Forecasting the western Pacific subtropical high index during typhoon activity using a hybrid deep learning model

Seasonal location and intensity changes in the western Pacific subtropical high(WPSH)are important factors dominating the synoptic weather and the distribution and magnitude of precipitation in the rain belt over East Asia.Therefore,this article delves into the forecast of the western Pacific subtropical high index during typhoon activity by adopting a hybrid deep learning model.Firstly,the predictors,which are the inputs of the model,are analysed based on three characteristics:the first is the statistical discipline of the WPSH index anomalies corresponding to the three types of typhoon paths;the second is the correspondence of distributions between sea surface temperature,850 hPa zonal wind(u),meridional wind(v),and 500 hPa potential height field;and the third is the numerical sensitivity experiment,which reflects the evident impact of variations in the physical field around the typhoon to the WPSH index.Secondly,the model is repeatedly trained through the backward propagation algorithm to predict the WPSH index using 2011–2018 atmospheric variables as the input of the training set.The model predicts the WPSH index after 6 h,24 h,48 h,and 72 h.The validation set using independent data in 2019 is utilized to illustrate the performance.Finally,the model is improved by changing the CNN2D module to the DeCNN module to enhance its ability to predict images.Taking the 2019 typhoon“Lekima”as an example,it shows the promising performance of this model to predict the 500 hPa potential height field.

Temporal and Spatial Distributions of the Spring Persistent Rains over Southeastern China

The spring persistent rains （SPR） over southeastern China （SEC） is a synoptic and climatic phenomenon that is unique in East Asia. Sufficient evidence proves that it results from the mechanical and thermal effects of the giant Tibetan Plateau （TP）, but its temporal span and spatial distribution are not clear at present. A climatological analysis of the NCEP/NCAR circulation and sensible heat data shows that at the 13th pentad of the solar year （lst pentad of March） there are remarkable increases in the sensible heating over the main and southeastern part of the TP, the southwesterly velocity over the southeastern flank of the TP and SEC, and rainfall over SEC, indicating the onset of the SPR. However, after the 27th pentad of the solar year （3rd pentad of May）, these variables, except for the sensible heating over the main part of the TP, decrease rapidly. The ridge line of the subtropical high in the mid-low troposphere over the South China Sea （SCS） slopes northward to the SCS and the SCS monsoon instead of southward as before breaks out, indicating the end The rain belt center over SEC shifts of the SPR. Hence, it is reasonable to define the SPR temporal span from the 13th to 27th pentad of the solar year. Data analysis and numerical sensitivity experiments show that, although the warm and cold airs converge at about 30°N in the SPR period, the distribution and intensity of the SPR rain belt are obviously influenced by the topography of the Nanling and Wuyi Mountains （NWM）. The mountains can block and lift cold and warm airs, strengthening frontogenesis and rainfall. As a result, the axis of the SPR rain belt is superposed over that of the mountain range. Accordingly, the spatial distribution of the SPR extends over most of the SEC, more specifically, to the south of the middle and lower reaches of the Yangtze River （30°N）, and to the east of 110°E.