Evaluation of MLP-ANN Training Algorithms for Modeling Soil Pore-Water Pressure Responses to Rainfall
This article has a reply.
VIEW THE REPLYThis article has a reply.
VIEW THE REPLYPublication: Journal of Hydrologic Engineering
Volume 18, Issue 1
Abstract
Knowledge of pore-water pressure responses to rainfall is vital in slope failure and slope hydrological studies. The performance of four artificial neural network (ANN) training algorithms was evaluated to identify the training algorithm appropriate for modeling the dynamics of soil pore-water pressure responses to rainfall patterns using multilayer perceptron (MLP) ANN. The ANN model comprised eight neurons in the input layer, four neurons in the hidden layer, and a single neuron in the output layer representing an ANN architecture. The training algorithms evaluated include the gradient descent, gradient descent with momentum, scaled conjugate gradient, and Levenberg-Marquardt (LM). The performance of the training algorithms was evaluated using standard performance evaluation measures—root mean square error, coefficient of efficiency, and the time and number of epochs required to reach a predefined accuracy. It was found that all the training algorithms could be used in the prediction of pore-water pressures. However, the LM algorithm required the least time and epochs for training the network and gave the minimum error during both training and testing. The LM training algorithm is therefore proposed as an ideal and fast training algorithm for modeling the dynamics of soil pore-water pressure changes in response to rainfall patterns.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
The first author gratefully acknowledges the financial support provided by Universiti Teknologi PETRONAS as part of a Ph.D. scholarship.
References
Caudill, M. (1987). “Neural networks primer, part I.” AI Expert, 2(12), 46–52.
Cestisli, B., and Barkana, A. (2010). “Speeding up the scaled conjugate gradient algorithm and its application in neuro-fuzzy classifier training.” Soft Comput., 14(4), 365–378.
Chiang, Y. M., Chang, L. C., and Chang, F. J. (2004). “Comparison of static-feedforward and dynamic-feedback neural networks for rainfall-runoff modeling.” J. Hydrol., 290(3–4), 297–311.
Cigizoglu, H. K. (2005). “Application of the generalized regression neural networks to intermittent flow forecasting and estimation.” J. Hydrol. Eng., 10(4), 336–341.
Demirel, M. C., Anabela, V., and Kahya, E. (2009). “Flow forecast by SWAT model and ANN in Pracana Basin, Portugal.” Adv. Eng. Softw., 40(7), 467–473.
Fernando, D. A. K., and Shamseldin, A. (2009). “Investigation of internal functioning of the radial basis function neural network river flow forecasting models.” J. Hydrol. Eng., 14(3), 286–292.
Fernando, D. A. K., Zhang, X., and Kinley, P. F. (2005). “Combined sewer overflow forecasting with feed-forward back-propagation artificial neural network.” Int. J. Appl. Sci. Eng. Technol.-1, 4, 212–217.
Hagan, M. T., and Menhaj, M. B. (1994). “Training feed forward networks with the Marquardt algorithm.” IEEE Trans. Neural Networks, 5(6), 989–993.
Jain, A., and Indurthy, S. K. V. P. (2003). “Comparative analysis of event based rainfall—runoff modeling techniques—deterministic, statistical, and artificial neural networks.” J. Hydrol. Eng., 8(2), 1–6.
Jain, A., and Srinivasulu, S. (2004). “Development of effective and efficient rainfall—runoff models using integration of deterministic, real-coded genetic algorithms, and artificial neural network techniques.” Water Resour. Res., 40(4), W04302,.
Jang, J. S. R., Sun, C. T., and Mizutani, E. (1997). Neuro-fuzzy and soft computing, Prentice Hall, Upper Saddle River, NJ.
Ju, Q., Yu, Z., Hao, Z., Ou, G., Zhao, J., and Liu, D. (2009). “Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model.” Neurocomputing, 72(13–15), 2873–2883.
