Parameter Sensitivity Analysis of Artificial Neural Network for Predicting Water Turbidity

The present study focuses on the discussion over the parameter of Artificial Neural Network (ANN). Sensitivity analysis is applied to assess the effect of the parameters of ANN on the prediction of turbidity of raw water in the water treatment plant. The result shows that transfer function of hidden layer is a critical parameter of ANN. When the transfer function changes, the reliability of prediction of water turbidity is greatly different. Moreover, the estimated water turbidity is less sensitive to training times and learning velocity than the number of neurons in the hidden layer. Therefore, it is important to select an appropriate transfer function and suitable number of neurons in the hidden layer in the process of parameter training and validation.

Authors:

• Chia-Ling Chang
• Chung-Sheng Liao

Keywords:

• Artificial Neural Network (ANN)
• sensitivity analysis
• turbidity.

References:

[1] ASCE Task Committee on Application of The Artificial Neural Networks
in Hydrology (2000a). Artificial neural networks in hydrology I:
preliminary concepts. Journal of Hydrologic Engineering, 5(2), 115-123.
[2] ASCE Task Committee on Application of The Artificial Neural Networks
in Hydrology (2000b). Artificial neural networks in hydrology II:
hydrologic applications. Journal of Hydrologic Engineering, 5 (2),
124-137.
[3] Chang, C.L., Lo, S.L., Hu, C.Y., Wang, L.H. and Ma, C.L. (2010).
Relationship between turbidity in the Linnei water treatment plant and its
upstream hydrologic environment. 2009 Water Resource Management
Conference, Taipei, Taiwan. (in Chinese)
[4] Rajurkar, M.P., Kothyari, U.C., Chaube, U.C. (2004). Modeling of the
daily rainfall-runoff relationship with artificial neural network. Journal of
Hydrology, 285, 96-113.
[5] McCulloch, W.S. and Pitts, W. (1943). A logical calculus of the ideas
imminent in nervous activity. Bulletin and Mathematical Biophysics, 5,
115-133.
[6] Maier, H.R. and Dandy, G.C. (2000). Neural networks for the prediction
and forecasting of water resources variables: a review of modelling issues
and applications. Environmental Modelling and Software, 15, 101-124.
[7] Karul, C., Soyupak, S., Cilesiz, A.F., Akbay, N. and Germen, E. (2000).
Case studies on the use of neural networks in eutrophication modeling.
Ecological Modelling, 134, 145-152.
[8] Tokar, A.S. and Markus, M. (2000). Precipitation runoff modeling using
artificial neural networks and conceptual models. Journal of Hydrologic
Engineering, ASCE, 5(2), 156-161.
[9] Lee, T.L. and Jeng, D.S. (2002). Application of artificial neural networks
in tide forecasting. Ocean Engineering, 29, 1003-1022.
[10] Rajurkar, M.P., Kothyari, U.C. and Chaube, U.C. (2002). Artificial neural
network for daily rainfall-runoff modeling. Hydrological Sciences
Journal, 47(6), 865-877.
[11] Philip, N.S and Joseph, K.B. (2003). A neural network tool for
analyzingtrends in rainfall. Computers & Geosciences, 29, 215-223.
[12] Palani, S., Liong, S.Y., Tkalich, P. (2008). An ANN application for water
quality forecasting. Marine Pollution Bulletin, 56, 1586-1597.
[13] Lee, T.L. (2009). Predictions of typhoon storm surge in Taiwan using
artificial neural networks. Advances in Engineering Software, 40,
1200-1206.
[14] Caudill, M. and Butler, C. (1992). Understanding neural networks. Basic
Networks, 1, MIT Press, Cambridge, MA.
[15] Schladow, S.G. and Hamilton, D.P. (1997). Prediction of water quality in
lakes and reservoirs: Part ÔàíÔÇöModel calibration, sensitivity analysis and
application. Ecological Modelling, 96, 111-123.
[16] Al-Abed, N.A. and Whiteley, H.R. (2002). Calibration of the
hydrological simulation program fortran (HSPF) model using automatic
calibration and geographical information systems. Hydrological
Processes, 16, 3169-3188.
[17] Chung, E.S. and Lee, K.S. (2009). Prioritization of water management for
sustainability using hydrologic simulation model and multicriteria
decision making techniques. Journal of Environmental Management, 90,
1502-1511.
[18] Calver, A. (1988). Calibration, sensitivity and validation of a
physically-based rainfall-runoff model. Journal of Hydrology, 103,
103-115.
[19] Walker, S. (1996). Modelling nitrate in Tile-Drained Watersheds of
East-Central Illinois. Ph.D. Thesis, University of Illinois at
Urbana-Champain.
[20] Jacomino, V.M.F. and Fields, D.E. (1997). A critical approach to the
calibration of a watershed model. Journal of the American Water
Resources Association, 33(1), 143-154.
[21] Chang, C.L, Lo, S.L. and Hu, C.Y. (2007). An analysis of required
parameters in WinVAST model for runoff simulation. Advances in Asian
Environmental Engineering, 6(1), 7-12.