Long-Range Niño-3.4 Predictions Using Pairwise Dynamic Combinations of Multiple Models

Journal of Climate - Tập 22 Số 3 - Trang 793-805 - 2009
Shahadat Chowdhury1, Ashish Sharma1
1School of Civil and Environmental Engineering, University of New South Wales, Sydney, Australia

Tóm tắt

Abstract The interest in climate prediction has seen a rise in the number of modeling alternatives in recent years. One way to reduce the predictive uncertainty from any such modeling procedure is to combine or average the modeled outputs. Multiple model results can be combined such that the combination weights may either be static or vary over time. This research develops a methodology for combining forecasts from multiple models in a dynamic setting. The authors mix models on a pairwise basis using importance weights that vary in time, reflecting the persistence of individual model skills. Such an approach is referred to here as a dynamic pairwise combination tree and is presented as an improvement over the case where the importance weights are static or constant over time. The pairwise importance weight is modeled as a product of a “mixture ratio” and a “bias direction,” the former representing the fraction of the absolute residual error associated with each of the paired models, and the latter representing an indicator of the sign of the two residual errors. The mixture ratio is modeled using a generalized autoregressive model and the bias direction using ordered logistic regression. The method is applied to combine three climate models, the variables of interest being the monthly sea surface temperature anomalies averaged over the Niño-3.4 region from 1956 to 2001. The authors test the combined model skill using a “leave ± 6 months out cross-validation” approach along with validation in 10-yr blocks. This study attained a small but consistent improvement of the predictive skill of the dynamically combined models compared to the existing practice of static weight combination.

Từ khóa


Tài liệu tham khảo

Agresti, 1996, An Introduction to Categorical Data Analysis.

Aksu, 1992, An empirical analysis of the accuracy of SA, OLS, ERLS and NRLS combination forecasts., Int. J. Forecasting, 8, 27, 10.1016/0169-2070(92)90005-T

Armstrong, 1989, Combining forecasts: The end of the beginning or the beginning of the end?, Int. J. Forecasting, 5, 585, 10.1016/0169-2070(89)90013-7

Armstrong, 2001, Combining forecasts., 10.1007/978-0-306-47630-3_19

Barnston, 2003, Multimodel ensembling in seasonal climate forecasting at IRI., Bull. Amer. Meteor. Soc., 84, 1783, 10.1175/BAMS-84-12-1783

Bates, 1969, The combination of forecasts., Oper. Res. Quart., 20, 451, 10.1057/jors.1969.103

Bottomley, 1990, Global Ocean Surface Temperature Atlas.

Carrasco, 2002, Review and assessment of the nested logit model., Transp. Rev., 22, 197, 10.1080/01441640110091224

Chambers, 1992, Linear models.

Chandler, 2005, On the use of generalized linear models for interpreting climate variability., Environmetrics, 16, 699, 10.1002/env.731

Clemen, 1989, Combining forecasts: A review and annotated bibliography., Int. J. Forecasting, 5, 559, 10.1016/0169-2070(89)90012-5

Cleveland, 1979, Robust locally weighted regression and smoothing scatterplots., J. Amer. Stat. Assoc., 74, 829, 10.1080/01621459.1979.10481038

Cleveland, 1988, Regression by local fitting: Methods, properties, and computational algorithms., J. Econometrics, 37, 87, 10.1016/0304-4076(88)90077-2

Coelho, 2004, Forecast calibration and combination: A simple Bayesian approach for ENSO., J. Climate, 17, 1504, 10.1175/1520-0442(2004)017<1504:FCACAS>2.0.CO;2

Colman, 2003, Statistical prediction of global sea-surface temperature anomalies., Int. J. Climatol., 23, 1677, 10.1002/joc.956

Dawes, 1994, The past and the future of forecasting research., Int. J. Forecasting, 10, 151, 10.1016/0169-2070(94)90057-4

de Gooijer, 2006, 25 years of time series forecasting., Int. J. Forecasting, 22, 443, 10.1016/j.ijforecast.2006.01.001

de Menezes, 2000, Review of guidelines for the use of combined forecasts., Eur. J. Oper. Res., 120, 190, 10.1016/S0377-2217(98)00380-4

