The Use of Stochastic Gradient Boosting Method for Multi-Model Combination of Rainfall-Runoff Models

 Abstract— In this study the novel stochastic gradient boosting (SGB) combination method is addressed for producing daily river flows from four different rain-runoff models of Ohinemuri catchment, New Zealand. The selected rainfall-runoff models are two empirical black-box models: linear perturbation model and linear varying gain factor model, two conceptual models: Soil Moisture Accounting and Routing model and Nedbor-Afrstromnings model. In this study, the simple average combination method and the weighted average combination method were used as a benchmark for comparing the results of the novel SGB combination method. The models and combination results are evaluated using statistical and graphical criteria. Overall results of this study show that the use of combination technique can certainly improve the simulated river flows of four selected models for Ohinemuri catchment, New Zealand. The results also indicate that the novel SGB combination method is capable to develop a multi-model combination system of the Ohinemuri river catchment in New Zealand.

[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]  Hoshin Vijai Gupta,et al.  Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling , 2009 .

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

[4]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

[5]  Wenzhi Zhao,et al.  Application of the Takagi–Sugeno fuzzy system for combination forecasting of river flow in semiarid mountain regions , 2009 .

[6]  J. E. Nash,et al.  A hybrid model for flow forecasting on large catchments , 1983 .

[7]  Application of the linear perturbation model (LPM) to flood routing on the Mekong River , 1988 .

[8]  Kieran M. O'Connor,et al.  Real-time flow forecasting in the absence of quantitative precipitation forecasts: A multi-model approach , 2007 .

[9]  Young-Oh Kim,et al.  Combining Rainfall-Runoff Model Outputs for Improving Ensemble Streamflow Prediction , 2006 .

[10]  Lutz Breuer,et al.  Multi-model data fusion as a tool for PUB: example in a Swedish mesoscale catchment , 2011 .

[11]  R. Abrahart,et al.  Use of Gene Expression Programming for Multimodel Combination of Rainfall-Runoff Models , 2012 .

[12]  C. Granger,et al.  Forecasting Economic Time Series. , 1988 .

[13]  J. Friedman.  Stochastic gradient boosting , 2002 .

[14]  Jens Christian Refsgaard,et al.  Validation and Intercomparison of Different Updating Procedures for Real-Time Forecasting , 1997 .

[15]  S. Sorooshian,et al.  Multimodel Combination Techniques for Analysis of Hydrological Simulations: Application to Distributed Model Intercomparison Project Results , 2006 .

[16]  R. Clemen.  Combining forecasts: A review and annotated bibliography , 1989 .

[17]  Asaad Y. Shamseldin,et al.  A comparative study of three neural network forecast combination methods for simulated river flows of different rainfall—runoff models , 2007 .

[18]  P. E. O'connell,et al.  River flow forecasting through conceptual models part III - The Ray catchment at Grendon Underwood , 1970 .

[19]  George Cavadias,et al.  The Combination of Simulated Discharges of Hydrological Models , 1986 .

[20]  J. Scott Armstrong,et al.  Forecasting for Environmental Decision Making , 2001 .

[21]  R. L. Winkler,et al.  Averages of Forecasts: Some Empirical Results , 1983 .

[22]  A. Shamseldin,et al.  Methods for combining the outputs of different rainfall–runoff models , 1997 .