An effective downscaling model for operational prediction of summer precipitation over China

Abstract

A hybrid downscaling model for operational prediction of summer precipitation at 160 stations over China is proposed in this paper. The prediction model is conducted in February, and six predictors extending from the tropics to high latitudes with specific mechanisms are involved. Simultaneous sea level pressure over pan-East Asia and spring sea surface temperature (SST) over the tropical Atlantic Ocean are from the Climate Forecast System version 2 (CFSv2). The others are observational predictors including winter SST over the tropical Indian Ocean, sea ice concentration (SIC) over the Hudson Bay–Baffin Bay–Davis Strait in winter and the Barents–Kara Sea in autumn, and winter outgoing longwave radiation over the tropics. Different predictors impact the summer precipitation of different regions in China. Validations for schemes based on individual predictors (IP-schemes) and all predictors (HD-scheme) indicate that downscaling schemes outperform CFSv2 in predicting summer precipitation over China, especially the HD-scheme. The temporal and spatial anomaly correlation coefficient, root-mean-square errors, and ratio of the same sign (RSS) are estimated. For RSS (Anomalous RSS), the results are improved from 27.8% (23.8%) for CFSv2 to 77.8% (61.9%) for HD-scheme. Notably, the RSSs of IP-schemes based on SIC are equivalent to that of HD-scheme. This partly emphasizes the importance of preceding Arctic sea ice to summer rainfall in China. Moreover, two cases from hindcasts and two from the operational application are chosen for further validation of the prediction skill of HD-scheme. The case studies confirm that the hybrid downscaling model proposed in this paper not only outperforms CFSv2 but can also be applied well to real-time forecasting of summer precipitation over China.