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 (SST), 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.