Karim, S., and Zahra, D. (2008). “Comparative analysis of training methods and different data for the Rainfall-Runoff prediction using artificial neural networks.” Res. J. Environ. Sci., 2(5), 353–365.
Kisi, O., and Uncuoglu, E. (2005). “Comparison of three back-propagation training algorithms for two case studies.” Indian J. Eng. Mater. Sci., 12(5), 434–442.
Maier, H. R., and Dandy, G. C. (2000). “Neural networks for the prediction and forecasting of water resources variables: A review of modeling issues and applications.” Environ. Model. Software, 15(1), 101–124.
May, D. B., and Sivakumar, M. (2009). “Prediction of urban storm water quality using artificial neural networks.” Environ. Model. Software, 24(2), 296–302.
Meteorological Service Singapore. (1997). Summary of observations (annual publication), Singapore.
Moller, M. F. (1993). “A scaled conjugate gradient algorithm for fast supervised learning.” Neural Networks, 6(4), 525–533.
Mustafa, M. R., Rezaur, R. B., Rahardjo, H., and Isa, M. H. (2011). “Prediction of pore-water pressure using radial basis function neural network.” Eng. Geol., 135–136, 40–47.
Mustafa, M. R., Rezaur, R. B., Saiedi, S., and Rahardjo, H. (2010). “Prediction of pore-water pressure variation using ANN with Scaled Conjugate Gradient learning algorithm.” Proc., First Int. Conf. on Sustainable Building and Infrastructure-ICSBI2010, Kuala Lumpur, Malaysia, Universiti Teknologi Petronas, Malaysia.
Rafik, Z., Ridha, B., and Daniel, R. (2008). “Levenberg-Marqurdt learning neural network for adaptive pre-distortion for time varying HPA with memory in OFDM systems.” 16th European Signal Processing Conference (EUSIPCO 2008), Lausanne, Switzerland.
Rahardjo, H., Leong, E. C., and Rezaur, R. B. (2008). “Characteristics of pore-water pressure distribution in residual soil slopes under tropical rainfalls.” Hydrol. Processes, 22(4), 506–523.
Rahardjo, H., Meilani, I., Leong, E. C., and Rezaur, R. B. (2009). “Shear strength characteristics of a compacted soil under infiltration conditions.” Geomech. Eng., 1(1), 35–52.
Rahardjo, H., Ong, T. H., Rezaur, R. B., and Leong, E. C. (2007). “Factors controlling instability of homogeneous soil slopes under rainfall.” Geotech. Geoenviron. Eng., 133(12), 1532–1543.
Rezaur, R. B., Rahardjo, H., Leong, E. C., and Lee, T. T. (2003). “Hydrological behavior of residual soil slopes in Singapore.” J. Hydrol. Eng., 8(3), 133–144.
Rojas, R. (1996). Neural networks: A systematic introduction, Springer, Berlin, 151–184.
Schraudolph, N. N., and Graepel, T. (2002). “Towards stochastic conjugate gradient methods.” Proc., Ninth Int. Conf. on Neural Information Processing (ICONIP-2002), 853–856.
Srinivasulu, S., and Jain, A. (2006). “A comparative analysis of training methods for artificial neural network rainfall-runoff models.” Appl. Soft Comput., 6(3), 295–306.
Wang, Y., Kim, S., and Principe, J. C. (2005). “Comparison of TDNN training algorithms in brain machine interfaces.” Proc., IEEE Int. Joint Conf. on Neural Networks (IJCNN-2005), IEEE, New York, 2459–2462.
Zhang, B., and Govindaraju, S. (2000). “Prediction of watershed runoff using Bayesian concepts and modular neural networks.” Water Resour. Res., 36(3), 753–762.
Information & Authors
Information
Published In
Journal of Hydrologic Engineering
Volume 18 • Issue 1 • January 2013
Pages: 50 - 57
Copyright
© 2013 American Society of Civil Engineers.
History
Received: May 14, 2011
Accepted: Feb 3, 2012
Published online: Feb 6, 2012
Published in print: Jan 1, 2013
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.