A winter precipitation-type prediction is a challenging problem due to the complexity in the physical mechanisms and computability in numerical modeling. In this study, we introduce a new method of precipitation-type prediction based on the machine learning approach LightGBM. The precipitation-type records of the in situ observations collected from 32 national weather stations in northern China during 1997–2018 are used as the labels. The features are selected from the conventional meteorological data of the corresponding hourly reanalysis data ERA5. The evaluation results of the model performance reflect that randomly sampled validation data will lead to an illusion of a better model performance. Extreme climate background conditions will reduce the prediction accuracy of the predictive model. A feature importance analysis illustrates that the features of the surrounding area with a –12 h offset time have a higher impact on the ground precipitation types. The exploration of the predictability of our model reveals the feasibility of using the analysis data to predict future precipitation types. We use the ECMWF precipitation-type (ECPT) forecast products as the benchmark to compare with our machine learning precipitation-type (MLPT) predictions. The overall accuracy (ACC) and Heidke skill score (HSS) of the MLPT are 0.83 and 0.69, respectively, which are considerably higher than the 0.78 and 0.59 of the ECPT. For stations at elevations below 800 m, the overall performance of the MLPT is even better.

Deep convective systems (DCSs) play a crucial role in global water cycles, energy distribution, and extreme weather events. This study aims to enhance the understanding of DCSs by creating a comprehensive dataset through the fusion of multisource A-Train satellite observations and reanalysis data. Fusing data from multiple active and passive sensors allows us to capture detailed vertical profiles and life stages of DCSs, overcoming the limitations of polar-orbiting satellites in tracking convection over time. Comparison with convection tracking data from geostationary satellites confirmed the reliability of lifecycle determination. Reanalysis data are included for each observed DCS samples, incorporating environmental conditions and aerosol data up to 36 h before the DCS occurrence. Using the fused dataset, we examined the radiative properties of DCSs across different stages of their lifecycle and the influence of environmental factors and aerosols on them. Radiative heating rates showed distinct variations, with mature stages exhibiting the highest shortwave heating and longwave cooling rates due to denser and higher cloud tops. Our findings reveal the role of humidity in increasing cloud top heights and the influence of vertical wind shear on convection development. Additionally, aerosol impacts were notable during the mature and dissipating stages, with higher concentrations linked to increased cloud top heights and lower temperatures. This comprehensive dataset advances the understanding of DCS dynamics, aiding in the improvement of predictive models for severe weather.