Machine Learning Approaches for Error Correction of Hydraulic Simulation Models for Canal Flow Schemes
Publication: Journal of Irrigation and Drainage Engineering
Volume 138, Issue 11
Abstract
Modernization of today’s irrigation systems attempts to improve system efficiency and management effectiveness of every component of the system (reservoirs, canals, and gates) using automation technologies, along with hydraulic simulation models. The canal flow control scheme resulting from the coupling of the system automation and the simulation models has proven to be an excellent irrigation water management instrument around the world. Nevertheless, the harsh environment of irrigation systems can induce uncertainties or errors in the components of canal flow control that can worsen over time, misleading or confusing both human and computer controllers. These errors can be attributed to parameter measurement and conceptual sources, with the complexity of locating their individual origin. In this paper, a framework is presented to minimize the collective or aggregate error within an irrigation canal flow control scheme that uses a learning machine algorithm (multilayer perceptron and relevance vector machine) embedded in a hydraulic simulation model fed by a canal automation system. This framework is evaluated using actual data from an irrigation conveyance canal located at the Lower Sevier River Basin in Utah. The results obtained prove the adequacy of the proposed framework in minimizing the aggregate error, which affects the simulation results of the automation system (up to 91% in bias and 83% in maximum absolute error) when compared with the original values obtained in the verification period. The temporal correlation of the aggregate error was also significantly reduced, thus resulting in reduced local biases and structures in the model prediction error.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
The authors thank the Utah Water Research Laboratory, the Utah Center for Water Resources Research, and the Utah State University Research Foundation for their support of this research. The authors also thank the U.S. Bureau of Reclamation and the Lower Basin Commissioner of the Sevier River Water Users Association for their continued assistance and support in this research.
References
Anguita, D., Boni, A., and Ridella, S. (2000). “Evaluating the generalization ability of support vector machines through the bootstrap.” Neural Process. Lett., 11(1), 51–58.
Artichowicz, W., and Szymkiewicz, R. (2009). “Inverse integration of the open channel flow equations.” 11th Int. Symp. on Water Management and Hydraulic Engineering (online publication), Ohrid, Macedonia, 1–5.
Asefa, T., Kemblowski, M., McKee, M., and Khalil, A. F. (2006). “Multi-time scale stream flow predictions: The support vector machines approach.” J. Hydrol. (Amsterdam), 318(1–4), 7–16.
Bishop, C. M. (1995). Neural networks for pattern recognition, Oxford University Press, Oxford, UK.
Breiman, L. (2001). “Statistical modeling: The two cultures (with comments and a rejoinder by the author).” Statist. Sci., 16(3), 199–231.
Chesher, A. (1991). “The effect of measurement error.” Biometrika, 78(3), 451–462.
Clemmens, A. J., Bautista, E., Wahlin, B. T., and Strand, R. J. (2005). “Simulation of automatic canal control sytems.” J. Irrig. Drain. Eng., 131(4), 324.
Cortez, P. (2010). “Sensitivity analysis for time lag selection to forecast seasonal time series using neural networks and support vector machines.” 2010 Int. Joint Conf. on Neural Networks (IJCNN), IEEE, Barcelona, Spain, 1–8.
Demissie, Y. K., Valocchi, A. J., Minsker, B. S., and Bailey, B. A. (2009). “Integrating a calibrated groundwater flow model with error-correcting data-driven models to improve predictions.” J. Hydrol. (Amsterdam), 364(3/4), 257–271.
Efron, B., and Tibshirani, R. J. (1993). An introduction to the bootstrap, Chapman and Hall, New York, 436.
Ghosh, S., and Mujumdar, P. (2008). “Statistical downscaling of GCM simulations to streamflow using relevance vector machine.” Adv. Water Resour., 31(1), 132–146.
Gupta, H. V., Wagener, T., and Liu, Y. (2008). “Reconciling theory with observations: Elements of a diagnostic approach to model evaluation.” Hydrol. Process., 22(18), 3802–3813.
Guyon, I., and Elisseeff, A. (2003). “An introduction to variable and feature selection.” J. Mach. Learn. Res., 3, 1157–1182.
Hesterberg, T., Moore, D. S., Monaghan, S., Clipson, A., and Epstein, R. (2005). “Bootstrap methods and permutation tests.” Practice of business statistics, Companion Ch. 18, Freeman, New York, Vol. 5, 70.
Khalil, A. F., McKee, M., Kemblowski, M., and Asefa, T. (2005). “Sparse Bayesian learning machine for real-time management of reservoir releases.” Water Resour. Res., 41(11), W11401.
Khalil, A. F., McKee, M., Kemblowski, M., Asefa, T., and Bastidas, L. A. (2006). “Multiobjective analysis of chaotic dynamic systems with sparse learning machines.” Adv. Water Resour., 29(1), 72–88.
Landeras, G., Ortiz-Barredo, A., and López, J. J. (2009). “Forecasting weekly evapotranspiration with ARIMA and artificial neural network models.” J. Irrig. Drain. Eng., 135(3), 323–334.
MacKay, D. J. C. (1992). “A practical Bayesian framework for backpropagation networks.” Neural Comput., 4(3), 448–472.
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.
Martí, P., Provenzano, G., Royuela, Á., and Palau-Salvador, G. (2010). “Integrated emitter local loss prediction using artificial neural networks.” J. Irrig. Drain. Eng., 136(1), 11–22.
