Measuring the atmospheric electric field is of crucial importance for studying the discharge phenomena of thunderstorm clouds. If one is used to indicate the occurrence of a lightning event and zero to indicate the non-occurrence of the event, then a binary classification problem needs to be solved. Based on the established database of weather samples, we designed a lightning prediction system using deep learning techniques. First, the features of time-series data from multiple electric field measurement sites are extracted by a sparse auto encoder (SAE) to construct a visual picture, and a binary prediction of whether lightning occurs at a specific time interval is obtained based on the improved ResNet50. Then, the central location of lightning flashes is located based on the extracted features using a multilayer perceptron (MLP) model. The performance of the method yields satisfactory results with 88.2% accuracy, 92.2% precision rate, 81.5% recall rate, and 86.4% F1-score for weather samples, which is a significant improvement over traditional methods. Multiple spatial localization results for several minutes before and after can be used to know the specific area where lightning is likely to occur. All the above methods passed the reliability and robustness tests, and the experimental results demonstrate the effectiveness and superiority of the model in lightning short-time proximity warning.

The numerical simulations of the initial plasma dynamics induced by 1064 nm laser irradiation on a KCl-Ti mixture target in a laser-triggered vacuum switch are performed. The simulation results showed that laser irradiance strongly affects the dynamics of the initial plasma. With higher laser fluence, the plasma plume will have higher temperatures and densities, and the shock front will also move faster. During the laser ablation, the plasma shielding is a non-negligible process. As the degree of ionization increases, the absorption coefficient of the plume increases and the it begins to absorb the laser energy. The temperature and velocity of the plume increase dramatically as it absorbs laser energy. When laser fluence gets higher, the plasma shielding starts with a shorter time and a larger proportion of the laser energy is absorbed by the plume.

The laser-triggered vacuum switch (LTVS) is a type of high-voltage closing switch with broad application prospects in pulsed-power technology. Research into the triggering process of the LTVS is not only helpful to understand the triggering mechanism of the LTVS but also beneficial to the optimization of the LTVS. In this paper, the triggering process and the delay time of a LTVS with a Ti–KCl mixture target was analyzed theoretically. A numerical simulation was performed to describe the laser-target ablation process and the expansion dynamics of the initial plasma. The simulation results were compared with the experimental results. It is clear that the triggering process and delay time strongly depend on the laser intensity. As the laser intensity rises, the velocity of initial plasma increases, resulting in a shorter delay time of the LTVS. Increasing the gap voltage can also shorten the delay time.

In recent years, deep learning techniques have been developed in the field of storm nowcasting, and they primarily focus on 2D radar product processing. Deep learning’s application to obtaining motion fields is limited by the lack of a motion field ground truth dataset for training. In this paper, we propose a method for storm motion estimation based on a point cloud deep learning network, which can perform 3D motion field estimation on two consecutive frames of weather radar volumetric data. To address the lack of ground truth data, we propose a synthetic data generation method based on Perlin noise and also generate a dataset to train the network. Our model’s architecture is based on FlowNet 3D. In this sense, we import an attention architecture to improve its ability to embed motion features. We also redesign the loss function to make it suitable for our task. In the experiment section, we first evaluate the performance of the trained model on our synthetic dataset. The experimental results demonstrate the following: first, that the trained network has the ability to estimate 3D motion from radar point cloud data; second, that it is a robust solution for radar data with different resolutions and observation ranges; and finally, that for the examined task, our proposed architecture has a 5-15% lower end point error than the original. Then, we directly apply the model trained on synthetic data to real cases, demonstrating the feasibility of our trained model on real data. Although motion field is a low-level product when considering a storm’s evolutionary process, it has the potential to serve a higher-level purpose, such as lightning or hail nowcasting. The point cloud approach provides a new perspective on weather radar data processing.