Intraseasonal oscillation of the evaporation duct, lasting 30–60 days, has been identified over the South China Sea (SCS) summer monsoon region based on multiple reanalyses and observational data. The boreal summer intraseasonal oscillation (BSISO) causes anomalies at the air–sea boundary and thus plays a dominant role in modulating the variation of the evaporation duct. The height and strength of the duct enhance/suppress during the negative/positive phase of the BSISO over the SCS. This results from the fact that active BSISO convection reduces solar radiation reaching the sea surface by increasing cumulus cloud cover, whereupon precipitation and water vapor transported by the enhanced southwest jet increase humidity over the air–sea boundary. Reduced air–sea temperatures and humidity differences lead to a weaker evaporation duct. Usually, the temporal evolution of the evaporation duct lags 2–4 days behind the BSISO, with the center of evaporation duct anomalies farther south than the BSISO. Simulated electromagnetic fields substantively influence the condition of the evaporation duct, with obvious over-the-horizon and radar blind spot effects in the typical negative phase of the BSISO, which is very different from standard atmospheric conditions.

Against the backdrop of global warming, extreme precipitation events have become more frequent. In complex terrain regions, due to the vulnerability of their ecosystems, extreme precipitation events can lead to significant secondary disasters. Utilizing daily rainfall data from the National Meteorological Information Center of China and statistical analysis, this study explores the spatial and temporal distribution of extreme precipitation in the Central Southwest China (CSC) region. The temporal pattern of extreme precipitation in CSC shows a consistent trend, while the spatial distribution reveals an opposite phase between the northern and southern parts of CSC. Based on this, we propose a new method for constructing extreme precipitation prediction models for complex terrain regions based on physical mechanisms, and take CSC area as a study case. Instead of anonymous feature selection, this method improves the accuracy and stability of the model by studying the impact of sea–air interactions on extreme precipitation and then introducing it into deep learning. It was found that the sea surface temperature (SST) anomaly in the South Indian Ocean affects extreme precipitation in the CSC by influencing uplift, atmospheric instability, and moisture. The SST anomaly also affects the intensity of cross-equatorial airflow, which changes the trajectory of the Pacific–Japan teleconnection wave and impacts extreme precipitation. These findings provide a comprehensive and reliable approach for forecasting extreme precipitation in CSC and are further integrated into the extreme precipitation prediction models.