Arranging 3 years’ worth of airborne precipitation particle images to construct a precipitation particle image dataset in Shan⁃ dong Province. Building a precipitation particle recognition model based on EfficientNet convolutional neural network, named PREN (Precipitation particle Recognition model based on EfficientNet convolutional neural Network).The accuracy rate is 98%, and the multimodel and multi-index evaluation and comparison experiments verify that PREN demonstrates excellent robustness and generalization ability. Taking typical stratiform-cumulus mixed cloud precipitation as two examples (total 3 time periods), PREN is applied to the par⁃ ticle characteristics analysis of generating cells. Combined with airborne Ka-band cloud radar and DMT particle measurement system, an analysis conducted on the shape proportion of precipitation particles inside and outside the generating cells and indifferent intensity generating cells, revealing the precipitation mechanism. The results show that the shapes of precipitation particles in the generating cells are mainly spherical, needle-like, irregular and columnar. Precipitation particles outside the generating cells are mostly spherical and needle-like. The cloud microphysical parameters in the generating cells with different intensities vary. The proportion of graupel and needle particles in the precipitation maturity stage is higher than that in the dissipation stage. The average chord length of precipi⁃ tation particles in the maturity stage is 415 µm. While the average chord length of particles in dissipation stage is 367 µm. The par⁃ ticles on the top of generating cells are mainly spherical and hexagonal, primarily growing through the process of deposition. The ratio of irregular particles and columnar particles in the 0 ℃ are increasing, and the melting process and dynamic conditions favor aggregation and growth, forming irregular particles, while columns mainly originate from the upper levels of the atmosphere.
Based on the record data of water disasters and the 5-min precipitation of 40 meteorological observation stations along the Shuozhou-Huanghua Railway from 2017 to 2019, the characteristics of railway water disasters and precipitation distribution were analyzed, then the three precipitation factors including continuous precipitation, the hourly maximum precipitation and the 24-hour precipitation were counted, the rainfall warning thresholds of no warning, patrol warning, speed limit warning and blockade warning of railway sections in plains and mountainous areas were formulated by using the mean-standard deviation method and the maximum value method. The results show that the water disasters of the Shuozhou-Huanghua Railway mainly occurred in July and August, and the duration of precipitation was mostly within 48 hours. The precipitation types causing water disasters were mainly local rainstorm, short-time heavy precipitation and long-duration precipitation, the railway water disasters in plain sections were mainly caused by local rainstorm, but the main cause of mountainous sections was long-duration precipitation. For railway section in the plain, the accuracy rate of patrol warning was 88.5%, the false rate was 11.5%, the accuracy rate of speed limit warning was 100%, for the railway section in the mountainous, the accuracy of patrols warning was 88.9% and the false rate was 11.1%. The rainfall warning threshold for railway sections in plains and mountainous areas could provide reference for safe running and efficient operation of railway.