Accurate and prior identification of local severe storm systems in pre-convection environments using geostationary satellite imagery measurements is a challenging task. Methodologies for “convective initiation” identification have already been developed and explored for operational nowcasting applications; however, warning of such convective systems using the new generation of geostationary satellite imagery measurements in pre-convection environments is still not well studied. In this investigation, the Random Forest (RF) machine learning algorithm is used to develop a predictive statistical model for tracking and identifying three different types of convective storm systems (weak, medium, and severe) over East Asia by combining spatially-temporally collocated Himawari-8 (H08) measurements and Numerical Weather Prediction (NWP) forecast data. The Global Precipitation Measurement (GPM) gridded product is used as a benchmark to train the predictive models based on a sample-balance technique which can adjust or balance the samples of three different convection types to avoid over-fitting any type of dataset. Variables such as brightness temperatures (BTs) from H08 water vapor absorption bands (6.2 μm, 6.9 μm and 7.3 μm) and Total Precipitable Water (TPW) from NWP show relatively high ranks in the predictive model training. These sensitive variables are closely associated with convectively dominated precipitation areas, indicating the importance of predictors from both H08 and NWP data. The final optimal RF model is achieved with an accuracy of 0.79 for classification of all convective storm systems, while the Probability of Detection (POD) of this model for severe and medium convections can reach 0.66 and 0.70, respectively. Two typical sudden convective storm cases in the warm season of 2018 tracked by this algorithm are described, and results indicate that the H08 and NWP based statistical model using the RF algorithm is capable of capturing local burst convective storm systems about 1–2 h earlier than the outbreak of heavy rainfall.

This study evaluates the representativeness of two widely used next-generation global satellite precipitation estimates data for short-term precipitation over China, namely the satellite data from the Climate Prediction Center morphing (CMORPH) and the satellite data from the Global Precipitation Measurement (GPM) mission. These two satellite precipitation data sets were compared with the hourly liquid in-situ precipitation from China national surface stations from 2016 to 2020. The results showed that the GPM precipitation data has better representativeness of surface short-term precipitation than that of the CMORPH data, and these two quantitative precipitation estimate (QPE) data sets underestimated extreme precipitation. Moreover, we analyzed the influence of the error between two QPE data sets and the in-situ precipitation on the classification of short-term precipitation intensity. China uses 8.1–16 mm/h as the definition of heavy precipitation, but the accuracy of the satellite QPE product was different due to the different lowest threshold of heavy rain (more than 8.1 mm/h or more than 16 mm/h). Increasing the threshold value of the QPE data for short-term strong precipitation resulted in lower accuracy for detecting such events, but higher accuracy for detecting moderate intensity rainfall. When studying short-term strong precipitation over China using precipitation grade, selecting an appropriate threshold was important to ensure accurate judgments. Additionally, it is important to account for errors caused by QPE data, which can significantly affect the accuracy of precipitation grading.