Nowcasting of convective storms is urgently needed yet rather challenging. Current nowcasting methods are mostly based on radar echo extrapolation, which suffer from the insufficiency of input information and ineffectiveness of model architecture. A novel deep‐learning (DL) model, FURENet, is designed for extracting information from multiple input variables to make predictions. Polarimetric radar variables, K_DP and Z_DR, which provide extra microphysics and dynamic structure information of storms, are fed into the model to improve nowcasting. Two representative cases indicate that K_DP and Z_DR can help the DL model better forecast convective organization and initiation. Quantitative statistical evaluation shows using FURENet, K_DP, and Z_DR synergistically improve nowcasting skills (CSI score) by 13.2% and 17.4% for the lead time of 30 and 60 min, respectively. Further evaluation shows the microphysical information provided by the polarimetric variables can enhance the DL model in understanding the evolution of convective storms and making more trustable nowcasts.

Deep-learning-based radar echo extrapolation methods have achieved remarkable progress in the precipitation nowcasting field. However, they suffer from a common notorious problem—they tend to produce blurry predictions. Although some efforts have been made in recent years, the blurring problem is still under-addressed. In this work, we propose three effective strategies to assist deep-learning-based radar echo extrapolation methods to achieve more realistic and detailed prediction. Specifically, we propose a spatial generative adversarial network (GAN) and a spectrum GAN to improve image fidelity. The spatial and spectrum GANs aim at penalizing the distribution discrepancy between generated and real images from the spatial domain and spectral domain, respectively. In addition, a masked style loss is devised to further enhance the details by transferring the detailed texture of ground truth radar sequences to extrapolated ones. We apply a foreground mask to prevent the background noise from transferring to the outputs. Moreover, we also design a new metric termed the power spectral density score (PSDS) to quantify the perceptual quality from a frequency perspective. The PSDS metric can be applied as a complement to other visual evaluation metrics (e.g., LPIPS) to achieve a comprehensive measurement of image sharpness. We test our approaches with both ConvLSTM baseline and U-Net baseline, and comprehensive ablation experiments on the SEVIR dataset show that the proposed approaches are able to produce much more realistic radar images than baselines. Most notably, our methods can be readily applied to any deep-learning-based spatiotemporal forecasting models to acquire more detailed results.

Drive-by download attacks, which exploit vulnerabilities of web browsers to control client computers, have become a major venue for attackers. To detect such attacks, researchers have proposed many approaches such as anomaly-based [22, 23] and vulnerability-based [44, 50] detections. However, anomaly-based approaches are vulnerable to data pollution, and existing vulnerability-based approaches cannot accurately describe the vulnerability condition of all the drive-by download attacks. In this paper, we propose a vulnerability-based approach, namely JShield, which uses novel opcode vulnerability signature, a deterministic finite automaton (DFA) with a variable pool at opcode level, to match drive-by download vulnerabilities. We investigate all the JavaScript engine vulnerabilities of web browsers from 2009 to 2014, as well as those of portable document files (PDF) readers from 2007 to 2014. JShield is able to match all of those vulnerabilities; furthermore, the overall evaluation shows that JShield is so lightweight that it only adds 2.39 percent of overhead to original execution as the median among top 500 Alexa web sites.

Accurate nowcasting of severe convective precipitation is critical for early warning yet still remains challenging. Although deep learning methods show promise, most models lack physical constraints, limiting their consistency with atmospheric processes. We introduce FURECast, a deep learning model that not only leverages three‐dimensional structure of polarimetric radar variables ( Z _H , Z _DR , K _DP ) but also embeds their intrinsic self‐consistency relation as a physical constraint. The model employs an encoder‐translator‐decoder architecture, integrating multi‐level inputs via late fusion and evolving features through cascaded multiscale blocks. Moreover, a novel physical loss term is introduced to enforce microphysical consistency during training. Evaluated on S‐band (GD‐SPOL) and C‐band (NJU‐CPOL) radar data sets, FURECast achieves a 14.1% improvement in 90‐min critical success index (35 dBZ threshold) over the 2D reflectivity‐only baseline, while reducing physical inconsistency by two orders of magnitude. These results underscore the value of 3D polarimetric structure and physics‐guided learning in advancing convective precipitation nowcasting.

This study developed Fully Connected Neural Network (FCNN) models to retrieve the microphysical parameters of ice particles, specifically volume-weighted median diameter (D_m) and ice water content (IWC), using polarimetric radar measurements including reflectivity (Z_H), differential reflectivity (Z_DR), and specific differential phase (K_DP). The performance and uncertainties of FCNN-based retrievals were evaluated through comparisons with conventional power-law (PL) estimators, where the effects of particle aspect ratio (AR), density (DC), and radar measurement errors were considered. For ice retrievals with a fixed DC, FCNN models outperformed PL, especially in the presence of measurement errors. Errors in Z_DR and K_DP can increase retrieval bias and reduce correlation coefficients in both kinds of methods. For datasets with varying DCs, Z_DR, even combined with Z_H and K_DP, was unable to fully capture simultaneous changes in DC and AR, limiting the FCNNs ability to account for shape and density variations. Both the FCNN and PL methods were applied to analyze a snowstorm event and a mesoscale convective system (MCS). Both approaches successfully identified larger ice particles formed through riming and aggregation towards the ground. The FCNN exhibited higher retrieval accuracy and a smoother vertical IWC profile, particularly in the dendritic growth layer. Additionally, evaluation using airborne in situ observations in the MCS demonstrated that both methods performed well in retrieving D_m, with the FCNN providing more accurate IWC estimates.

Accurate identification of non-precipitation echoes (NPEs) in weather radar observations requires effective use of polarimetric signatures together with spatiotemporal structure. Here we present a unified deep-learning framework to quantify the independent and synergistic contributions of model architecture, dual-polarization variables, and short-term temporal evolution to NPE identification. Using data from the Guangzhou S-band dual-polarization radar, we conduct controlled comparative experiments with two representative architectures: a pointwise multilayer perceptron (MLP) and a Transformer-based Swin U-Net that explicitly learns spatial context. We further perform ablation experiments across single- versus dual-polarization inputs and single-volume versus two-volume inputs. Results show that architecture-driven spatial-context learning is the dominant factor: Swin U-Net consistently outperforms the pointwise MLP under all input settings. On a high-confidence test subset, for example, the Critical Success Index (CSI) increases from 0.887 for the dual-polarization MLP to 0.950 for the dual-polarization Swin U-Net. Dual-polarization variables provide essential microphysical constraints and substantially improve class separability, particularly for pointwise classifiers. Incorporating two consecutive volumes further improves performance by capturing short-term echo evolution, with larger gains for the MLP than for Swin U-Net. The best-performing configuration, combining Swin U-Net with dual-polarization and two-volume inputs, achieves a CSI of 0.953 on the high-confidence test subset. Notably, the Swin U-Net using only the reflectivity factor (Z_H) as input retains strong skill (CSI = 0.927), indicating that spatial-context learning can partially compensate for missing polarimetry and thus providing a practical pathway for quality control of legacy single-polarization archives.