Improved irrigation water demand forecasting using a soft-computing hybrid model

Recently, Computational Neural Networks (CNNs) and fuzzy inference systems have been successfully applied to time series forecasting. In this study the performance of a hybrid methodology combining feed forward CNN, fuzzy logic and genetic algorithm to forecast one-day ahead daily water demands at irrigation districts considering that only flows in previous days are available for the calibration of the models were analysed. Individual forecasting models were developed using historical time series data from the Fuente Palmera irrigation district located in Andalucia, southern Spain. These models included univariate autoregressive CNNs trained with the Levenberg–Marquardt algorithm (LM). The individual models forecasting were then corrected via a fuzzy logic approach whose parameters were adjusted using a genetic algorithm in order to improve the forecasting accuracy. For the purpose of comparison, this hybrid methodology was also applied with univariate autoregressive CNN models trained with the Extended-Delta-Bar-Delta algorithm (EDBD) and calibrated in a previous study in the same irrigation district. A multicriteria evaluation with several statistics and absolute error measures showed that the hybrid model performed significantly better than univariate and multivariate autoregressive CNNs.

[1]  Robert J. Abrahart,et al.  Multi-model data fusion for river flow forecasting: an evaluation of six alternative methods based on two contrasting catchments , 2002 .

[2]  Mustafa M. Aral,et al.  Remediation System Design with Multiple Uncertain Parameters Using Fuzzy Sets and Genetic Algorithm , 2005 .

[3]  E. Fereres,et al.  Evaluating irrigation performance in a Mediterranean environment , 2004, Irrigation Science.

[4]  Luis S. Pereira,et al.  Higher performance through combined improvements in irrigation methods and scheduling : a discussion , 1999 .

[5]  Ozgur Kisi,et al.  Adaptive Neurofuzzy Computing Technique for Evapotranspiration Estimation , 2007 .

[6]  Inmaculada Pulido-Calvo,et al.  Demand Forecasting for Irrigation Water Distribution Systems , 2003 .

[7]  A. Shamseldin,et al.  A real-time combination method for the outputs of different rainfall-runoff models , 1999 .

[8]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[9]  Kuolin Hsu,et al.  Improved streamflow forecasting using self-organizing radial basis function artificial neural networks , 2004 .

[10]  Martin Burton,et al.  Benchmarking performance in the irrigation and drainage sector: a tool for change , 2004 .

[11]  David H. Wolpert,et al.  On Bias Plus Variance , 1997, Neural Computation.

[12]  Momcilo Markus,et al.  PRECIPITATION-RUNOFF MODELING USING ARTIFICIAL NEURAL NETWORKS AND CONCEPTUAL MODELS , 2000 .

[13]  R. López-Luque,et al.  Benchmarking and multivariate data analysis techniques for improving the efficiency of irrigation districts: An application in spain , 2008 .

[14]  Peggy A. Johnson,et al.  Stream hydrological and ecological responses to climate change assessed with an artificial neural network , 1996 .

[15]  Jens Ove Riis,et al.  A hybrid econometric—neural network modeling approach for sales forecasting , 1996 .

[16]  Peter Wallensteen,et al.  Comprehensive Assessment of the Freshwater Resources of the World, International Fresh Water Resources: Conflict or Cooperation , 1997 .

[17]  MSc PhD Adrian J. Shepherd BA.  Second-Order Methods for Neural Networks , 1997, Perspectives in Neural Computing.

[18]  Nicola Lamaddalena,et al.  A simulation model to generate the demand hydrographs in large-scale irrigation systems , 2006 .

[19]  E. Camacho Poyato,et al.  Applying benchmarking and data envelopment analysis (DEA) techniques to irrigation districts in Spain , 2004 .

[20]  Juan Carlos Gutiérrez Estrada,et al.  ESTIMACIÓN A CORTO PLAZO DE LA TEMPERATURA DEL AGUA. APLICACIÓN EN SISTEMAS DE PRODUCCIÓN EN MEDIO ACUÁTICO , 2005 .

[21]  K. Thirumalaiah,et al.  Hydrological Forecasting Using Neural Networks , 2000 .

[22]  K. Thirumalaiah,et al.  River Stage Forecasting Using Artificial Neural Networks , 1998 .

[23]  H. Murase,et al.  Reservoir Level Forecasting using Neural Networks: Lake Naivasha , 2007 .

