Clouds have an enormous influence on the Earth's energy balance, climate, and weather. Cloud types have different cloud radiative effects, which is an essential indicator of the cloud effect on radiation. Therefore, identifying the cloud type is important in meteorology. In this letter, we propose a new convolutional neural network model, called CloudNet, for accurate ground‐based meteorological cloud classification. We build a ground‐based cloud data set, called Cirrus Cumulus Stratus Nimbus, which consists of 11 categories under meteorological standards. The total number of cloud images is three times that of the previous database. In particular, it is the first time that contrails, a type of cloud generated by human activity, have been taken into account in the ground‐based cloud classification, making the Cirrus Cumulus Stratus Nimbus data set more discriminative and comprehensive than existing ground‐based cloud databases. The evaluation of a large number of experiments demonstrates that the proposed CloudNet model could achieve good performance in meteorological cloud classification.

The instability of lithium-ion batteries may result in system operation failure and cause safety accidents, thus predicting the remaining useful life (RUL) accurately is helpful for reducing the risk of battery failure and extending its useful life. In this paper, a hybrid model based on TCN-GRU-DNN and dual attention mechanism is proposed for enhancing the RUL prediction accuracy of lithium-ion batteries. Firstly, the Temporal Convolutional Network (TCN) with a feature attention mechanism is applied to form an encoder module to capture the battery capacity regeneration phenomenon, and then a Gated Recurrent Unit (GRU) with a temporal attention mechanism is denoted as a decoder module for better characterizing the decay trend of the capacity series. Finally, the final prediction results are output through a Deep Neural Network (DNN). We conducted experiments on two data sets NASA and CALCE. The prediction errors are presented in subsequent experiments under different evaluation standards such as absolute error (AE), root mean square error (RMSE), mean absolute error (MAE), and R-squared error (R²). The experimental results demonstrate that the proposed model can achieve a more accurate prediction for RUL on lithium-ion batteries, with RMSE does not exceed 2.407% in the NASA dataset and does not exceed 0.897% in the CALCE lithium-ion battery dataset respectively.

Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content. Therefore, we present ResDiff, a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR). ResDiff utilizes a combination of a CNN, which restores primary low-frequency components, and a DPM, which predicts the residual between the ground-truth image and the CNN predicted image. In contrast to the common diffusion-based methods that directly use LR space to guide the noise towards HR space, ResDiff utilizes the CNN’s initial prediction to direct the noise towards the residual space between HR space and CNN-predicted space, which not only accelerates the generation process but also acquires superior sample quality. Additionally, a frequency-domain-based loss function for CNN is introduced to facilitate its restoration, and a frequency-domain guided diffusion is designed for DPM on behalf of predicting high-frequency details. The extensive experiments on multiple benchmark datasets demonstrate that ResDiff outperforms previous diffusion based methods in terms of shorter model convergence time, superior generation quality, and more diverse samples.

Recently, convolution neural network (CNN)-based hyperspectral image (HSI) classification has enjoyed high popularity due to its appealing performance. However, using 2-D or 3-D convolution in a standalone mode may be suboptimal in real applications. On the one hand, the 2-D convolution overlooks the spectral information in extracting feature maps. On the other hand, the 3-D convolution suffers from heavy computation in practice and seems to perform poorly in scenarios having analogous textures along with consecutive spectral bands. To solve these problems, we propose a mixed CNN with covariance pooling for HSI classification. Specifically, our network architecture starts with spectral-spatial 3-D convolutions that followed by a spatial 2-D convolution. Through this mixture operation, we fuse the feature maps generated by 3-D convolutions along the spectral bands for providing complementary information and reducing the dimension of channels. In addition, the covariance pooling technique is adopted to fully extract the second-order information from spectral-spatial feature maps. Motivated by the channel-wise attention mechanism, we further propose two principal component analysis (PCA)-involved strategies, channel-wise shift and channel-wise weighting, to highlight the importance of different spectral bands and recalibrate channel-wise feature response, which can effectively improve the classification accuracy and stability, especially in the case of limited sample size. To verify the effectiveness of the proposed model, we conduct classification experiments on three well-known HSI data sets, Indian Pines, University of Pavia, and Salinas Scene. The experimental results show that our proposal, although with less parameters, achieves better accuracy than other state-of-the-art methods.

Precipitation nowcasting is one of the fundamental challenges in natural hazard research. High-intensity rainfall, especially the rainstorm, will lead to the enormous loss of people’s property. Existing methods usually utilize convolution operation to extract rainfall features and increase the network depth to expand the receptive field to obtain fake global features. Although this scheme is simple, only local rainfall features can be extracted leading to insensitivity to high-intensity rainfall. This letter proposes a novel precipitation nowcasting framework named Rainformer, in which, two practical components are proposed: the global features extraction unit and the gate fusion unit (GFU). The former provides robust global features learning ability depending on the window-based multi-head self-attention (W-MSA) mechanism, while the latter provides a balanced fusion of local and global features. Rainformer has a simple yet efficient architecture and significantly improves the accuracy of rainfall prediction, especially on high-intensity rainfall. It offers a potential solution for real-world applications. The experimental results show that Rainformer outperforms seven state of the arts methods on the benchmark database and provides more insights into the high-intensity rainfall prediction task.

A large amount of labeled data are important to enhance the performance of deep-learning-based methods in the area of fault diagnosis. Because it is difficult to obtain high-quality samples in real industrial applications, federated learning is an effective framework for solving the problem of sparse samples by using the distributed data. Its global model is updated by the local client without sharing data at each round. Considering computing resources and communication loss of multiple clients, an efficient method based on stacked sparse autoencoders (SSAEs) and Siamese networks is proposed to detect interturn short-circuit (ITSC) faults in permanent magnet synchronous motors. In this article, to achieve an accurate ITSC fault detection, an SSAE was employed to extract sparse features in a limited number of samples, and Siamese networks were used to determine the similarity between the given samples. The problem of fault diagnosis is transformed into a classification problem under few-shot learning. Furthermore, the proposed method is trained successfully in the frameworks of centralized learning and decentralized structure. The experimental results indicate that the proposed method achieved high fault diagnosis accuracy. Moreover, it is suitable for deployment in smart manufacturing systems.