In traditional single image super-resolution (SR) methods based on dictionary model, a large number of image features are needed to train the SR dictionary. In general, these features are extracted by artificial rules, such as pixel gray, gradient, and texture structure. But, the dictionary model trained by these artificial features or their combinations has exhibited poor expression especially for the images with complex and rich structures. Therefore, how to improve the dictionary expression ability and make the dictionary have more accurate description of the image features is a problem worthy of further study. In this paper, based on the advantage of dictionary training and deep learning, a new method of single image SR based on deep learning features and dictionary model is proposed. The new algorithm contains three steps. First, the features of high-resolution and low-resolution training images are extracted by a Kernel deep learning network. Second, in the sparse representation of SR framework, the dictionary model is trained by these deep learning features. Finally, an LR image SR is completed. Theoretical analysis show that the dictionary trained by deep learning features can improve in the ability to express image complex structure and texture, and it has more advantage than traditional artificial features dictionary. The experimental results indicate that the proposed algorithm can produce good SR visual results than the comparison algorithm, such as Bicubic, sparse coding super-resolution, and super-resolution convolutional neural network. And the peak signal to noise ratio and structural similarity index measurement are improved, the Computation Time is also reasonable.

The hyperspectral snapshot compressive imaging (SCI) system encodes three-dimensional hyperspectral images into a single two-dimensional snapshot measurement and then decodes the underlying 3-D hyperspectral images by solving the compressive sensing reconstruction problem. Practical applications of SCI imaging systems require fast and high-quality reconstruction. To meet this requirement, we propose a novel encoder and decoder network with dense back-projection joint attention for hyperspectral SCI. The main contributions of our network lie in two aspects. First, we propose a dense back-projection module and deploy it in an encoder with five scales. It computes the back-projection between each scale and all its preceding scales, thereby fusing complementary information between different scales for efficient reconstruction. Second, we design a spatial-spectral attention module and deploy it in the decoder to boost reconstruction quality. By exploiting a cascade of spatial-spectral attention, it can efficiently capture spatial and spectral correlations in hyperspectral images with a low volume of parameters. In addition, a compound loss, including the reconstruction loss, and the spatial–spectral total variation loss, is designed to guide network learning in an end-to-end manner. Intensive experiments on simulation and real data show that our method has obvious advantages over multiple state-of-the-art methods, achieving a significant improvement in reconstruction quality and a substantial reduction in running time.

Typhoons are extreme weather events that pose significant threats to human life and property. Sequential satellite imagery of typhoon clouds, which is rich in spatio-temporal information, plays a critical role in understanding their formation, development, and evolutionary dynamics. Recently, the rapid advancement of deep learning that combines physical insights with data-driven has opened new avenues for research in Earth science. In this study, for high-quality prediction of sequential typhoon cloud images, we propose a physics-enhanced deep learning model termed C²PhyNet. Specifically, we introduce a novel disentangling spatio-temporal block integrated with a criss-cross physics-enhanced unit. To further improve the fine structural details in the predicted typhoon cloud images, a concurrent spatial and channel squeeze-and-excitation attention mechanism is incorporated into both the encoder and decoder modules. Our quantitative analysis demonstrates the superiority of the proposed approach over existing sequential image prediction models on the publicly available Digital Typhoon dataset. The experimental results show that our method achieves superior performance, with a Structural Similarity Index Measure (SSIM) of 0.8200 and a Peak Signal-to-Noise Ratio (PSNR) of 23.26. C²PhyNet is capable of generating high-quality sequential typhoon cloud images, which can significantly enhance the ability of meteorologists to forecast typhoon-related details with greater accuracy. Furthermore, our research contributes to improved risk mitigation and more effective disaster warning and management strategies.

Accurate snow depth estimation is of significant importance, particularly for preventing avalanche disasters and predicting flood seasons. The predominant approaches for such snow depth estimation, based on deep learning methods, typically rely on passive microwave remote sensing data. However, due to the low resolution of passive microwave remote sensing data, it often results in low-accuracy outcomes, posing considerable limitations in application. To further improve the accuracy of snow depth estimation, in this paper, we used active microwave remote sensing data. We fused multi-spectral optical satellite images, synthetic aperture radar (SAR) images and land cover distribution images to generate a snow remote sensing dataset (SRSD). It is a first-of-its-kind dataset that includes active microwave remote sensing images in high-latitude regions of Asia. Using these novel data, we proposed a multi-scale feature perception and aggregation neural network (MFPANet) that focuses on improving feature extraction from multi-source images. Our systematic analysis reveals that the proposed approach is not only robust but also achieves high accuracy in snow depth estimation compared to existing state-of-the-art methods, with RMSE of 0.360 and with MAE of 0.128. Finally, we selected several representative areas in our study region and applied our method to map snow depth distribution, demonstrating its broad application prospects.

Segmenting clouds and their shadows is a critical challenge in remote sensing image processing. The shape, texture, lighting conditions, and background of clouds and their shadows impact the effectiveness of cloud detection. Currently, architectures that maintain high resolution throughout the entire information-extraction process are rapidly emerging. This parallel architecture, combining high and low resolutions, produces detailed high-resolution representations, enhancing segmentation prediction accuracy. This paper continues the parallel architecture of high and low resolution. When handling high- and low-resolution images, this paper employs a hybrid approach combining the Transformer and CNN models. This method facilitates interaction between the two models, enabling the extraction of both semantic and spatial details from the images. To address the challenge of inadequate fusion and significant information loss between high- and low-resolution images, this paper introduces a method based on ASMA (Axial Sharing Mixed Attention). This approach establishes pixel-level dependencies between high-resolution and low-resolution images, aiming to enhance the efficiency of image fusion. In addition, to enhance the effective focus on critical information in remote sensing images, the AGM (Attention Guide Module) is introduced, to integrate attention elements from original features into ASMA, to alleviate the problem of insufficient channel modeling of the self-attention mechanism. Our experimental results on the Cloud and Cloud Shadow dataset, the SPARCS dataset, and the CSWV dataset demonstrate the effectiveness of our method, surpassing the state-of-the-art techniques for cloud and cloud shadow segmentation.