A Neural Network Nonlinear Multimodel Ensemble to Improve Precipitation Forecasts over Continental US

A novel multimodel ensemble approach based on learning from data using the neural network (NN) technique is formulated and applied for improving 24-hour precipitation forecasts over the continental US. The developed nonlinear approach allowed us to account for nonlinear correlation between ensemble members and to produce “optimal” forecast represented by a nonlinear NN ensemble mean. The NN approach is compared with the conservative multi-model ensemble, with multiple linear regression ensemble approaches, and with results obtained by human forecasters. The NN multi-model ensemble improves upon conservative multi-model ensemble and multiple linear regression ensemble, it (1) significantly reduces high bias at low precipitation level, (2) significantly reduces low bias at high precipitation level, and (3) sharpens features making them closer to the observed ones. The NN multi-model ensemble performs at least as well as human forecasters supplied with the same information. The developed approach is a generic approach that can be applied to other multi-model ensemble fields as well as to single model ensembles.

[1]  G. Lewicki,et al.  Approximation by Superpositions of a Sigmoidal Function , 2003 .

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

[3]  Vladimir M. Krasnopolsky,et al.  Neural network emulations for complex multidimensional geophysical mappings: Applications of neural network techniques to atmospheric and oceanic satellite retrievals and numerical modeling , 2007 .

[4]  Vladimir M. Krasnopolsky.  Reducing Uncertainties in Neural Network Jacobians and Improving Accuracy of Neural Network Emulations with NN Ensemble Approaches , 2006, IJCNN.

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

[6]  Jun Du,et al.  Short-Range Ensemble Forecasting of Quantitative Precipitation , 1997 .

[7]  T. Palmer,et al.  Stochastic representation of model uncertainties in the ECMWF ensemble prediction system , 2007 .

[8]  Alex J. Cannon,et al.  Downscaling recent streamflow conditions in British Columbia, Canada using ensemble neural network models , 2002 .

[9]  Vladimir M. Krasnopolsky,et al.  Using neural network emulations of model physics in numerical model ensembles , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[10]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[11]  Roberto Buizza,et al.  Impact of Ensemble Size on Ensemble Prediction , 1998 .

[12]  Philip J. Rasch,et al.  Development of neural network convection parameterizations for climate and NWP models using Cloud Resolving Model simulations , 2011 .

[13]  James J. Hack,et al.  A Characterization of Tropical Transient Activity in the CAM3 Atmospheric Hydrologic Cycle , 2006 .

[14]  C. M. Kishtawal,et al.  Multimodel Ensemble Forecasts for Weather and Seasonal Climate , 2000 .

[15]  R. Buizza,et al.  A Comparison of the ECMWF, MSC, and NCEP Global Ensemble Prediction Systems , 2005 .

[16]  Florian Pappenberger,et al.  The Ensemble Prediction System - Recent and Ongoing Developments , 2007 .

[17]  Paulin Coulibaly,et al.  Temporal neural networks for downscaling climate variability and extremes , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[18]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[19]  E. Ebert.  Ability of a Poor Man's Ensemble to Predict the Probability and Distribution of Precipitation , 2001 .

[20]  T. N. Krishnamurti,et al.  Ensemble Forecasting of Hurricane Tracks , 1997 .