Real-time forecasting of short-term irrigation canal demands using a robust multivariate Bayesian learning model

详细信息    查看全文

• 作者：Andres M. Ticlavilca (1)
  Mac McKee (1)
  Wynn R. Walker (2)
  
• 刊名：Irrigation Science
• 出版年：2013
• 出版时间：March 2013
• 年：2013
• 卷：31
• 期：2
• 页码：151-167
• 全文大小：995KB
• 参考文献：1. Adeloye AJ (2009) Multiple linear regression and artificial neural networks models for generalized reservoir storage-yield-reliability function for reservoir planning. J Hydrol Eng 14(7):731-38 CrossRef
  2. ASCE Task Committee on Definition of Criteria for Evaluation of Watershed Models of the Watershed Management, Irrigation, Drainage Division (ASCE) (1993) Criteria for evaluation of watershed models. J Irr Drain Eng 119(3):429-42 CrossRef
  3. ASCE Task Committee on the Application of ANNs in Hydrology (2000a) Artificial neural networks in hydrology, I: preliminary concepts. J Hydrol Eng 5(2):115-23 CrossRef
  4. ASCE Task Committee on the Application of ANNs in Hydrology (2000b) Artificial neural networks in hydrology, II: hydrologic application. J Hydrol Eng 5(2):124-37 CrossRef
  5. Berger B, Hansen R, Hilton A (2002) Using the World-Wide-Web as a support system to enhance water management. Paper presented at the 18th ICID congress and 53rd IEC meeting, International Committee on Irrigation and Drainage, Montreal, Quebec, Canada
  6. Berger B, Hansen R, Jensen R (2003) Sevier River Basin System Description. Sevier River Water Users Association, Delta
  7. Bishop CM (1995) Neural network for pattern recognition. Oxford University Press, USA
  8. Cherkassky V, Krasnopolsky V, Solomatine DP, Valdes J (2006) Computational intelligence in earth sciences and environmental applications: issues and challenges. Neural Netw 19:113-21 CrossRef
  9. De Sanctis AE, Shang F, Uber JG (2010) Real-time identification of possible contamination sources using network backtracking methods. J Water Resour Plan Manage 136(4):444-53 CrossRef
  10. Demuth H, Beale M, Hagan M (2009) Neural network toolbox user’s guide. The MathWorks Inc, USA
  11. Duda RO, Hart P, Stork D (2001) Pattern classification, 2nd edn. Wiley Interscience, USA
  12. Efron B, Tibshirani R (1998) An introduction of the bootstrap. Monographs on statistics and applied probability, vol 57. CRC Press LLC, USA
  13. Khalil A, Almasari M, McKee M, Kemblowski MW, Kaluarachchi J (2005a) Applicability of statistical learning algorithms in groundwater quality modeling. Water Resour Res 41:W05010 CrossRef
  14. Khalil A, McKee M, Kemblowski MW, Asefa T (2005b) Sparse Bayesian learning machine for real-time management of reservoir releases. Water Resour Res 41:W11401 CrossRef
  15. Khalil A, McKee M, Kemblowski MW, Asefa T, Bastidas L (2005c) Multiobjective analysis of chaotic dynamic systems with sparse learning machines. Adv Water Res 29:72-8 CrossRef
  16. Khalil A, McKee M, Kemblowski MW, Asefa T (2005d) Basin-scale water management and forecasting using neural networks. J Am Water Resour Res 41:195-08 CrossRef
  17. Kim Y, Jabro JD, and Evans RG (2010) Wireless lysimeters for real-time online soil water monitoring. Irrig Sci. doi:10.1007/s00271-010-0249-x
  18. Kisi O (2009) Daily pan evaporation modeling using multi-layer perceptrons and radial basis neural networks. Hydrol Process 23:213-23 CrossRef
  19. Krasnopolsky VM (2009) Neural network applications to solve forward and inverse problems in atmospheric and oceanic satellite remote sensing. Artif Intell Methods Environ Sci 9:191-05 CrossRef
  20. Kumar A, Bnadyopadhyay A, Raghuwanshi NS (2008) Comparative study of conventional and artificial neural network-based ETo estimation models. Irrig Sci 26:531-45 CrossRef
  21. Kumar A, Raghuwanshi NS, Singh R (2011) Artificial neural networks approach in evapotranspiration modeling: a review. Irrig Sci 29:11-5 CrossRef
  22. Legates DR, McCabe GJ (1999) Evaluating the use of “goodness-of-fit-measures in hydrologic and hydroclimatic model validation. Water Resour Res 35(1):233-41 CrossRef
  23. Lobbrecht AH, Solomatine DP (2002) Machine learning in real-time control of water systems. Urban Water 4:283-89 CrossRef
  24. Lobbrecht AH, Dibike YB, Solomatine DP (2005) Neural networks and fuzzy systems in model based control of the overwaard polder. J Water Resour Plan Manage 131(2):135-45 CrossRef