Nabney, I. T. (2001). NETLAB: Algorithms for pattern recognition, Springer-Verlag, New York.
Nabney, I. T. (2011). “Netlab toolbox.” 〈http://www1.aston.ac.uk/eas/research/groups/ncrg/resources/netlab/〉 (Jan. 5, 2010).
Pebesma, E. J., Switzer, P., and Loague, K. (2005). “Error analysis for the evaluation of model performance: Rainfall-runoff event time series data.” Hydrol. Process., 19(8), 1529–1548.
Pierce, S. G., Worden, K., and Bezazi, A. (2008). “Uncertainty analysis of a neural network used for fatigue lifetime prediction.” Mech. Syst. Signal Process., 22(6), 1395–1411.
Pulido-Calvo, I., and Gutiérrez-Estrada, J. C. (2009). “Improved irrigation water demand forecasting using a soft-computing hybrid model.” Biosyst. Eng., 102(2), 202–218.
Pulido-Calvo, I., Montesinos, P., Roldán, J., and Ruiz-Navarro, F. (2007). “Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems.” Biosyst. Eng., 97(2), 283–293.
Pulido-Calvo, I., Roldán, J., López-Luque, R., and Gutiérrez-Estrada, J. C. (2003). “Demand forecasting for irrigation water distribution systems.” J. Irrig. Drain. Eng., 129(6), 422–431.
Rosenberry, D. O. (1990). “Effect of sensor error on interpretation of long-term water-level data.” Ground Water, 28(6), 927–936.
Seibert, J. (2003). “Reliability of model predictions outside calibration conditions.” Nord. Hydrol., 34(5), 477–492.
Sevier River Water Users Association (SRWUA). (2011). “Canal A recording data.” Rivers and Canals, 〈http://www.sevierriver.org〉 (Dec. 15, 2009).
Skogerboe, G. V., and Merkley, G. P. (1996). Irrigation maintenance and operations learning process, Water Resources Publications, Englewood, CO, 369.
Souza, F., and Araujo, R. (2011). “Variable and time-lag selection using empirical data.” 2011 IEEE 16th Conf. on Emerging Technologies & Factory Automation (ETFA), IEEE, Washington, DC, 1–8.
Ticlavilca, A. M., and McKee, M. (2011). “Multivariate Bayesian regression approach to forecast releases from a system of multiple reservoirs.” Water Resour. Manage., 25, 523–543.
Ticlavilca, A. M., McKee, M., and Walker, W. R. (2011). “Real-time forecasting of short-term irrigation canal demands using a robust multivariate Bayesian learning model.” Irrig. Sci., August.
Tikka, J., and Hollmen, J. (2008). “Sequential input selection algorithm for long-term prediction of time series.” Neurocomputing, 71(13–15), 2604–2615.
Tikka, J., Hollmén, J., and Lendasse, A. (2005). “Input selection for long-term prediction of time series.” Computational intelligence and bioinspired systems, Springer-Verlag, New York, 1002–1009.
Tipping, M. E. (2001). “Sparse Bayesian learning and the relevance vector machine.” J. Mach. Learn. Res., 1(3), 211–244.
Tipping, M. E. (2011). “SparseBayes library for Matlab—version 2.” Software, 〈http://www.miketipping.com〉 (Jan. 5, 2010).
Tipping, M. E., and Faul, A. (2003). “Fast marginal likelihood maximization for sparse Bayesian models.” Proc., 9th Int. Workshop on Artificial Intelligence and Statistics (online publication), Key West, FL, 1, 1–13.
Torres, A. F., Walker, W. R., and McKee, M. (2011). “Forecasting daily potential evapotranspiration using machine learning and limited climatic data.” Agr. Water Manage., 98(4), 553–562.
Walker, W. R. (2011). “Lessons for the last half century of irrigation engineering research—Where to now?” IV National Irrigation Conference and III Iberoamerican Irrigation and Drainage Conference, La Molina National Agrarian Univ., Lima, Peru, 23.
Walker, W. R., and Skogerboe, G. V. (1987). Surface irrigation theory and practice, Prentice-Hall, Englewood Cliffs, NJ, 150.
Walker, W. R., and Stringam, B. S. (1999). “Low cost adaptable canal automation for small canals.” Irrig. Drain., 48(3), 39–46.
Walker, W. R., and Stringam, B. S. (2000). “Canal automation for water conservation and improved flexibility.” Proc., 4th Decennial National Irrigation Symposium, American Society of Agricultural Engineers, Phoenix, AZ.
Zaman, B., Jensen, A. M., and McKee, M. (2011). ”Use of high-resolution multispectral imagery acquired with an autonomous unmanned aerial vehicle to quantify the spread of an invasive wetlands species.” Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International eds., Vancouver, Canada, 1, 803–806.
Zechman, E. M., and Ranjithan, S. (2007). “Evolutionary computation-based approach for model error correction and calibration.” Adv. Water Resour., 30(5), 1360–1370.
Information & Authors
Information
Published In
Copyright
© 2012 American Society of Civil Engineers.
History
Received: Jan 1, 2011
Accepted: Apr 23, 2012
Published online: Apr 25, 2012
Published in print: Nov 1, 2012
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.