Search

By observing well‐known sea surface temperature (SST) indices and outputs from Climate Forecast System version 2 (CFSv2) hindcasts and predictions, in this study, we developed a hybrid statistical downscaling prediction model (HSDPM) based on a timescale decomposition approach, which effectively improved the forecasting ability of summer (June–August) precipitation over Hainan Island (HNSP) in China; this precipitation presented multiple obvious timescale variabilities. We found that the interannual variability of the HNSP is closely related to the observed North Atlantic tripole SST anomalies in the preceding winter and the summer sea level pressure over the South China Sea by CFSv2 predicted in March. On the other hand, the interdecadal variability in the HNSP is linked to the prewinter Pacific Interdecadal Oscillation (PDO) according to the observations, the CFSv2 predictions of the summer surface air temperature over the tropical central‐east Pacific. On this basis, both the interannual and interdecadal components of the HNSP are effectively predicted using the corresponding predictors via multiple regression; thus, the HSDPM is ultimately established by combining the above two components. Compared with the original CFSv2 model, the HSDPM model achieves a considerable improvement in performance in predicting the HNSP. Specifically, the temporal correlation coefficient, ratio of root‐mean‐square error and anomaly sign consistency rate between the observed and HSDPM‐predicted HNSPs are 0.70, 17.4% and 80.5%, respectively, which are significantly greater than the above three forecasting index values of 0.23, 38.3% and 48.8%, respectively, obtained from the original CFSv2 predictions. The application of the HSDPM may be beneficial for drought and flood prevention and mitigation in Hainan Island. [ABSTRACT FROM AUTHOR]

Accurate short-term climate predictions, specifically the prediction of dominant rain belts during flood seasons, represent a significant challenge, particularly in the absence of notable external forcing signal anomalies in the previous winter. To address this challenge, we propose a novel climate index based on an Auto-Encoder (AE) Neural Network that exhibits superior performance in indicating several significant precipitation events in the Yangtze and Huaihe River Basins under varying El Niño conditions. Notably, the novel climate index rectifies the discrepancy between the 2019/2020 Niño index and the 2020 summer precipitation. In order to understand the information source of AE, the causality between AE and other indices was further analyzed by Granger Causality. The results show that AE index mainly contains the information of subtropical high index and ocean index, which is consistent with previous studies. • AE obtained by Auto-encoder can make up for the "failure" of Nino index in abnormally heavy precipitation events. • In terms of magnitude and state, AE has better description of precipitation than Nino3.4. • The main indices of AE information are subtropical high-pressure index and sea surface temperature index. [ABSTRACT FROM AUTHOR]