Improving the accuracy of objective classification and spatiotemporal forecasting of severe convective weather has always been a challenge in meteorological forecasting. This paper integrates mesoscale models with machine learning classification algorithms to achieve hourly forecasts of classified severe convection. The specific algorithm is as follows: First, the XGBoost classification algorithm and over 10 years of historical data are used to establish a classification potential forecast model for severe convection. Secondly, by statistically analyzing the optimal spatial neighborhood radius and probability density distribution characteristics of CMA-SH9 model elements, and extracting element thresholds based on the combination of optimal scores, a spatial neighborhood graded element ingredient model is established. Finally, through joint discrimination, the machine learning classification method and the spatial neighborhood element "ingredient method" are integrated to establish hourly forecast models for thunderstorm gales and short-term heavy rainfall. Validation shows that this fusion algorithm significantly outperforms numerical model forecast results and national guidance products. For short-term heavy rainfall forecasts on an hourly basis over 24 hours during 2021-2022, the average hit rate is 0.51, and the TS (Threat Score) is 0.15, representing improvements of 83% and 33% respectively compared to the model. For thunderstorm gale forecasts on an hourly basis over 24 hours, the average hit rate reaches 0.37, and the TS is 0.07, representing improvements of 67% and 130% respectively compared to the model (reflectivity factor Z ≥ 45dBz).Significantly improved the forecast accuracy of thunderstorm gale.