Evolutionary multiobjective optimization for selecting members of an ensemble streamflow forecasting model

We are proposing to use the Nondominated Sorting Genetic Algorithm II (NSGA-II) for optimizing a hydrological forecasting model of 800 simultaneous streamflow predictors. The optimization is based on the selection of the best 48 predictors from the 800 that jointly define the "best" ensemble in terms of two probabilistic criteria. Results showed that the difficulties in simplifying the ensembles mainly originate from the preservation of the system reliability. We conclude that Pareto fronts generated with NSGA-II allow the development of a decision process based explicitly on the trade-off between different probabilistic properties. In other words, evolutionary multiobjective optimization offers more flexibility to the operational hydrologists than a priori methods that produce only one selection.

[1]  A. E. Eiben,et al.  Introduction to Evolutionary Computing , 2003, Natural Computing Series.

[2]  Christian Gagné,et al.  Simplifying a hydrological ensemble prediction system with a backward greedy selection of members – Part 1: Optimization criteria , 2011 .

[3]  F. Molteni,et al.  A strategy for high‐resolution ensemble prediction. I: Definition of representative members and global‐model experiments , 2001 .

[4]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[5]  R. Buizza,et al.  Flood forecasting using medium-range probabilistic weather prediction , 2005 .

[6]  Jasper A Vrugt,et al.  Improved evolutionary optimization from genetically adaptive multimethod search , 2007, Proceedings of the National Academy of Sciences.

[7]  Andreas S. Weigend,et al.  Predicting Daily Probability Distributions of S&P500 Returns , 1998 .

[8]  F. Anctil,et al.  An experiment on the evolution of an ensemble of neural networks for streamflow forecasting , 2009 .

[9]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[10]  K. Beven,et al.  Cascading model uncertainty from medium range weather forecasts (10 days) through a rainfall-runoff model to flood inundation predictions within the European Flood Forecasting System (EFFS) , 2005 .

[11]  Naonori Ueda,et al.  Generalization error of ensemble estimators , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[12]  Anders Krogh,et al.  Neural Network Ensembles, Cross Validation, and Active Learning , 1994, NIPS.

[13]  Simon Jaun,et al.  A probabilistic view on the August 2005 floods in the upper Rhine catchment , 2008 .

[14]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[15]  A. H. Murphy,et al.  What Is a Good Forecast? An Essay on the Nature of Goodness in Weather Forecasting , 1993 .

[16]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[17]  Jihoon Yang,et al.  Feature Subset Selection Using a Genetic Algorithm , 1998, IEEE Intell. Syst..

[18]  Marc Parizeau,et al.  DEAP: evolutionary algorithms made easy , 2012, J. Mach. Learn. Res..

[19]  Vilas M. Thakare,et al.  Computing the Most Significant Solution from Pareto Front obtained in Multi-objective Evolutionary , 2010 .

[20]  Martyn P. Clark,et al.  HEPEX: The Hydrological Ensemble Prediction Experiment , 2007 .

[21]  Christian Gagné,et al.  Simplifying a hydrological ensemble prediction system with a backward greedy selection of members – Part 2: Generalization in time and space , 2011 .

[22]  E. Sprokkereef,et al.  Verification of ensemble flow forecasts for the River Rhine , 2009 .

[23]  Kenneth A. De Jong,et al.  Genetic algorithms as a tool for feature selection in machine learning , 1992, Proceedings Fourth International Conference on Tools with Artificial Intelligence TAI '92.

[24]  W. Briggs.  Statistical Methods in the Atmospheric Sciences , 2007 .

[25]  A. Raftery,et al.  Strictly Proper Scoring Rules, Prediction, and Estimation , 2007 .

[26]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[27]  F. Anctil,et al.  Can a multi-model approach improve hydrological ensemble forecasting? A study on 29 French catchments using 16 hydrological model structures , 2011 .

[28]  Jasbir S. Arora,et al.  Survey of multi-objective optimization methods for engineering , 2004 .

[29]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[30]  Florian Pappenberger,et al.  Ensemble flood forecasting: a review. , 2009 .

[31]  Shahid Ali,et al.  Feature subset selection using multi-objective genetic algorithms , 2009, 2009 IEEE 13th International Multitopic Conference.

[32]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[33]  E. Roulin,et al.  Skill and relative economic value of medium-range hydrological ensemble predictions , 2006 .