资源环境科技发展态势分析平台

During the last few decades, weather circulation type classifications (CTCs) have been widely used to gain insight into processes at the synoptic scale, but also for studying the relationship between atmospheric circulation and surface climate variability. This study aims to evaluate the best performing CTCs based on COST733 software for the stratification of daily ground-level precipitation and surface air temperature across Italy by means of four statistical metrics. Six classification methods belonging to the four COST733 groups (threshold-based, PCA-based, leader algorithms and optimization algorithms) were investigated on 32 and 26 data time series derived from Italian weather stations for daily mean temperature and daily mean precipitation, respectively. CTCs were computed using gridded mean sea level pressure and geopotential height at 500hPa derived from the NCEP Reanalysis 2 dataset between 1979 and 2015 and tested on three different numbers of classes (8/9, 11/12 and 18 circulation types). Evaluation metrics showed an evident seasonal variability and high-spatial heterogeneity reflecting the geographical complexity of the Italian territory. The study points out that the best classification, both for temperature and precipitation, is strongly dependent on the classification variable (mean sea level pressure and geopotential height at 500hPa) showing relevant differences between surface temperature and precipitation. A low number of circulation types (8/9) resulted as the most appropriate grouping for the Italian domain and the Principal Component Transversal and Simulated Annealing were the best performing classification procedures for ground-level precipitation and temperature stratification, respectively.