Deutsch, 1994, The combination of forecasts using changing weights., Int. J. Forecasting, 10, 47, 10.1016/0169-2070(94)90049-3

Doblas-Reyes, 2005, The rationale behind the success of multi-model ensembles in seasonal forecasting: II. Calibration and combination., Tellus, 57A, 234

Dunteman, 2006, An Introduction to Generalized Linear Models., 10.4135/9781412983273

Ferrari, 2004, Beta regression for modelling rates and proportions., J. Appl. Stat., 31, 799, 10.1080/0266476042000214501

Fraedrich, 1989, Combining predictive scheme in long-range forecasting., J. Climate, 2, 291, 10.1175/1520-0442(1989)002<0291:CPSILR>2.0.CO;2

Fritsch, 2000, Model consensus., Wea. Forecasting, 15, 571, 10.1175/1520-0434(2000)015<0571:MC>2.0.CO;2

Gelman, 2006, Data Analysis Using Regression and Multilevel/Hierarchical Models., 10.1017/CBO9780511790942

Granger, 1977, Forecasting Economic Time Series.

Greene, 2006, Probabilistic multimodel regional temperature change projections., J. Climate, 19, 4326, 10.1175/JCLI3864.1

Hastie, 1986, Generalized additive models., Stat. Sci., 1, 297, 10.1214/ss/1177013604

Hastie, 1992, Generalised linear models.

Hastie, 2000, The Elements of Statistical Learning, Data Mining, Inference and Prediction.

Hibon, 2005, To combine or not to combine: Selecting among forecasts and their combinations., Int. J. Forecasting, 21, 15, 10.1016/j.ijforecast.2004.05.002

Hoeting, 1999, Bayesian model averaging: A tutorial (with discussion)., Stat. Sci., 14, 382

Kamstra, 1998, Combining qualitative forecasts using logit., Int. J. Forecasting, 14, 83, 10.1016/S0169-2070(97)00056-3

Kim, 2006, Combining rainfall-runoff model outputs for improving ensemble streamflow prediction., J. Hydrol. Eng., 11, 578, 10.1061/(ASCE)1084-0699(2006)11:6(578)

Kondrashov, 2005, A hierarchy of data-based ENSO models., J. Climate, 18, 4425, 10.1175/JCLI3567.1

Lall, 1996, A nearest neighbor bootstrap for time series resampling., Water Resour. Res., 32, 679, 10.1029/95WR02966

Lall, 2006, Locally weighted polynomial regression: Parameter choice and application to forecasts of the Great Salt Lake., Water Resour. Res., 42, W05422, 10.1029/2004WR003782

Larrick, 2006, Intuitions about combining opinions: Misappreciation of the averaging principle., Manage. Sci., 52, 111, 10.1287/mnsc.1050.0459

Lundberg, 2003, Time-varying smooth transition autoregressive models., J. Business Econ. Stat., 21, 104, 10.1198/073500102288618810

Marshall, L. A. , 2006: Bayesian analysis of rainfall-runoff models: Insights to parameter estimation, model comparison and hierarchical model development. Ph.D. thesis, School of Civil and Environmental Engineering, University of New South Wales, 222 pp.

Marshall, 2007, Towards dynamic catchment modelling: A Bayesian hierarchical modelling framework., Hydrol. Processes, 21, 847, 10.1002/hyp.6294

McCullagh, 1989, Generalized Linear Models., 10.1007/978-1-4899-3242-6

McLeod, 1987, Combining hydrologic forecast., J. Water Resour. Plann. Manage., 113, 29, 10.1061/(ASCE)0733-9496(1987)113:1(29)

Mehrotra, 2006, Conditional resampling of hydrologic time series using multiple predictor variables: A K-nearest neighbour approach., Adv. Water Resour., 29, 987, 10.1016/j.advwatres.2005.08.007

