Knowledge Extraction from Trained Neural Network River Flow Models
Publication: Journal of Hydrologic Engineering
Volume 10, Issue 4
Abstract
Artificial neural networks (ANNs), due to their excellent capabilities for modeling complex processes, have been successfully applied to a variety of problems in hydrology. However, one of the major criticisms of ANNs is that they are just black-box models, since a satisfactory explanation of their behavior has not been offered. They, in particular, do not explain easily how the inputs are related to the output, and also whether the selected inputs have any significant relationship with an output. In this paper, a perturbation analysis for determining the order of influence of the elements in the input vector on the output vector is discussed. The approach is illustrated though a case study of a river flow model developed for the Narmada Basin, India. The analyses of the results suggest that each variable in the input vector (flow values at different antecedent time steps) influences the shape of the hydrograph in different ways. However, the magnitude of the influence cannot be clearly quantified by this approach. Further it adds that the selection of input vector based on linear measures between the variables of interest, which is commonly employed, may still include certain spurious elements that only increase the model complexity.
Get full access to this article
View all available purchase options and get full access to this article.
References
American Society for Civil Engineering (ASCE) Task Committee. (2000). “Artificial neural networks in hydrology-II: Hydrologic applications.” J. Hydrologic Eng., 5(2), 124–137.
Benitez, J. M., Castro, J. L., and Requena, I. (1997). “Are artificial neural networks black boxes?.” IEEE Trans. Neural Netw., 8(5), 1156–1164.
Campolo, M., Andreussi, P., and Soldati, A. (1999). “River flood forecasting with neural network model.” Water Resour. Res., 35(4), 1191–1197.
Castro, J. L., Mantas, C. J., and Benitez, J. M. (2002). “Interpretation of artificial neural networks by means of fuzzy rules.” IEEE Trans. Neural Netw., 13(1), 101–116.
Dowson, C. W., and Wilby, R. L. (2001). “Hydrological modeling using artificial neural networks.” Prog. Phys. Geogr., 25(1), 80–108.
Eberhart, R. C., and Dobbins, R. W. (1990). Neural network PC tools: A practical guide, Academic, New York.
Ho, Y.-C. (1992). “Perturbation analysis: Concepts and algorithms.” Proc., 1992 Winter Simulation Conf., Arlington, Va., J. J. Swain, D. Goldsman, R. C. Crain, and J. R. Wilson, eds., 231–240.
Hsu, K., Gupta, V. H., and Sorooshian, S. (1995). “Artificial neural network modeling of the rainfall-runoff process.” Water Resour. Res., 31(10), 2517–2530.
Jain, A., Sudheer, K. P., and Srinivasulu, S. (2004). “Identification of physical processes inherent in artificial neural network rainfall runoff models.” Hydrolog. Process., 118(3), 571–581.
Jain, A., Varshney, A. K., and Joshi, U. C. (2001). “Short-term water demand forecast modeling at IIT Kanpur using artificial neural networks.” Water Resour. Manage., 15(5), 299–321.
Jingsheng, J. (2002). “Clustering technique for evaluating and validating neural network performance.” J. Comput. Civ. Eng., 16(2), 152–155.
Lange, N. T. (1999). “New mathematical approaches in hydrological modeling-an application of artificial neural networks.” Phys. Chem. Earth, 24(1&2), 31–35.
Lozowski, A., Cholewo, T. J., and Zurada, J. M. (1996). “Crisp rule extraction from perceptron network classifiers.” Proc., IEEE International Conf. on Neural Networks. Plenary, Panel, and Special Sessions, Washington, D.C., 94–99.
Maier, H. R., and Dandy, G. C. (1997). “Determining inputs for neural network models of multivariate time series.” Microcomput. Civ. Eng., 12, 353–368.
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 application.” Environ. Model. Softw., 15, 101–124.
Schmitz, G. P. J., Aldrich, C., and Gouws, F. S. (1999). “ANN-DT: An algorithm for extraction of decision trees from artificial neural networks.” IEEE Trans. Neural Netw., 10(6), 1392–1401.
Stewart, I. (1989). Does God play dice? The mathematics of chaos, Blackwell, Cambridge, Mass.
Sudheer, K. P., Gosain, A. K., and Ramasastri, K. S. (2002). “A data-driven algorithm for constructing artificial neural network rainfall-runoff models.” Hydrolog. Process., 16(6), 1325–1330.
Sudheer, K. P., and Jain, A. (2004). “Explaining the internal behaviour of artificial neural network river flow models.” Hydrolog. Process., 118(4), 833–844.
Sudheer, K. P., Nayak, P. C., and Ramasastri, K. S. (2003). “Improving peak flow estimates in artificial neural network river flow models.” Hydrolog. Process., 17(3), 677–686.
Tickle, A. B., Andrews, R., Golea, M., and Diederich, J. (1998). “The truth will come to light: Directions and challenges in extracting knowledge embedded within trained artificial neural network.” IEEE Trans. Neural Netw., 9(6), 1057–1068.
Wilby, R. L., Abrahart, R. J., and Dawson, C. W. (2003). “Detection of conceptual model rainfall-runoff processes inside an artificial neural network.” Hydrol. Sci. J., 48(2), 163–181.
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 10 • Issue 4 • July 2005
Pages: 264 - 269
Copyright
© 2005 ASCE.
History
Received: Mar 18, 2004
Accepted: Jul 6, 2004
Published online: Jul 1, 2005
Published in print: Jul 2005
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.