TY - JOUR
T1 - A probabilistic water quality index for river water quality assessment
T2 - A case study
AU - Nikoo, Mohammad Reza
AU - Kerachian, Reza
AU - Malakpour-Estalaki, Siamak
AU - Bashi-Azghadi, Seyyed Nasser
AU - Azimi-Ghadikolaee, Mohammad Mahdi
N1 - Funding Information:
Acknowledgements This study was financially supported by the Tehran Regional Water Company (TRWC) under grant no. 4-73-89. Technical contributions of Dr. Eslamizadeh, Mr. Yamini, and Ms. Darvishi, managers and experts of TRWC, are hereby acknowledged.
PY - 2011/10
Y1 - 2011/10
N2 - Available water quality indices have some limitations such as incorporating a limited number of water quality variables and providing deterministic outputs. This paper presents a hybrid probabilistic water quality index by utilizing fuzzy inference systems (FIS), Bayesian networks (BNs), and probabilistic neural networks (PNNs). The outputs of two traditional water quality indices, namely the indices proposed by the National Sanitation Foundation and the Canadian Council of Ministers of the Environment, are selected as inputs of the FIS. The FIS is trained based on the opinions of several water quality experts. Then the trained FIS is used in a Monte Carlo analysis to provide the required input-output data for training both the BN and PNN. The trained BN and PNN can be used for probabilistic water quality assessment using water quality monitoring data. The efficiency and applicability of the proposed methodology is evaluated using water quality data obtained from water quality monitoring system of the Jajrood River in Iran.
AB - Available water quality indices have some limitations such as incorporating a limited number of water quality variables and providing deterministic outputs. This paper presents a hybrid probabilistic water quality index by utilizing fuzzy inference systems (FIS), Bayesian networks (BNs), and probabilistic neural networks (PNNs). The outputs of two traditional water quality indices, namely the indices proposed by the National Sanitation Foundation and the Canadian Council of Ministers of the Environment, are selected as inputs of the FIS. The FIS is trained based on the opinions of several water quality experts. Then the trained FIS is used in a Monte Carlo analysis to provide the required input-output data for training both the BN and PNN. The trained BN and PNN can be used for probabilistic water quality assessment using water quality monitoring data. The efficiency and applicability of the proposed methodology is evaluated using water quality data obtained from water quality monitoring system of the Jajrood River in Iran.
KW - Bayesian networks (BNs)
KW - Fuzzy inference system (FIS)
KW - Probabilistic neural networks (PNNs)
KW - Water quality index (WQI)
KW - Water quality zoning
UR - http://www.scopus.com/inward/record.url?scp=80054760989&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80054760989&partnerID=8YFLogxK
U2 - 10.1007/s10661-010-1842-4
DO - 10.1007/s10661-010-1842-4
M3 - Article
C2 - 21188505
AN - SCOPUS:80054760989
SN - 0167-6369
VL - 181
SP - 465
EP - 478
JO - Environmental Monitoring and Assessment
JF - Environmental Monitoring and Assessment
IS - 1-4
ER -