By constructing a correlation network between global sea surface temperature anomalies (SSTAs) and summer precipitation anomalies in the Yunnan–Guizhou Plateau, key SST regions influencing summer precipitation anomalies in the Yunnan–Guizhou Plateau were selected. It was found that spring SSTAs in the Bay of Bengal, southwestern Atlantic, and eastern Pacific are crucial for influencing summer precipitation anomalies in the Yunnan–Guizhou Plateau. Setting SSTAs from these three regions as predictor variables 3 months in advance, we constructed multiple linear regression (MLR), ridge regression (RR), and lasso regression (LR) models to predict summer precipitation anomalies over the Yunnan–Guizhou region. The training phase involved data spanning from 1961 to 2005, which aimed to predict precipitation anomalies in the Yunnan–Guizhou Plateau for the period extending from 2006 to 2022. Based on MLR, RR, and LR models, the correlations between predicted values and observed summer precipitation anomalies in Yunnan–Guizhou were 0.48, 0.46, and 0.46, respectively. These values were all higher than the correlation coefficients of the NCC_CSM model’s predicted and observed values. Additionally, its performance in predicting summer precipitation anomalies over the Yunnan–Guizhou region, based on key SST regions, was assessed using performance metrics such as anomaly correlation coefficient (ACC), anomaly sign consistency rate (PC), and trend anomaly comprehensive score (PS score). The average ACC of MLR, RR, and LR models was higher than that of the NCC_CSM model’s predictions. For MLR, RR, LR, and NCC_CSM models, the PCs exceeding 50% of the year were 14, 14, 11, and 10, respectively. Furthermore, the average PS score for predicting summer precipitation anomalies over the Yunnan–Guizhou region using MLR, RR, and LR was approximately 73 points; 8 higher than the average PS score of the NCC_CSM model. Therefore, predicting summer precipitation anomalies over the Yunnan–Guizhou region based on key SST regions is of great significance for improving the prediction skills of precipitation anomalies in this region.

The application of sub-seasonal prediction error analysis and interpretation remains a key research frontier of climate prediction. Related studies are essential for deepening the understanding of model performance, investigating error sources, and improving model prediction accuracy. Based on four perspectives—basic characteristics, spatial and temporal consistency, and potential causes of prediction errors—this study systematically investigates the sub-seasonal hindcast errors of summer precipitation over China from the state-of-the-art model system BCC–CPS–S2Sv2 (S2Sv2). The findings reveal that (1) S2Sv2 shows significant prediction skill in the first three pentads and shows an obvious increase in RMSE and a decrease in SCC of the precipitation prediction. This feature is quite similar to other operational models. (2) The prediction error primarily presents typical modes such as the meridional dipole, triple or consistent patterns. Prediction errors maintain spatial consistency in South China, the middle and lower reaches of the Yangtze River, and North China. Temporal consistency of the prediction errors shows a significant correlation between neighboring pentads, which diminishes as the prediction period extends, with a better correlation lasting for 2–4 pentads in some areas. (3) The prediction errors of S2Sv2 are significantly correlated with major circulation patterns in East Asia and key area sea surface temperatures (SSTs). For instance, errors are larger when the West Pacific Subtropical High is stronger, but smaller when the East Asia Trough is stronger. Errors also decrease with higher SSTs in the central equatorial Pacific and increase with higher SSTs in the tropical North Atlantic. This study provides valuable insights into the limitations of the S2Sv2 model and offers important references for error correction and model application.