Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations
Authorized Users Only
2015
Authors
Siljić, AleksandraAntanasijević, Davor

Perić-Grujić, Aleksandra

Ristić, Mirjana

Pocajt, Viktor

Article (Published version)

Metadata
Show full item recordAbstract
Biological oxygen demand (BOD) is the most significant water quality parameter and indicates water pollution with respect to the present biodegradable organic matter content. European countries are therefore obliged to report annual BOD values to Eurostat; however, BOD data at the national level is only available for 28 of 35 listed European countries for the period prior to 2008, among which 46 % of data is missing. This paper describes the development of an artificial neural network model for the forecasting of annual BOD values at the national level, using widely available sustainability and economical/industrial parameters as inputs. The initial general regression neural network (GRNN) model was trained, validated and tested utilizing 20 inputs. The number of inputs was reduced to 15 using the Monte Carlo simulation technique as the input selection method. The best results were achieved with the GRNN model utilizing 25 % less inputs than the initial model and a comparison with a mu...ltiple linear regression model trained and tested using the same input variables using multiple statistical performance indicators confirmed the advantage of the GRNN model. Sensitivity analysis has shown that inputs with the greatest effect on the GRNN model were (in descending order) precipitation, rural population with access to improved water sources, treatment capacity of wastewater treatment plants (urban) and treatment of municipal waste, with the last two having an equal effect. Finally, it was concluded that the developed GRNN model can be useful as a tool to support the decision-making process on sustainable development at a regional, national and international level.
Keywords:
GRNN / BOD / River water / MCS / MLR / SustainabilitySource:
Environmental Science and Pollution Research, 2015, 22, 6, 4230-4241Publisher:
- Springer Heidelberg, Heidelberg
Funding / projects:
DOI: 10.1007/s11356-014-3669-y
ISSN: 0944-1344
PubMed: 25280507
WoS: 000350572500019
Scopus: 2-s2.0-84925516159
Institution/Community
Tehnološko-metalurški fakultetTY - JOUR AU - Siljić, Aleksandra AU - Antanasijević, Davor AU - Perić-Grujić, Aleksandra AU - Ristić, Mirjana AU - Pocajt, Viktor PY - 2015 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3033 AB - Biological oxygen demand (BOD) is the most significant water quality parameter and indicates water pollution with respect to the present biodegradable organic matter content. European countries are therefore obliged to report annual BOD values to Eurostat; however, BOD data at the national level is only available for 28 of 35 listed European countries for the period prior to 2008, among which 46 % of data is missing. This paper describes the development of an artificial neural network model for the forecasting of annual BOD values at the national level, using widely available sustainability and economical/industrial parameters as inputs. The initial general regression neural network (GRNN) model was trained, validated and tested utilizing 20 inputs. The number of inputs was reduced to 15 using the Monte Carlo simulation technique as the input selection method. The best results were achieved with the GRNN model utilizing 25 % less inputs than the initial model and a comparison with a multiple linear regression model trained and tested using the same input variables using multiple statistical performance indicators confirmed the advantage of the GRNN model. Sensitivity analysis has shown that inputs with the greatest effect on the GRNN model were (in descending order) precipitation, rural population with access to improved water sources, treatment capacity of wastewater treatment plants (urban) and treatment of municipal waste, with the last two having an equal effect. Finally, it was concluded that the developed GRNN model can be useful as a tool to support the decision-making process on sustainable development at a regional, national and international level. PB - Springer Heidelberg, Heidelberg T2 - Environmental Science and Pollution Research T1 - Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations EP - 4241 IS - 6 SP - 4230 VL - 22 DO - 10.1007/s11356-014-3669-y ER -
@article{ author = "Siljić, Aleksandra and Antanasijević, Davor and Perić-Grujić, Aleksandra and Ristić, Mirjana and Pocajt, Viktor", year = "2015", abstract = "Biological oxygen demand (BOD) is the most significant water quality parameter and indicates water pollution with respect to the present biodegradable organic matter content. European countries are therefore obliged to report annual BOD values to Eurostat; however, BOD data at the national level is only available for 28 of 35 listed European countries for the period prior to 2008, among which 46 % of data is missing. This paper describes the development of an artificial neural network model for the forecasting of annual BOD values at the national level, using widely available sustainability and economical/industrial parameters as inputs. The initial general regression neural network (GRNN) model was trained, validated and tested utilizing 20 inputs. The number of inputs was reduced to 15 using the Monte Carlo simulation technique as the input selection method. The best results were achieved with the GRNN model utilizing 25 % less inputs than the initial model and a comparison with a multiple linear regression model trained and tested using the same input variables using multiple statistical performance indicators confirmed the advantage of the GRNN model. Sensitivity analysis has shown that inputs with the greatest effect on the GRNN model were (in descending order) precipitation, rural population with access to improved water sources, treatment capacity of wastewater treatment plants (urban) and treatment of municipal waste, with the last two having an equal effect. Finally, it was concluded that the developed GRNN model can be useful as a tool to support the decision-making process on sustainable development at a regional, national and international level.", publisher = "Springer Heidelberg, Heidelberg", journal = "Environmental Science and Pollution Research", title = "Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations", pages = "4241-4230", number = "6", volume = "22", doi = "10.1007/s11356-014-3669-y" }
Siljić, A., Antanasijević, D., Perić-Grujić, A., Ristić, M.,& Pocajt, V.. (2015). Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations. in Environmental Science and Pollution Research Springer Heidelberg, Heidelberg., 22(6), 4230-4241. https://doi.org/10.1007/s11356-014-3669-y
Siljić A, Antanasijević D, Perić-Grujić A, Ristić M, Pocajt V. Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations. in Environmental Science and Pollution Research. 2015;22(6):4230-4241. doi:10.1007/s11356-014-3669-y .
Siljić, Aleksandra, Antanasijević, Davor, Perić-Grujić, Aleksandra, Ristić, Mirjana, Pocajt, Viktor, "Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations" in Environmental Science and Pollution Research, 22, no. 6 (2015):4230-4241, https://doi.org/10.1007/s11356-014-3669-y . .