A Statistical-Dynamical Scheme for the Extraseasonal Prediction of Summer Rainfall for 160 Observation Stations across China

The purpose of this study was to design and test a statistical--dynamical scheme for the extraseasonal (one season in advance) prediction of summer rainfall at 160 observation stations across China. The scheme combined both valuable information from the preceding observations and dynamical information from synchronous numerical predictions of atmospheric circulation factors produced by an atmospheric general circulation model. First, the key preceding climatic signals and synchronous atmospheric circulation factors that were not only closely related to summer rainfall but also numerically predictable were identified as the potential predictors. Second, the extraseasonal prediction models of summer rainfall were constructed using a multivariate linear regression analysis for 15 subregions and then 160 stations across China. Cross-validation analyses performed for the period 1983--2008 revealed that the performance of the prediction models was not only high in terms of interannual variation, trend, and sign but also was stable during the whole period. Furthermore, the performance of the scheme was confirmed by the accuracy of the real-time prediction of summer rainfall during 2009 and 2010.