Palmer, 2004, Development of a European multimodel ensemble system for seasonal-to-interannual prediction (DEMETER)., Bull. Amer. Meteor. Soc., 85, 853, 10.1175/BAMS-85-6-853

Pavan, 2000, Multi-model seasonal hindcasts over the Euro-Atlantic: Skill scores and dynamic features., Climate Dyn., 16, 611, 10.1007/s003820000063

Peng, 2002, An analysis of multimodel ensemble predictions for seasonal climate anomalies., J. Geophys. Res., 107, 4710, 10.1029/2002JD002712

Phillips-Wren, 2004, A multiple-criteria framework for evaluation of decision support systems., Omega, 32, 323, 10.1016/j.omega.2004.01.003

Raftery, 2005, Using Bayesian model averaging to calibrate forecast ensembles., Mon. Wea. Rev., 133, 1155, 10.1175/MWR2906.1

Ragonda, 2006, A multimodel ensemble forecast framework: Application to spring seasonal flows in the Gunnison River Basin., Water Resour. Res., 42, W09404

Rajagopalan, 2002, Categorical climate forecasts through regularization and optimal combination of multiple GCM ensembles., Mon. Wea. Rev., 130, 1792, 10.1175/1520-0493(2002)130<1792:CCFTRA>2.0.CO;2

Robertson, 2004, Improved combination of multiple atmospheric GCM ensembles for seasonal prediction., Mon. Wea. Rev., 132, 2732, 10.1175/MWR2818.1

Sanders, 1963, On subjective probability forecasting., J. Appl. Meteor., 2, 191, 10.1175/1520-0450(1963)002<0191:OSPF>2.0.CO;2

See, 2001, Multi-model data fusion for hydrological forecasting., Comput. Geosci., 27, 987, 10.1016/S0098-3004(00)00136-9

Shamseldin, 1997, Methods for combining the outputs of different rainfall-runoff models., J. Hydrol., 197, 203, 10.1016/S0022-1694(96)03259-3

Sharma, 2000, Seasonal to interannual rainfall probabilistic forecasts for improved water supply management: Part 1—A strategy for system predictor identification., J. Hydrol., 239, 232, 10.1016/S0022-1694(00)00346-2

Sharma, 1999, A nonparametric approach for daily rainfall simulation., Math. Comput. Simul., 48, 361, 10.1016/S0378-4754(99)00016-6

Sharma, 2004, Model averaging and its use in probabilistic forecasting of hydrologic variables.

Shephard, 1995, Generalized linear autoregressions.

Smith, 2003, Extended reconstruction of global sea surface temperatures based on COADS data (1854–1997)., J. Climate, 16, 1495, 10.1175/1520-0442-16.10.1495

Terui, 2002, Combined forecasts from linear and nonlinear time series models., Int. J. Forecasting, 18, 421, 10.1016/S0169-2070(01)00120-0

Thompson, 1977, How to improve accuracy by combining independent forecast., Mon. Wea. Rev., 105, 228, 10.1175/1520-0493(1977)105<0228:HTIABC>2.0.CO;2

Van den Dool, 2000, Constructed analogue prediction of the east central tropical Pacific SST and the entire world ocean for 2001., Exp. Long-Lead Forecast Bull., 9, 38

Xiong, 2001, A non-linear combination of the forecasts of rainfall-runoff models by the first-order Takagi-Sugeno fuzzy system., J. Hydrol., 245, 196, 10.1016/S0022-1694(01)00349-3

Yang, 2005, Spatial-temporal rainfall simulation using generalized linear models., Water Resour. Res., 41, W11415, 10.1029/2004WR003739

Yu, 2005, A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates., Comput. Oper. Res., 32, 2523, 10.1016/j.cor.2004.06.024

Zou, 2004, Combining time series models for forecasting., Int. J. Forecasting, 20, 69, 10.1016/S0169-2070(03)00004-9

Thông tin
Thông tin xuất bản

Journal of Climate

Tập 22 Số 3

793-805

Thông tin tác giả