article (Published version)
Metadata
Show full item record
Abstract
The aims of this study are to create an artificial neural network (ANN) model using non-specific water quality parameters and to examine the accuracy of three different ANN architectures: General Regression Neural Network (GRNN), Backpropagation Neural Network (BPNN) and Recurrent Neural Network (RNN), for prediction of dissolved oxygen (DO) concentration in the Danube River. The neural network model has been developed using measured data collected from the Bezdan monitoring station on the Danube River. The input variables used for the ANN model are water flow, temperature, pH and electrical conductivity. The model was trained and validated using available data from 2004 to 2008 and tested using the data from 2009. The order of performance for the created architectures based on their comparison with the test data is RNN gt GRNN gt BPNN. The ANN results are compared with multiple linear regression (MLR) model using multiple statistical indicators. The comparison of the RNN model wit...h the MLR model indicates that the RNN model performs much better, since all predictions of the RNN model for the test data were within the error of less than +/- 10 %. In case of the MLR, only 55 % of predictions were within the error of less than +/- 10 %. The developed RNN model can be used as a tool for the prediction of DO in river waters.

Keywords:
Modelling of dissolved oxygen / Modelling of water quality / Artificial neural network / Multiple linear regression
Source:
Environmental Science and Pollution Research, 2013, 20, 12, 9006-9013
Publisher:
  • Springer Heidelberg, Heidelberg
Funding / projects:
  • Development and Application of Methods and Materials for Monitoring New Organic Contaminants, Toxic Compounds and Heavy Metals (RS-172007)

DOI: 10.1007/s11356-013-1876-6

ISSN: 0944-1344

PubMed: 23764983

WoS: 000327498600068

Scopus: 2-s2.0-84891145294
[ Google Scholar ]
63
48
URI
http://TechnoRep.tmf.bg.ac.rs/handle/123456789/2434
Collections
  • Radovi istraživača / Researchers’ publications (TMF)
Institution/Community
Tehnološko-metalurški fakultet
TY  - JOUR
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Povrenović, Dragan
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, Mirjana
PY  - 2013
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/2434
AB  - The aims of this study are to create an artificial neural network (ANN) model using non-specific water quality parameters and to examine the accuracy of three different ANN architectures: General Regression Neural Network (GRNN), Backpropagation Neural Network (BPNN) and Recurrent Neural Network (RNN), for prediction of dissolved oxygen (DO) concentration in the Danube River. The neural network model has been developed using measured data collected from the Bezdan monitoring station on the Danube River. The input variables used for the ANN model are water flow, temperature, pH and electrical conductivity. The model was trained and validated using available data from 2004 to 2008 and tested using the data from 2009. The order of performance for the created architectures based on their comparison with the test data is RNN  gt  GRNN  gt  BPNN. The ANN results are compared with multiple linear regression (MLR) model using multiple statistical indicators. The comparison of the RNN model with the MLR model indicates that the RNN model performs much better, since all predictions of the RNN model for the test data were within the error of less than +/- 10 %. In case of the MLR, only 55 % of predictions were within the error of less than +/- 10 %. The developed RNN model can be used as a tool for the prediction of DO in river waters.
PB  - Springer Heidelberg, Heidelberg
T2  - Environmental Science and Pollution Research
T1  - Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study
EP  - 9013
IS  - 12
SP  - 9006
VL  - 20
DO  - 10.1007/s11356-013-1876-6
ER  - 
@article{
author = "Antanasijević, Davor and Pocajt, Viktor and Povrenović, Dragan and Perić-Grujić, Aleksandra and Ristić, Mirjana",
year = "2013",
abstract = "The aims of this study are to create an artificial neural network (ANN) model using non-specific water quality parameters and to examine the accuracy of three different ANN architectures: General Regression Neural Network (GRNN), Backpropagation Neural Network (BPNN) and Recurrent Neural Network (RNN), for prediction of dissolved oxygen (DO) concentration in the Danube River. The neural network model has been developed using measured data collected from the Bezdan monitoring station on the Danube River. The input variables used for the ANN model are water flow, temperature, pH and electrical conductivity. The model was trained and validated using available data from 2004 to 2008 and tested using the data from 2009. The order of performance for the created architectures based on their comparison with the test data is RNN  gt  GRNN  gt  BPNN. The ANN results are compared with multiple linear regression (MLR) model using multiple statistical indicators. The comparison of the RNN model with the MLR model indicates that the RNN model performs much better, since all predictions of the RNN model for the test data were within the error of less than +/- 10 %. In case of the MLR, only 55 % of predictions were within the error of less than +/- 10 %. The developed RNN model can be used as a tool for the prediction of DO in river waters.",
publisher = "Springer Heidelberg, Heidelberg",
journal = "Environmental Science and Pollution Research",
title = "Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study",
pages = "9013-9006",
number = "12",
volume = "20",
doi = "10.1007/s11356-013-1876-6"
}
Antanasijević, D., Pocajt, V., Povrenović, D., Perić-Grujić, A.,& Ristić, M.. (2013). Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study. in Environmental Science and Pollution Research
Springer Heidelberg, Heidelberg., 20(12), 9006-9013.
https://doi.org/10.1007/s11356-013-1876-6
Antanasijević D, Pocajt V, Povrenović D, Perić-Grujić A, Ristić M. Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study. in Environmental Science and Pollution Research. 2013;20(12):9006-9013.
doi:10.1007/s11356-013-1876-6 .
Antanasijević, Davor, Pocajt, Viktor, Povrenović, Dragan, Perić-Grujić, Aleksandra, Ristić, Mirjana, "Modelling of dissolved oxygen content using artificial neural networks: Danube River, North Serbia, case study" in Environmental Science and Pollution Research, 20, no. 12 (2013):9006-9013,
https://doi.org/10.1007/s11356-013-1876-6 . .

DSpace software copyright © 2002-2015  DuraSpace
About TechnoRep | Send Feedback

OpenAIRERCUB
 

 

All of DSpaceInstitutions/communitiesAuthorsTitlesSubjectsThis institutionAuthorsTitlesSubjects

Statistics

View Usage Statistics

DSpace software copyright © 2002-2015  DuraSpace
About TechnoRep | Send Feedback

OpenAIRERCUB