Accurate drought prediction is important for drought resistance and water resources management. However, the seasonal drought prediction is of low accuracy for both dynamical and statistical models. In this study, we combined dynamical models and machine learning to construct hybrid (dynamical-statistical) models. We used the random forest approach to identify representative regions based on geopotential height, sea-level pressure, and 2-m temperature. The least absolute shrinkage and selection operator (Lasso and an artificial neural network (ANN) were used to construct the statistical models, with atmospheric variables as predictors and 3-month Standardized Precipitation Index (SPI3) as the predictand. The atmospheric variables forecasted by the European Centre for Medium-Range Weather Forecasts (ECMWF) SEAS5 model were processed as predictors to force the statistical models. The resulting hybrid models, constructed using dynamical models and machine learning, were named as dynamic-Lasso (‘D-Lasso’) and dynamic-ANN (‘D-ANN’) separately. The results suggested that prediction skills were improved by the hybrid models; compared to the best available dynamical model (UK Met Office), D-ANN extends the forecast horizons by 6, 21, and 4 days in northern, eastern, and southern China, respectively. In spring and summer, the correlation skills were also improved. The effective prediction of the atmospheric anomalies over the eastern and southern Tibetan Plateau and the Northwest Pacific region was identified as the main contributor to successful seasonal drought prediction. Overall, the hybrid models were able to predict drought processes effectively, and D-ANN outperformed the D-Lasso in drought onset and persistence phases.