Seeking Consensus: A New Approach

Abstract Simulated evolution is used to generate consensus forecasts of next-day minimum temperature for a site in Ohio. The evolved forecast algorithm logic is interpretable in terms of physics that might be accounted for by experienced forecasters, but the logic of the individual algorithms that form the consensus is unique. As a result, evolved program consensus forecasts produce substantial increases in forecast accuracy relative to forecast benchmarks such as model output statistics (MOS) and those from the National Weather Service (NWS). The best consensus produces a mean absolute error (MAE) of 2.98°F on an independent test dataset, representing a 27% improvement relative to MOS. These results translate to potential annual cost savings for electricity production in the state of Ohio of the order of $2 million relative to the NWS forecasts. Perfect forecasts provide nearly $6 million in additional annual electricity production cost savings relative to the evolved program consensus. The frequency of ...

[1]  Thomas M. Hamill,et al.  Verification of Eta–RSM Short-Range Ensemble Forecasts , 1997 .

[2]  R. Stull,et al.  Evaluation of Probabilistic Medium-Range Temperature Forecasts from the North American Ensemble Forecast System. , 2009 .

[3]  Paul J. Roebber,et al.  Does Distance from the Forecast Site Affect Skill , 1996 .

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

[5]  Lance F. Bosart.  Whither the Weather Analysis and Forecasting Process , 2003 .

[6]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[7]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[8]  F. Sanders,et al.  Skill In Forecasting Daily Temperature and Precipitation: Some Experimental Results , 1973 .

[9]  Paul J. Roebber,et al.  Synoptic regulation of the 3 May 1999 tornado outbreak , 2002 .

[10]  D. Richardson.  Skill and relative economic value of the ECMWF ensemble prediction system , 2000 .

[11]  Chris Snyder,et al.  Mesoscale Predictability of the “Surprise” Snowstorm of 24–25 January 2000 , 2002 .

[12]  Cândida Ferreira,et al.  Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence , 2014, Studies in Computational Intelligence.

[13]  B. M. Lewis,et al.  OBJECTIVE PREDICTION OF FIVE-DAY MEAN TEMPERATURES DURING WINTER , 1959 .

[14]  B. Hobbs,et al.  Analysis of the value for unit commitment of improved load forecasts , 1999 .

[15]  Zoltan Toth,et al.  A Synoptic Evaluation of the NCEP Ensemble , 1997 .

[16]  L. Bosart,et al.  The Complex Relationship between Forecast Skill and Forecast Value: A Real-World Analysis , 1996, Weather and Forecasting.

[17]  J. Whitaker,et al.  REFORECASTS An Important Dataset for Improving Weather Predictions , 2006 .

[18]  Frederick Sanders.  Trends in Skill of Daily Forecasts of Temperature and Precipitation, 1966–78 , 1979 .

[19]  David S. Richardson,et al.  ON THE ECONOMIC VALUE OF ENSEMBLE BASED WEATHER FORECASTS , 2001 .

[20]  Eugenia Kalnay,et al.  Atmospheric Modeling, Data Assimilation and Predictability , 2002 .

[21]  Alireza Khotanzad,et al.  The Economic Value of Temperature Forecasts in Electricity Generation , 2005 .

[22]  Robert L. Vislocky,et al.  Performance of an Advanced MOS System in the 1996–97 National Collegiate Weather Forecasting Contest , 1997 .

[23]  Roland B. Stull,et al.  Deterministic Ensemble Forecasts Using Gene-Expression Programming* , 2009 .

[24]  Clifford F. Mass,et al.  IFPS and the Future of the National Weather Service , 2003 .

[25]  Thomas M. Hamill,et al.  Ensemble Calibration of 500-hPa Geopotential Height and 850-hPa and 2-m Temperatures Using Reforecasts , 2007 .

[26]  Robert L. Vislocky,et al.  Improved Model Output Statistics Forecasts through Model Consensus , 1995 .

[27]  John R. Gyakum.  Experiments in Temperature and Precipitation Forecasting for Illinois , 1986 .

[28]  J. McGinley,et al.  Diagnosis and Optimization of Ensemble Forecasts , 2008 .

[29]  Lance F. Bosart.  SUNYA Experimental Results in Forecasting Daily Temperature and Precipitation , 1975 .

[30]  Enric Valor,et al.  Daily Air Temperature and Electricity Load in Spain , 2001 .

[31]  P. D. Thompson,et al.  How to Improve Accuracy by Combining Independent Forecasts , 1977 .

[32]  Mark A. Liniger,et al.  Can multi‐model combination really enhance the prediction skill of probabilistic ensemble forecasts? , 2007 .

[33]  Harold E. Brooks,et al.  Using Ensembles for Short-Range Forecasting , 1999 .

[34]  Candida Ferreira.  Gene expression programming , 2006 .

[35]  Renate Hagedorn,et al.  Probabilistic Forecast Calibration Using ECMWF and GFS Ensemble Reforecasts. Part I: Two-Meter Temperatures , 2008 .