On the evening of 30 April 2021, a severe hailstorm swept across eastern China, causing catastrophic gale and damaging hailstones. This hailstorm event was directly caused by two mesoscale convective systems associated with strong squall lines, with mid-level cold advection from the northeast cold vortex, and strong low-level convergence associated with the low-level vortex and wind shear line. Double nesting of the high-resolution weather research and forecasting model (9–1 km) is utilized to simulate this hailstorm with five microphysics schemes. The radar-based maximum estimated size of hail (MESH) algorithm, differential reflectivity and fractions skill scores were used to quantitatively evaluate the precision. All schemes basically captured the two squall lines that swept through eastern China, although they appeared one or two hours earlier than observation. Particularly, Goddard and Thompson performed better in the MESH swath and fractions skill scores among the five different schemes. However, Thompson most realistically captured the reflectivity pattern, intensity and vertical structure of mesoscale convective systems. Its high-reflectivity column corresponded to the maximum center of the hail mixing ratio within the updraft region, which is consistent with the characteristics of a pulse-type hailstorm in its mature phase.
In this study, we applied an explainable machine learning technique based on the LightGBM method, a category of gradient boosting decision tree algorithm, to conduct a quantitative radar precipitation estimation and move to understand the underlying reasons for excellent estimations. By introducing 3D grid radar reflectivity data into the LightGBM algorithm, we constructed three LightGBM models, including 2D and 3D LightGBM models. Ten groups of experiments were carried out to compare the performances of the LightGBM models with traditional Z–R relationship methods. To further assess the performances of the LightGBM models, rainfall events with 11,483 total samples during August-September of 2022 were used for statistical analysis, and two heavy rainfall events were specifically chosen for the spatial distribution evaluation. The results from both the statistical analysis and spatial distribution demonstrate that the performance of the LightGBM 3D model with nine points is the best method for quantitative precipitation estimation in this study. Through analyzing the explainability of the LightGBM models from Shapley additive explanations (SHAP) regression values, it can be inferred that the superior performance of the LightGBM 3D model is mainly attributed to its consideration of the rain gauge station attributes, diurnal variation characteristics, and the influence of spatial offset.