Improvement of climate predictions and reduction of their uncertainties using learning algorithms

Abstract. Simulated climate dynamics, initialized with observed conditions, is expected to be synchronized, for several years, with the actual dynamics. However, the predictions of climate models are not sufficiently accurate. Moreover, there is a large variance between simulations initialized at different times and between different models. One way to improve climate predictions and to reduce the associated uncertainties is to use an ensemble of climate model predictions, weighted according to their past performances. Here, we show that skillful predictions, for a decadal time scale, of the 2 m temperature can be achieved by applying a sequential learning algorithm to an ensemble of decadal climate model simulations. The predictions generated by the learning algorithm are shown to be better than those of each of the models in the ensemble, the better performing simple average and a reference climatology. In addition, the uncertainties associated with the predictions are shown to be reduced relative to those derived from an equally weighted ensemble of bias-corrected predictions. The results show that learning algorithms can help to better assess future climate dynamics.

[1]  Veronika Eyring,et al.  A Summary of the CMIP5 Experiment Design , 2010 .

[2]  W. Dewar,et al.  A multi-model superensemble algorithm for seasonal climate prediction using DEMETER forecasts , 2005 .

[3]  Vivien Mallet,et al.  Ozone ensemble forecast with machine learning algorithms , 2009 .

[4]  G. Meehl,et al.  Decadal prediction: Can it be skillful? , 2009 .

[5]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[6]  T. Krishnamurti,et al.  Improving Global Model Precipitation Forecasts over India Using Downscaling and the FSU Superensemble. Part I: 1–5-Day Forecasts , 2009 .

[7]  F. Doblas-Reyes,et al.  Multi-model seasonal hindcasts over the Euro-Atlantic: skill scores and dynamic features , 2000 .

[8]  Balaji Rajagopalan,et al.  Categorical Climate Forecasts through Regularization and Optimal Combination of Multiple GCM Ensembles , 2002 .

[9]  Tommi S. Jaakkola,et al.  Online Learning of Non-stationary Sequences , 2003, NIPS.

[10]  Karl E. Taylor,et al.  An overview of CMIP5 and the experiment design , 2012 .

[11]  Vivien Mallet,et al.  Ensemble forecast of analyses: Coupling data assimilation and sequential aggregation , 2010 .

[12]  R. Reynolds,et al.  The NCEP/NCAR 40-Year Reanalysis Project , 1996, Renewable Energy.

[13]  Thomas T. Warner,et al.  Numerical Weather and Climate Prediction , 2011 .

[14]  H. Künsch,et al.  Bayesian multi-model projection of climate: bias assumptions and interannual variability , 2009 .

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

[16]  S. Kobayashi,et al.  The JRA-25 Reanalysis , 2007 .

[17]  Manfred K. Warmuth,et al.  Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..

[18]  A. Sterl,et al.  The ERA‐40 re‐analysis , 2005 .

[19]  Hans R. Künsch,et al.  Bayesian multi-model projections of climate: generalization and application to ENSEMBLES results , 2010 .

[20]  Richard L. Smith,et al.  Bayesian Modeling of Uncertainty in Ensembles of Climate Models , 2009 .

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

[22]  Francisco J. Doblas-Reyes,et al.  Multi‐model spread and probabilistic seasonal forecasts in PROVOST , 2000 .

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

[24]  Upmanu Lall,et al.  Improved Combination of Multiple Atmospheric GCM Ensembles for Seasonal Prediction , 2004 .

[25]  Andrew P. Morse,et al.  DEVELOPMENT OF A EUROPEAN MULTIMODEL ENSEMBLE SYSTEM FOR SEASONAL-TO-INTERANNUAL PREDICTION (DEMETER) , 2004 .

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

[27]  E. Hawkins,et al.  The Potential to Narrow Uncertainty in Regional Climate Predictions , 2009 .

[28]  P. Webster,et al.  Evaluation of short‐term climate change prediction in multi‐model CMIP5 decadal hindcasts , 2012 .

[29]  P. Alpert,et al.  A new methodology for weighting high-resolution model simulations to project future rainfall in the Middle East , 2013 .

[30]  T. N. Krishnamurti,et al.  Improving Global Model Precipitation Forecasts over India Using Downscaling and the FSU Superensemble. Part II: Seasonal Climate , 2009 .

[31]  Manfred K. Warmuth,et al.  The weighted majority algorithm , 1989, 30th Annual Symposium on Foundations of Computer Science.

[32]  Hisashi Kato,et al.  Comparison of four ensemble methods combining regional climate simulations over Asia , 2011 .

[33]  M. Collins.  Ensembles and probabilities: a new era in the prediction of climate change , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[34]  Reto Knutti,et al.  The use of the multi-model ensemble in probabilistic climate projections , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[35]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[36]  Istvan Szunyogh,et al.  Predictability of Weather and Climate: Ensemble forecasting and data assimilation: two problems with the same solution? , 2006 .

[37]  T. N. Krishnamurti,et al.  Improvement of the Multimodel Superensemble Technique for Seasonal Forecasts , 2003 .

[38]  Claire Monteleoni,et al.  Tracking climate models , 2011, CIDU.

[39]  Mark Herbster,et al.  Tracking the Best Expert , 1995, Machine-mediated learning.