[24]  R. Clement,et al.  Calcul des dbits dans les rseaux d'irrigation fonctionnant la demande , 1966 .

[25]  Inmaculada Pulido-Calvo,et al.  Comparison between traditional methods and artificial neural networks for ammonia concentration forecasting in an eel (Anguilla anguilla L.) intensive rearing system , 2004 .

[26]  Cyril Goutte,et al.  Note on Free Lunches and Cross-Validation , 1997, Neural Computation.

[27]  R. López-Luque,et al.  Application of Data Envelopment Analysis to Studies of Irrigation Efficiency in Andalusia , 2004 .

[28]  J. Roldán,et al.  Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems , 2007 .

[29]  Stefano Marsili-Libelli,et al.  Fuzzy prediction of the algal blooms in the Orbetello lagoon , 2004, Environ. Model. Softw..

[30]  Stan Openshaw,et al.  A hybrid multi-model approach to river level forecasting , 2000 .

[31]  Yen-Ming Chiang,et al.  Comparison of static-feedforward and dynamic-feedback neural networks for rainfall -runoff modeling , 2004 .

[32]  M. Erol Keskin,et al.  Adaptive neural-based fuzzy inference system (ANFIS) approach for modelling hydrological time series , 2006 .

[33]  Inmaculada Pulido-Calvo,et al.  Application of neural approaches to one-step daily flow forecasting in Portuguese watersheds , 2007 .

[34]  Kuolin Hsu,et al.  Artificial Neural Network Modeling of the Rainfall‐Runoff Process , 1995 .

[35]  Ashish Sharma,et al.  Impact of mid-Pacific Ocean thermocline on the prediction of Australian rainfall , 2006 .

[36]  David Horn,et al.  Combined Neural Networks for Time Series Analysis , 1993, NIPS.

[37]  J. Doorenbos,et al.  Guidelines for predicting crop water requirements , 1977 .

[38]  Li-Chiu Chang,et al.  Fuzzy exemplar‐based inference system for flood forecasting , 2005 .

[39]  Christian Jacob,et al.  Illustrating Evolutionary Computation with Mathematica , 2001 .

[40]  Roland K. Price,et al.  A neural network model of rainfall-runoff using radial basis functions , 1996 .

[41]  R. Abrahart,et al.  Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments , 2000 .

[42]  Robert J. Kuligowski,et al.  Experiments in Short-Term Precipitation Forecasting Using Artificial Neural Networks , 1998 .

[43]  José Maria Tarjuelo,et al.  New Methodology to Evaluate Flow Rates in On-Demand Irrigation Networks , 2007 .

[44]  Sebastián Ventura,et al.  Artificial Neural Networks for Estimation of Kinetic Analytical Parameters , 1995 .

[45]  T. McMahon,et al.  Forecasting operational demand for an urban water supply zone , 2002 .

[46]  Nicola Lamaddalena,et al.  Performance analysis of pressurized irrigation systems operating on-demand using flow-driven simulation models , 2008 .

[47]  Hao Ying,et al.  Denitrification in aquaculture systems: an example of a fuzzy logic control problem , 2000 .

[48]  Ashu Jain,et al.  Short-Term Water Demand Forecast Modelling at IIT Kanpur Using Artificial Neural Networks , 2001 .

[49]  Jagadeesh Anmala,et al.  Rainfall-Runoff Modeling Using Artificial Neural Networks , 2010 .

[50]  Ibrahim El-Amin,et al.  Artificial neural networks as applied to long-term demand forecasting , 1999, Artif. Intell. Eng..

[51]  Surendra Kumar Mishra,et al.  Simulation of Runoff and Sediment Yield using Artificial Neural Networks , 2006 .

[52]  Peter H. Gleick,et al.  Comprehensive Assessment of the Freshwater Resources of the World , 1997 .

[53]  Dirk Raes,et al.  Improving irrigation management by modelling the irrigation schedule , 1988 .

[54]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[55]  Yinghua Lin,et al.  A new approach to fuzzy-neural system modeling , 1995, IEEE Trans. Fuzzy Syst..

[56]  Yinghua Lin,et al.  Input variable identification - fuzzy curves and fuzzy surfaces , 1996, Fuzzy Sets Syst..

[57]  Robert J. Abrahart,et al.  Using pruning algorithms and genetic algorithms to optimise network architectures and forecasting inputs in a neural network rainfall-runoff model , 1999 .