  25. Nourani V, Mehdi K, Akira M (2009) A multivariate ANN-wavelet approach for rainfall–runoff modeling. Water Resour Manage 23:2877-894 CrossRef
  26. Parker RL (1994) Geophysical inverse theory. Princenton University Press, Princenton
  27. Pulido-Calvo I, Gutierrez-Estrada JC (2008) Improved irrigation water demand forecasting using a soft-computing hybrid model. Biosyst Eng 102(2):202-18 CrossRef
  28. Pulido-Calvo I, Roldan J, Lopez-Luque R, Gutierrez-Estrada JC (2003) Demand forecasting for irrigation water distribution systems. Irr Drain Eng 129(6):422-31 CrossRef
  29. Rahimi AK (2008) Artificial neural network estimation of reference evapotranspiration from pan evaporation in a semi-arid environment. Irrig Sci 27:35-9 CrossRef
  30. Renault D, Facon T, Wahaj R (2007) Modernizing irrigation management, the MASSCOTE approach. FAO Irrigation and Drainage Paper 63, Rome
  31. Shumway RH, Stoffer DS (2011) Time series analysis and its applications, 3rd edn. Springer, USA CrossRef
  32. Tabari H, Marofi S, Sabziparvar AA (2010) Estimation of daily pan evaporation using artificial neural network and multivariate non-linear regression. Irrig Sci 28:399-06 CrossRef
  33. Tan T, Van Cauwenberghe A (1999) Neural-network-based d-step-ahead predictor for nonlinear systems with time delay. Eng Appl of Artif Intell 12:21-5 CrossRef
  34. Thayananthan A (2005) Template-based pose estimation and tracking of 3D hand motion. Dissertation, University of Cambridge, UK
  35. Thayananthan A, Navaratnam R, Stenger B, Torr PHS, Cipolla R (2008) Pose estimation and tracking using multivariate regression. Pattern Recognit Lett 29(9):1302-310 CrossRef
  36. Ticlavilca AM, McKee M (2011) Multivariate Bayesian regression approach to forecast releases from a system of multiple reservoirs. Water Resour Manage 25:523-43 CrossRef
  37. Tipping ME (2001) Sparse Bayesian learning and the relevance vector machine. J Mach Learn 1:211-44
  38. Tipping ME (2004) Bayesian inference: an introduction to principles and practice in machine learning. In: Bousquet O, von Luxburg U, Ratsch G (eds) Advanced lectures on machine learning. Springer, Berlin, pp 41-2
  39. Tipping ME, Faul A (2003) Fast marginal likelihood maximization for sparse Bayesian models. Paper presented at ninth international workshop on artificial intelligence and statistics, Society for Artifical Intelligence and Statistics, Key West, Florida
  40. Tripathi S, Govindaraju R (2007) On selection of kernel parameters in relevance vector machines for hydrologic applications. Stoch Eviron Res Risk Asses 21:747-64 CrossRef
  41. Van Overloop PJ, Clemmens AJ, Strand RJ, Wagemaker RMJ (2010) Real-time implementation of model predictive control on Maricopa-Stanfield irrigation and drainage district’s WM Canal. J Irr Drain Eng 136(11):747-56 CrossRef
  42. Wang J, Neskovic P, Cooper LN (2005) Training data selection for support vector machines. In: Wang L, Chen K, Ong YS (eds) Advances in natural computation. Springer, Berlin, pp 554-64
  
• 作者单位：Andres M. Ticlavilca (1)
  Mac McKee (1)
  Wynn R. Walker (2)
  
  1. Utah Water Research Laboratory, Department of Civil and Environmental Engineering, Utah State University, 8200 Old Main Hill, Logan, UT, 84322-8200, USA
  2. Department of Civil and Environmental Engineering, College of Engineering, Utah State University, Logan, UT, 84322-4100, USA
  

文摘

In the lower Sevier River basin in Utah, the travel times between reservoir releases and arrival at irrigation canal diversions limit the reservoir operation in enabling delivery changes, which may not be compatible with the on demand schedule in the basin. This research presents a robust machine learning approach to forecast the short-term diversion demands for three irrigation canals. These real-time predictions can assist the operator to react promptly to short-term changes in demand and to properly release water from the reservoir. The models are developed in the form of a multivariate relevance vector machine (MVRVM) that is based on a Bayesian learning machine approach for regression. Predictive confidence intervals can also be obtained from the model with this Bayesian approach. Test results show that the MVRVM learns the input–output patterns with good accuracy. A bootstrap analysis is used to evaluate robustness of model parameter estimation. The MVRVM is compared in terms of performance and robustness with an Artificial Neural Network.