Northern Hemisphere Sudden Stratospheric Warming and Its Downward Impact in Four Chinese CMIP6 Models

Using the World Meteorological Organization definition and a threshold-based classification technique,simulations of vortex displacement and split sudden stratospheric warmings(SSWs)are evaluated for four Chinese models(BCC-CSM2-MR,FGOALS-f3-L,FGOALS-g3,and NESM3)from phase 6 of the Coupled Model Intercomparison Project(CMIP6)with the Japanese 55-year reanalysis(JRA-55)as a baseline.Compared with six or seven SSWs in a decade in JRA-55,three models underestimate the SSW frequency by~50%,while NESM3 doubles the SSW frequency.SSWs mainly appear in midwinter in JRA-55,but one-month climate drift is simulated in the models.The composite of splits is stronger than displacements in both the reanalysis and most models due to the longer pulse of positive eddy heat flux before onset of split SSWs.A wavenumber-1-like temperature anomaly pattern(cold Eurasia,warm North America)before onset of displacement SSWs is simulated,but cold anomalies are mainly confined to North America after displacement SSWs.Although the lower tropospheric temperature also displays a wavenumber-1-like pattern before split SSWs,most parts of Eurasia and North America are covered by cold anomalies after split SSWs in JRA-55.The models have different degrees of fidelity for the temperature anomaly pattern before split SSWs,but the wavenumber-2-like temperature anomaly pattern is well simulated after split SSWs.The center of the negative height anomalies in the Pacific sector before SSWs is sensitive to the SSW type in both JRA-55 and the models.A negative North Atlantic Oscillation is simulated after both types of SSWs in the models,although it is only observed for split SSWs.

Evaluation of dimension of fractal time series with the least square method

Properties of fractional Brownian motions （fBms） have been investigated by researchers in different fields, e.g. statistics, hydrology, biology, finance, and public transportation, which has helped us better understand many complex time series observed in nature [1-4]. The Hurst exponent H （0 〈 H 〈 1） is the most important parameter characterizing any given time series F（t）, where t represents the time steps, and the fractal dimension D is determined via the relation D = 2 - H.