Multispectral image pansharpening is a significant technology for remote sensing image analysis, aiming to restore a high-resolution multispectral (HRMS) image by merging a high-resolution panchromatic (PAN) image with a low-resolution multispectral (MS) image. While the convolutional neural networks (CNN) have garnered considerable attention for their exceptional fusion capabilities in recent years, existing CNN-based methods cannot effectively integrate spectral-spatial information. In this paper, we introduce a novel multispectral pansharpening framework that integrates spectral and spatial networks in a bilateral pyramid form, allowing for the extraction of hierarchical spectral-spatial information. The proposed reduced residual dense (RRD) module serves as the fundamental building block of the spatial network. The RRD module gradually reduces the dimension of feature maps and employs the concatenation of RRD with global residual learning for comprehensive feature representation. In the spectral network, we present a cooperative attention fusion (CAF) module to further enhance the correlation between spectral and spatial features. Through extensive experiments conducted on benchmarking simulated and real datasets, our proposed framework consistently outperforms state-of-the-art methods, demonstrating its effectiveness in multispectral image pansharpening applications.
With the development of the Smart Grid, accurate prediction of power generation is becoming an increasingly crucial task. The primary goal of this research is to create an efficient and reliable forecasting model to estimate the full-load power generation of a combined-cycle power plant (CCPP). The dataset used in this research is a subset of the publicly available UCI Machine Learning Repository. It contains 9568 items of data collected from a CCPP during its full load operation over a span of six years. To enhance the accuracy of power generation forecasting, a novel forecasting method based on Transformer encoders with deep neural networks (DNN) was proposed. The proposed model exploits the ability of the Transformer encoder to extract valuable information. Furthermore, bottleneck DNN blocks and residual connections are used in the DNN component. In this study, a series of experiments were conducted, and the performance of the proposed model was evaluated against other state-of-the-art machine learning models based on the CCPP dataset. The experimental results illustrated that using Transformer encoders along with DNN can considerably improve the accuracy of predicting CCPPs power generation (RMSE = 3.5370, MAE = 2.4033, MAPE = 0.5307%, and R2 = 0.9555).
20 October 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Pansharpening is an image fusion technique that integrates low-resolution multispectral (MS) images with high-resolution panchromatic (PAN) images to generate high-resolution multispectral images with enhanced spatial and spectral fidelity. Existing convolutional neural networks (CNNs) for pansharpening are limited in their ability to model long-range dependencies, whereas Transformer-based models often incur significant computational overhead. To efficiently capture global correlations among remote sensing image patches, we propose the global context injection Transformer (GCIFormer) as a core component in both the spatial and spectral branches. The proposed GCIFormer captures global dependencies at the window level and subsequently infuses them into the image representation at the patch level. Moreover, we design an axial fusion module (AFM) to capture long-range dependencies between the two modalities while mitigating information loss. AFM exploits axial features from different modalities by fusing their feature maps along respective axial directions. In addition, we introduce a PAN reconstruction loss to enhance the retention of high-frequency spatial details. Extensive experiments conducted on multiple benchmark datasets demonstrate that the proposed model outperforms state-of-the-art methods, showcasing its superior performance in pansharpening applications.
26 November 2025 in Journal of Visual Communication and Image Representation