Search

This study advances the precision and efficiency of precipitation nowcasting, particularly under extreme weather conditions. Traditional forecasting methods struggle with precision, spatial feature generalization, and recognizing long-range spatial correlations, challenges that intensify during extreme weather events. The Enhanced Temporal Correlation Jump Prediction Network (ETCJ-PredNet) introduces a novel attention mechanism that optimally leverages spatiotemporal data correlations. This model scrutinizes and encodes information from previous frames, enhancing predictions of high-intensity radar echoes. Additionally, ETCJ-PredNet addresses the issue of gradient vanishing through an innovative jump connection strategy. Comparative experiments on the Moving Modified National Institute of Standards and Technology (Moving-MNIST) and Hong Kong Observatory Dataset Number 7 (HKO-7) validate that ETCJ-PredNet outperforms existing models, particularly under extreme precipitation conditions. Detailed evaluations using Critical Success Index (CSI), Heidke Skill Score (HSS), Probability of Detection (POD), and False Alarm Ratio (FAR) across various rainfall intensities further underscore its superior predictive capabilities, especially as rainfall intensity exceeds 30 dbz,40 dbz, and 50 dbz. These results confirm ETCJ-PredNet's robustness and utility in real-time extreme weather forecasting. [ABSTRACT FROM AUTHOR]

Link prediction has always played a crucial role in unveiling the structural patterns and evolutionary rules of networks. However, as research on complex networks has progressed, the limitations of solely exploring low-order structures have become increasingly apparent. The introduction of high-order organizational theories has not only enriched the conceptual framework of network dynamics but also opened new avenues for investigating the mechanisms of network evolution and adaptation. The complexity and richness of high-order networks pose challenges for link prediction. This study introduces two novel approaches to forecast links in higher-order networks. The first one is to predict links directly in higher-order networks (LPHN), which directly predicts missing links within the higher-order network based on its structure; the other one is to predict higher-order links via link prediction in low-order networks(PHLN), which starts by predicting absent links in a low-order network. Subsequently, the inferred low-order structure is employed as a foundation to extrapolate and reconstruct the predicted higher-order network. Upon comparing the higher-order networks generated by both LPHN and PHLN with the original higher-order networks constructed directly from low-order networks, we discovered that the higher-order networks produced by PHLN exhibit greater accuracy and exhibit a more similar scale of giant components to the original higher-order network. Consequently, the PHLN demonstrates enhanced precision in forecasting the structure of higher-order networks while preserving networks' structural integrity. Moreover, PHLN exhibits superior performance in the context of large-scale and sparsely connected networks. [ABSTRACT FROM AUTHOR]

Few-shot image classification aims to improve the performance of traditional image classification when faced with limited data. Its main challenge lies in effectively utilizing sparse sample label data to accurately predict the true feature distribution. Recent approaches have employed data augmentation techniques like random Mask or mixture interpolation to enhance the diversity and generalization of labeled samples. However, these methods still encounter several issues: (1) random Mask can lead to complete blockage or exposure of foreground, causing loss of crucial sample information; and (2) uniform data distribution after mixture interpolation makes it difficult for the model to differentiate between different categories and effectively distinguish their boundaries. To address these challenges, this paper introduces a novel data augmentation method based on saliency mask blending. Firstly, it selectively preserves key image features through adaptive selection and retention using visual feature occlusion fusion and confidence clipping strategies. Secondly, a visual feature saliency fusion approach is employed to calculate the importance of various image regions, guiding the blending process to produce more diverse and enriched images with clearer category boundaries. The proposed method achieves outstanding performance on multiple standard few-shot image classification datasets (miniImageNet, tieredImageNet, Few-shot FC100, and CUB), surpassing state-of-the-art methods by approximately 0.2–1%. [ABSTRACT FROM AUTHOR]

Robustness is one of the most critical characteristics of complex networks, determining their stability and resilience in the face of various disturbances. With the research on complex networks, people have observed that higher-order networks can also affect the structure and function of the network. Therefore, when studying network robustness, we also need to consider the interaction between higher-order networks and low-order networks. To delve deeper into the investigation and comprehension of robustness in complex networks, this paper introduces a model of higher-low order networks with adjustable coupling strength. In this model, network nodes are categorized into autonomous and nonautonomous nodes, with coupling strength adjusted using three methods: random coupling, degree-related coupling, and local coupling. Validation is performed on ER networks, BA networks, SW networks, as well as several real-world networks. The results indicate that as coupling strength increases, network robustness correspondingly diminishes, and the network exhibits intricate percolation behavior. [ABSTRACT FROM AUTHOR]

In the era of noisy intermediate-scale quantum (NISQ) computing, the synergistic collaboration between quantum and classical computing models has emerged as a promising solution for tackling complex computational challenges. Long short-term memory (LSTM), as a popular network for modeling sequential data, has been widely acknowledged for its effectiveness. However, with the increasing demand for data and spatial feature extraction, the training cost of LSTM exhibits exponential growth. In this study, we propose the quantum convolutional long short-term memory (QConvLSTM) model. By ingeniously integrating classical convolutional LSTM (ConvLSTM) networks and quantum variational algorithms, we leverage the variational quantum properties and the accelerating characteristics of quantum states to optimize the model training process. Experimental validation demonstrates that, compared to various LSTM variants, our proposed QConvLSTM model outperforms in terms of performance. Additionally, we adopt a hierarchical tree-like circuit design philosophy to enhance the model's parallel computing capabilities while reducing dependence on quantum bit counts and circuit depth. Moreover, the inherent noise resilience in variational quantum algorithms makes this model more suitable for spatiotemporal sequence modeling tasks on NISQ devices. [ABSTRACT FROM AUTHOR]

Malicious attacks can cause significant damage to the structure and functionality of complex networks. Previous research has pointed out that the ability of networks to withstand malicious attacks becomes weaker when networks are coupled. However, traditional research on improving the robustness of networks has focused on individual low-order or higher-order networks, lacking studies on coupled networks with higher-order and low-order networks. This paper proposes a method for optimizing the robustness of coupled networks with higher-order and low-order based on a simulated annealing algorithm to address this issue. Without altering the network's degree distribution, the method rewires the edges, taking the robustness of low-order and higher-order networks as joint optimization objectives. Making minimal changes to the network, the method effectively enhances the robustness of coupled networks. Experiments were conducted on Erdős–Rényi random networks (ER), scale-free networks (BA), and small-world networks (SW). Finally, validation was performed on various real networks. The results indicate that this method can effectively enhance the robustness of coupled networks with higher-order and low-order. [ABSTRACT FROM AUTHOR]

Nowcasting has emerged as a critical foundation for services including heavy rain alerts and public transportation management. Although widely used for short-term forecasting, models such as TrajGRU and PredRNN exhibit limitations in predicting low-intensity rainfall and low temporal resolution, resulting in suboptimal performance during infrequent heavy rainfall events. To tackle these challenges, we introduce a spatio-temporal sequence and generative adversarial network model for short-term precipitation forecasting based on radar data. By enhancing the ConvLSTM model with a pre-trained TransGAN generator, we improve feature resolution. We first assessed the model's performance on the Moving MNIST dataset and subsequently validated it on the HKO-7 dataset. Employing metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), Structural Similarity Index Measure (SSIM), Critical Success Index (CSI), Probability of Detection (POD), and False Alarm Ratio (FAR), we compare our model's performance to existing models. Experimental results reveal that our proposed ConvLSTM-TransGAN model effectively captures weather system evolution and surpasses the performance of other traditional models. [ABSTRACT FROM AUTHOR]