Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction
Само за регистроване кориснике
2018
Аутори
Šiljić-Tomić, AleksandraAntanasijević, Davor
Ristić, Mirjana
Perić-Grujić, Aleksandra
Pocajt, Viktor
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
This paper presents an application of experimental design for the optimization of artificial neural network (ANN) for the prediction of dissolved oxygen (DO) content in the Danube River. The aim of this research was to obtain a more reliable ANN model that uses fewer monitoring records, by simultaneous optimization of the following model parameters: number of monitoring sites, number of historical monitoring data (expressed in years), and number of input water quality parameters used. Box-Behnken three-factor at three levels experimental design was applied for simultaneous spatial, temporal, and input variables optimization of the ANN model. The prediction of DO was performed using a feed-forward back-propagation neural network (BPNN), while the selection of most important inputs was done off-model using multi-filter approach that combines a chi-square ranking in the first step with a correlation-based elimination in the second step. The contour plots of absolute and relative error res...ponse surfaces were utilized to determine the optimal values of design factors. From the contour plots, two BPNN models that cover entire Danube flow through Serbia are proposed: an upstream model (BPNN-UP) that covers 8 monitoring sites prior to Belgrade and uses 12 inputs measured in the 7-year period and a downstream model (BPNN-DOWN) which covers 9 monitoring sites and uses 11 input parameters measured in the 6-year period. The main difference between the two models is that BPNN-UP utilizes inputs such as BOD, P, and PO43-, which is in accordance with the fact that this model covers northern part of Serbia (Vojvodina Autonomous Province) which is well-known for agricultural production and extensive use of fertilizers. Both models have shown very good agreement between measured and predicted DO (with R-2 gt = 0.86) and demonstrated that they can effectively forecast DO content in the Danube River.
Кључне речи:
Dissolved oxygen / Modeling / ANN / Design of experiment / Parameter selectionИзвор:
Environmental Science and Pollution Research, 2018, 25, 10, 9360-9370Издавач:
- Springer Heidelberg, Heidelberg
Финансирање / пројекти:
- Развој и примена метода и материјала за мониторинг нових загађујућих и токсичних органских материја и тешких метала (RS-MESTD-Basic Research (BR or ON)-172007)
DOI: 10.1007/s11356-018-1246-5
ISSN: 0944-1344
PubMed: 29349736
WoS: 000429561900018
Scopus: 2-s2.0-85040763382
Институција/група
Tehnološko-metalurški fakultetTY - JOUR AU - Šiljić-Tomić, Aleksandra AU - Antanasijević, Davor AU - Ristić, Mirjana AU - Perić-Grujić, Aleksandra AU - Pocajt, Viktor PY - 2018 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4028 AB - This paper presents an application of experimental design for the optimization of artificial neural network (ANN) for the prediction of dissolved oxygen (DO) content in the Danube River. The aim of this research was to obtain a more reliable ANN model that uses fewer monitoring records, by simultaneous optimization of the following model parameters: number of monitoring sites, number of historical monitoring data (expressed in years), and number of input water quality parameters used. Box-Behnken three-factor at three levels experimental design was applied for simultaneous spatial, temporal, and input variables optimization of the ANN model. The prediction of DO was performed using a feed-forward back-propagation neural network (BPNN), while the selection of most important inputs was done off-model using multi-filter approach that combines a chi-square ranking in the first step with a correlation-based elimination in the second step. The contour plots of absolute and relative error response surfaces were utilized to determine the optimal values of design factors. From the contour plots, two BPNN models that cover entire Danube flow through Serbia are proposed: an upstream model (BPNN-UP) that covers 8 monitoring sites prior to Belgrade and uses 12 inputs measured in the 7-year period and a downstream model (BPNN-DOWN) which covers 9 monitoring sites and uses 11 input parameters measured in the 6-year period. The main difference between the two models is that BPNN-UP utilizes inputs such as BOD, P, and PO43-, which is in accordance with the fact that this model covers northern part of Serbia (Vojvodina Autonomous Province) which is well-known for agricultural production and extensive use of fertilizers. Both models have shown very good agreement between measured and predicted DO (with R-2 gt = 0.86) and demonstrated that they can effectively forecast DO content in the Danube River. PB - Springer Heidelberg, Heidelberg T2 - Environmental Science and Pollution Research T1 - Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction EP - 9370 IS - 10 SP - 9360 VL - 25 DO - 10.1007/s11356-018-1246-5 ER -
@article{ author = "Šiljić-Tomić, Aleksandra and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor", year = "2018", abstract = "This paper presents an application of experimental design for the optimization of artificial neural network (ANN) for the prediction of dissolved oxygen (DO) content in the Danube River. The aim of this research was to obtain a more reliable ANN model that uses fewer monitoring records, by simultaneous optimization of the following model parameters: number of monitoring sites, number of historical monitoring data (expressed in years), and number of input water quality parameters used. Box-Behnken three-factor at three levels experimental design was applied for simultaneous spatial, temporal, and input variables optimization of the ANN model. The prediction of DO was performed using a feed-forward back-propagation neural network (BPNN), while the selection of most important inputs was done off-model using multi-filter approach that combines a chi-square ranking in the first step with a correlation-based elimination in the second step. The contour plots of absolute and relative error response surfaces were utilized to determine the optimal values of design factors. From the contour plots, two BPNN models that cover entire Danube flow through Serbia are proposed: an upstream model (BPNN-UP) that covers 8 monitoring sites prior to Belgrade and uses 12 inputs measured in the 7-year period and a downstream model (BPNN-DOWN) which covers 9 monitoring sites and uses 11 input parameters measured in the 6-year period. The main difference between the two models is that BPNN-UP utilizes inputs such as BOD, P, and PO43-, which is in accordance with the fact that this model covers northern part of Serbia (Vojvodina Autonomous Province) which is well-known for agricultural production and extensive use of fertilizers. Both models have shown very good agreement between measured and predicted DO (with R-2 gt = 0.86) and demonstrated that they can effectively forecast DO content in the Danube River.", publisher = "Springer Heidelberg, Heidelberg", journal = "Environmental Science and Pollution Research", title = "Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction", pages = "9370-9360", number = "10", volume = "25", doi = "10.1007/s11356-018-1246-5" }
Šiljić-Tomić, A., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2018). Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction. in Environmental Science and Pollution Research Springer Heidelberg, Heidelberg., 25(10), 9360-9370. https://doi.org/10.1007/s11356-018-1246-5
Šiljić-Tomić A, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction. in Environmental Science and Pollution Research. 2018;25(10):9360-9370. doi:10.1007/s11356-018-1246-5 .
Šiljić-Tomić, Aleksandra, Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction" in Environmental Science and Pollution Research, 25, no. 10 (2018):9360-9370, https://doi.org/10.1007/s11356-018-1246-5 . .