HeidkeSkillScore(fordeterministiccategoricalforecasts)：Heidke技巧评分（确定性分类预测）.pptVIP

* Heidke Skill Score (for deterministic categorical forecasts) Heidke score = Example: Suppose for OND 1997, rainfall forecasts are made for 15 stations in southern Brazil. Suppose forecast is defined by tercile-based category having highest probability. Suppose for all 15 stations, “above” is forecast with highest probability, and that observations were above normal for 12 stations, and near normal for 3 stations. Then Heidke score is: 100 X (12 – 15/3) / (15 – 15/3) 100 X 7 / 10 = 70 Note that the probabilities given in the forecasts did not matter, only which category had highest probability. Verification of climate predictions Verification of climate predictions Mainland United States The Heidke skill score (a “hit score”) Credit/Penalty matrix for some Variations of the Heidke Skill Score 1 (0.67) 0 (-0.33) 0 (-0.33) Above 0 (-0.33) 1 (0.67) 0 (-0.33) Near 0 (-0.33) 0 (-0.33) 1 (0.67) Below Above Near Below F O R E C A S T 1.125 0 -1.125 Above -0.375 0.750 -0.375 Near -1.125 0 1.125 Below Above Near Below 0.89 -0.11 -0.78 Above -0.11 0.22 -0.11 Near -0.78 -0.11 0.89 Below Above Near Below O B S E R V A T I O N O B S E R V A T I O N O B S E R V A T I O N Original Heidke score (Heidke, 1926 [in German]) for terciles LEPS (Potts et al., J. Climate, 1996) for terciles As modified in Barnston (Wea. and Forecasting, 1992) for terciles Root-mean-Square Skill Score: RMSSS for continuous deterministic forecasts RMSSS is defined as: where: RMSEf = root mean square error of forecasts, and RMSEs = root mean square error of standard used as no-skill baseline. Both persistence and climatology can be used as baseline. Persistence, for a given parameter, is the persisted anomaly from the forecast period immediately prior to