Search

This article proposes a dual global–local attention network (DGLAnet), which is an end-to-end unsupervised band selection (UBS) method that fully utilizes spatial and spectral information in both global and local aspects. The DGLAnet assumes that BS can be realized using the hyperspectral image (HSI) reconstruction process. First, the DGLAnet implements a dual attention module to obtain spatial–spectral and global–local features to reweight the HSI data. It adopts bi-directional relations to grasp spatial and spectral features from a global perspective. Meanwhile, the DGLAnet extracts local features through max-pooling and mean-pooling and then merges them via the convolution operation. Global–local features are utilized to learn attention to recalibrate the original data, and the reconstruction module is adopted to restore the original image from the reweighted HSI data. Finally, a proper band subset is selected by the constructed band evaluation index. Experiments on three hyperspectral data show that the DGLAnet outperforms other state-of-the-art methods and uses all bands with a lower computational cost. [ABSTRACT FROM AUTHOR]

• The paper proposes a pioneering unsupervised deep learning method for spatial-temporal-spectral fusion of HSI and MSI. • TDGAN revolutionizes the generation of high-quality hyperspectral time-series datasets and for the first time. • TDGAN framework incorporates a deep prior, resulting in a significant enhancement of image fusion performance. • Swin transformer is firstly used for spectral super-resolution represents a groundbreaking application. • Three discriminators have been designed to minimize the loss of phenological information and spatial-spectral information. Over the past decade, image fusion has emerged as an indispensable tool for surface monitoring due to its capability to reconstruct high-quality surface reflectance. While satisfactory progress has been made in the spatial-spectral and spatial-temporal fusion of remote sensing images, the fusion of spatial-temporal-spectral data remains a challenging task. This challenge arises from the presence of multiple nonlinear relationships caused by inconsistent temporal, spatial, and spectral resolutions. In this paper, we propose a novel approach to address the spatial-temporal-spectral fusion of remote sensing images using a triple discriminator Generative Adversarial Network called TDGAN. Our approach represents the first attempt at spatial-temporal-spectral fusion based on deep learning techniques. Specifically, TDGAN achieves unsupervised learning by incorporating a deep spectral transformation prior, explores the application performance of the Swin Transformer in spectral super-resolution for the first time. Additionally, three discriminators are designed based on the prior consistencies: phenological consistency for data acquired at different times and spatial-spectral consistency for data acquired at the same time. These discriminators effectively enhance the prediction accuracy of missing hyperspectral images. Extensive simulations and real experiments were conducted to evaluate the effectiveness of our proposed TDGAN. The results demonstrate its robustness and comparable performance to other state-of-the-art methods. The proposed approach provides high-quality hyperspectral datasets with high spatial and temporal resolutions, facilitating continuous land cover observations. [ABSTRACT FROM AUTHOR]

• Spectral database contains FTIR and Raman Data of over 20 different polymers. • Novel decision tree CNN architecture performed better than end-to-end networks. • Deep learning can distinguish between weathered and unaged plastic samples. Increasing plastic recycling rates is key to addressing plastic pollution. New technologies such as chemometric analysis of spectral data have shown great promises in improving the plastic sorting efficiency to boost recycling rates. In this work, a novel deep learning architecture, PolymerSpectraDecisionNet (PSDN) was developed, consisting of convolutional neural networks, residual networks and inception networks in a decision tree structure. To better represent the conditions in the plastic recycling industry, the models were built to identify the most widely recycled polymers – polyethylene, polypropylene and polyethylene terephthalate from open-sourced infrared and Raman spectral dataset containing over 20 different polymers. PSDN performed better than end-to-end neural networks, obtaining an accuracy of 0.949 and 0.967 with the Raman and infrared datasets respectively. The use of deep learning can also distinguish between weathered and unaged polymer samples, with accuracies of 0.954 for high density polyethylene and 0.906 for polyethylene terephthalate. [Display omitted] [ABSTRACT FROM AUTHOR]