A simulation of an extreme precipitation event in southern Xinjiang, which is the driest area in China, seizes the whole initiation process of the intense convective cell responsible for the high hourly rainfall amount. Considering the inner connection between convection and vertical motions, the characteristics and mechanisms of the vertical accelerations during this initial development of the deep convection are studied. It is shown that three key accelerations are responsible for the development from the nascent cumuli to a precipitating deep cumulonimbus, including sub-cloud boundary-layer acceleration, in-cloud deceleration, and cloud-top acceleration. By analyzing the right-hand terms of the vertical velocity equation in the framework of the WRF model, together with a diagnosed relation of perturbation pressure to perturbation potential temperature, perturbation-specific volume (or density), and moisture, the physical processes associated with the corresponding accelerations are revealed. It is found that sub-cloud acceleration is associated with three-dimensional divergence, indicating that the amount of upward transported air must be larger than that of horizontally convergent air. This is favorable for the persistent accumulation of water vapor into the accelerated area. In-cloud deceleration is caused by the intrusion or entrainment of mid-level cold air, which cools down the developing cloud and delays the deep convection formation. Cloud-top acceleration is responsible for the rapid upward extension of the cloud top, which is highly correlated with the convergence and upward transport of moisture.

Thunderstorms are the most frequent type of severe convective weather, which pose great threats to buildings, power transmission, communication facilities, and air transportation. Their analysis and forecasting have long been challenges in meteorological operations. Currently, deep learning-based lightning forecasting has a short valid period, mostly relying on satellite imagery, radar echoes, and lightning location data, focusing on very-short-range forecasting. The longest valid period does not exceed 6 h, and the forecasting accuracy is not high. Based on the physical quantities of the ECMWF numerical prediction model and the actual observations of single-point thunderstorms, this paper constructs a single-point thunderstorm forecasting model with a long validity period (>6 h). The study integrates multi-dimensional parameters such as thermal, dynamic, water vapor, and stratification instability, introduces the second-order moist potential vorticity S as a comprehensive predictor, systematically compares the forecasting performance of eight models, such as 1D PreRNN and ConvLSTM, and verifies the actual operational capability of the model through independent cases. The results show that the 1D PreRNN model has the best overall performance in all periods, which can effectively capture the temporal evolution characteristics of meteorological physical quantities and still has stable generalization performance under unbalanced samples. The model performs well in the 1st, 2nd, and 4th periods, and especially still has significant operational reference value in the 4th period with the longest forecasting validity period; only the 3rd period is weakly affected by the small number of samples. The effect of second-order moist potential vorticity has significant time-dependent differences. Its overall improvement effect is limited in short-term forecasting, but it can provide key disturbance signals in the 4th period with the longest forecasting validity period, and the model forecasting performance drops significantly after removal. The original binary cross-entropy loss is most suitable for the unbalanced sample scenario in this study, and weighted losses are prone to overcorrection. The method in this paper can achieve stable and reliable single-point thunderstorm forecasting for more than 6 h, and can provide long-term fixed-point meteorological support for key scenarios such as aerospace and new energy stations.