The wisdom of crowds — ensembles and modules in environmental modelling

Predictive models that are composed of a number of combined models, although ubiquitous in climate prediction have not yet become popular in many other areas of environmental modelling, despite growing evidence that they are superior to single-model methods in many ways. These combined-model methodologies are termed ensembles and modules, and this paper reviews their concepts, advantages and how to create them. Additionally, they will be discussed in terms of the critically important bias/variance trade-off. Moreover, ensembles and modules will be discussed with reference to historical and current research papers within environmental modelling.

[1]  Shu-Guang Liu,et al.  Improving Land Resource Evaluation Using Fuzzy Neural Network Ensembles * * Project supported by the , 2007 .

[2]  Bernard Grofman,et al.  Information pooling and group decision making : proceedings of the Second University of California, Irvine, Conference on Political Economy , 1986 .

[3]  Kagan Tumer,et al.  Error Correlation and Error Reduction in Ensemble Classifiers , 1996, Connect. Sci..

[4]  D. Mackay,et al.  Bayesian methods for adaptive models , 1992 .

[5]  Lee Baker.  Optimisation of pedotransfer function models for soil hydraulic properties using an artificial neural network ensemble method , 2005 .

[6]  Robert A. Jacobs,et al.  Methods For Combining Experts' Probability Assessments , 1995, Neural Computation.

[7]  Thomas Harter,et al.  Neural Networks Prediction of Soil Hydraulic Functions for Alluvial Soils Using Multistep Outflow Data , 2004 .

[8]  Renate Hagedorn,et al.  The rationale behind the success of multi-model ensembles in seasonal forecasting-II , 2005 .

[9]  Gabriela Espinosa,et al.  Using an Ensemble of Neural Based QSARs for the Prediction of Toxicological Properties of Chemical Contaminants , 2005 .

[10]  John F. Kolen,et al.  Backpropagation is Sensitive to Initial Conditions , 1990, Complex Syst..

[11]  L. Baker,et al.  Optimisation of pedotransfer functions using an artificial neural network ensemble method , 2008 .

[12]  Clive Fox,et al.  North Sea cod and climate change – modelling the effects of temperature on population dynamics , 2003 .

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

[14]  Walter J. Rawls,et al.  Field‐Scale Water Flow Simulations Using Ensembles of Pedotransfer Functions for Soil Water Retention , 2006 .

[15]  Kishan G. Mehrotra,et al.  Efficient classification for multiclass problems using modular neural networks , 1995, IEEE Trans. Neural Networks.

[16]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Andrew P. Morse,et al.  Malaria early warnings based on seasonal climate forecasts from multi-model ensembles , 2006, Nature.

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

[19]  Jonathan J. Gourley,et al.  A method for identifying sources of model uncertainty in rainfall-runoff simulations , 2004 .

[20]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[21]  Amanda J. C. Sharkey,et al.  Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems , 1999 .

[22]  Amin Elshorbagy,et al.  Estimating Saturated Hydraulic Conductivity In Spatially Variable Fields Using Neural Network Ensembles , 2006 .

[23]  Young-Oh Kim,et al.  Rainfall‐runoff models using artificial neural networks for ensemble streamflow prediction , 2005 .

[24]  F. Zwiers,et al.  Climate Predictions with Multimodel Ensembles , 2002 .

[25]  F.J Doblas-Reyes,et al.  Probabilistic prediction of climate using multi-model ensembles: from basics to applications , 2005, Philosophical Transactions of the Royal Society B: Biological Sciences.

[26]  Budiman Minasny,et al.  On digital soil mapping , 2003 .

[27]  T. N. Krishnamurti,et al.  Improved Weather and Seasonal Climate Forecasts from Multimodel Superensemble. , 1999, Science.

[28]  Colin McCormack.  Adaptation of Learning Rule Parameters Using a Meta Neural Network , 1997, Connect. Sci..

[29]  Renate Hagedorn,et al.  The rationale behind the success of multi-model ensembles in seasonal forecasting — I. Basic concept , 2005 .

[30]  B. Efron.  Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation , 1983 .

[31]  Yonglong Wang,et al.  Active learning based on a hybrid neural network modeller , 1998 .

[32]  M. Schaap,et al.  ROSETTA: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions , 2001 .

[33]  Masami Ito,et al.  Task decomposition and module combination based on class relations: a modular neural network for pattern classification , 1999, IEEE Trans. Neural Networks.

[34]  Dong-Jun Seo,et al.  Towards the characterization of streamflow simulation uncertainty through multimodel ensembles , 2004 .

[35]  Fuqing Zhang,et al.  Ensemble-based data assimilation and targeted observation of a chemical tracer in a sea breeze model , 2007 .

[36]  Marcel G. Schaap,et al.  Functional evaluation of pedotransfer functions derived from different scales of data collection , 2003 .

[37]  B. Grofman.  Information Pooling and Group Decision Making , 1986 .

[38]  James Surowiecki.  The wisdom of crowds: Why the many are smarter than the few and how collective wisdom shapes business, economies, societies, and nations Doubleday Books. , 2004 .