[58]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[59]  Bart Kosko,et al.  Fuzzy Engineering , 1996 .

[60]  Michael Y. Hu,et al.  A simulation study of artificial neural networks for nonlinear time-series forecasting , 2001, Comput. Oper. Res..

[61]  José Carlos Príncipe,et al.  A Theory for Neural Networks with Time Delays , 1990, NIPS.

[62]  Robert J. Abrahart,et al.  Multi-model data fusion for hydrological forecasting , 2001 .

[63]  L. L. Rogers,et al.  Optimization of groundwater remediation using artificial neural networks with parallel solute transport modeling , 1994 .

[64]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .

[65]  S. Sorooshian,et al.  Automatic calibration of conceptual rainfall-runoff models: sensitivity to calibration data , 1996 .

[66]  Umberto Fratino,et al.  On-farm Sprinkler Irrigation Performance as affected by the Distribution System , 2007 .

[67]  Chun-Chieh Yang,et al.  Artificial Neural Network Model for Subsurface-Drained Farmlands , 1997 .

[68]  Stefano Alvisi,et al.  A short-term, pattern-based model for water-demand forecasting , 2006 .

[69]  J. Doorenbos,et al.  Yield response to water , 1979 .

[70]  L. S. Pereira,et al.  Crop evapotranspiration : guidelines for computing crop water requirements , 1998 .

[71]  L. See,et al.  An evaluation of a traditional and a neural net modelling approach to flood forecasting for an upland catchment , 2002 .

[72]  P. Kitanidis,et al.  Real‐time forecasting with a conceptual hydrologic model: 2. Applications and results , 1980 .

[73]  Mahmut Firat,et al.  Evaluation of Artificial Neural Network Techniques for Municipal Water Consumption Modeling , 2009 .

[74]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[75]  K. Adamowski,et al.  Short‐term municipal water demand forecasting , 2005 .

[76]  Inmaculada Pulido-Calvo,et al.  Water Delivery System Planning Considering Irrigation Simultaneity , 2003 .

[77]  Mahmud Güngör,et al.  Hydrological time‐series modelling using an adaptive neuro‐fuzzy inference system , 2008 .

[78]  Krzysztof J. Cios,et al.  Time series forecasting by combining RBF networks, certainty factors, and the Box-Jenkins model , 1996, Neurocomputing.

[79]  Linda See,et al.  Applying soft computing approaches to river level forecasting , 1999 .

[80]  François Anctil,et al.  Evaluation of Neural Network Streamflow Forecasting on 47 Watersheds , 2005 .

[81]  Ding-Geng Chen,et al.  A fuzzy logic model with genetic algorithm for analyzing fish stock-recruitment relationships , 2000 .

[82]  Jose D. Salas,et al.  Regional Drought Analysis Based on Neural Networks , 2000 .

[83]  José María Sumpsi Viñas.  Economía y política de gestión del agua en la agricultura , 1998 .

[84]  Davar Khalili,et al.  Daily Stream Flow Prediction Capability of Artificial Neural Networks as influenced by Minimum Air Temperature Data , 2006 .

[85]  José Roldán Cañas,et al.  Técnicas de predicción a corto plazo de la demanda de agua. Aplicación al uso agrícola , 2002 .

[86]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[87]  M. Lorrai,et al.  Neural nets for modelling rainfall-runoff transformations , 1995 .

[88]  Witold F. Krajewski,et al.  Rainfall forecasting in space and time using a neural network , 1992 .

[89]  Hae-Hoon Park.  Analysis and prediction of walleye pollock (Theragra chalcogramma) landings in Korea by time series analysis , 1998 .

[90]  H. Riedwyl.  Goodness of Fit , 1967 .

[91]  E. Fereres,et al.  Evaluating irrigation performance in a Mediterranean environment , 2004, Irrigation Science.

[92]  Lefteri H. Tsoukalas,et al.  Fuzzy and neural approaches in engineering , 1997 .

[93]  Yonghong Tan,et al.  Neural-network-based d-step-ahead predictors for nonlinear systems with time delay , 1999 .

[94]  J. C. Gutiérrez-Estrada,et al.  Monthly catch forecasting of anchovy Engraulis ringens in the north area of Chile: Non-linear univariate approach , 2007 .

[95]  Ming Zhang,et al.  Rainfall estimation using artificial neural network group , 1997, Neurocomputing.