Deep learning methods used for hyperspectral image (HSI) classification often achieve greater accuracy than traditional algorithms but require large numbers of training epochs. To simplify model structures and reduce their training epochs, an end-to-end deep learning framework incorporating a spectral-spatial cascaded 3D convolutional neural network (CNN) with a convolutional long short-term memory (CLSTM) network, called SSCC, is proposed herein for HSI classification. The SSCC framework employs cascaded 3D CNN to learn the spectral-spatial features of HSIs and uses the CLSTM network to extract sequence features. Residual connections are used in SSCC to accelerate model convergence, with the outputs of previous convolutional layers concatenated as inputs for subsequent layers. Moreover, the data augmentation, parametric rectified linear unit, dynamic learning rate, batch normalization, and regularization (including dropout and L2) methods are used to increase classification accuracy and prevent overfitting. These attributes allow the SSCC framework to achieve good performance for HSI classification within 20 epochs. Three well-known datasets including Indiana Pines, University of Pavia, and Pavia Center were employed to evaluate the classification performance of the proposed algorithm. The GF-5 dataset of Anxin County, obtained from China’s recently launched spaceborne Advanced Hyperspectral Imager, was also used for classification experiments. The experimental results demonstrate that the proposed SSCC framework achieves state-of-the-art performance with better training efficiency than other deep learning methods.

Soil contamination by arsenic and heavy metals is an increasingly severe environmental problem. Efficiently investigation of soil contamination is the premise of soil protection and further the foundation of food security. Visible and near-infrared reflectance spectroscopy (VNIRS) has been widely used in soil science, due to its rapidity and convenience. With different spectrally active soil characteristics, soil reflectance spectra exhibit distinctive curve forms, which may limit the application of VNIRS in estimating contaminant elements in soil. Consequently, spectral clustering was applied to explore the potential of classification in estimating soil contaminant elements. Spectral clustering based on different distance measure methods and elements with different contamination levels were exploited. In this study, soil samples were collected from Hunan Province, China and 74 reflectance spectra of air-dried soil samples over 350–2500 nm were used to predict nickel (Ni) and zinc (Zn) concentrations. Spectral clustering was achieved by K-means clustering based on squared Euclidean distance and Cosine of spectral angle, respectively. The prediction model was calibrated with the combination of Genetic algorithm and partial least squares regression (GA-PLSR). The prediction accuracy shows that the prediction of Ni and Zn concentrations in soil was improved to different extents by the two clustering methods and the clustering based on squared Euclidean distance had better performance over the clustering relied on Cosine of the spectral angle. The result reveals the potential of spectral classification in predicting soil Ni and Zn concentrations. A selected subset of the 74 soil spectra was used to further explore the potential of spectral classification in estimating Zn concentrations. The prediction was dramatically improved by clustering based on squared Euclidean distance. Additionally, analysis on distance measure methods indicates that Euclidean distance is more suitable to describe the difference between the collected soil reflectance spectra, which brought the better performance of the clustering based on squared Euclidean distance.

Target detection is an active area in hyperspectral imagery (HSI) processing. Many algorithms have been proposed for the past decades. However, the conventional detectors mainly benefit from the spectral information without fully exploiting the spatial structures of HSI. Besides, they primarily use all bands information and ignore the inter-band redundancy. Moreover, they do not make full use of the difference between the background and target samples. To alleviate these problems, we proposed a novel joint sparse and low-rank multi-task learning (MTL) with extended multi-attribute profile (EMAP) algorithm (MTJSLR-EMAP). Briefly, the spatial features of HSI were first extracted by morphological attribute filters. Then the MTL was exploited to reduce band redundancy and retain the discriminative information simultaneously. Considering the distribution difference between the background and target samples, the target and background pixels were separately modeled with different regularization terms. In each task, a background pixel can be low-rank represented by the background samples while a target pixel can be sparsely represented by the target samples. Finally, the proposed algorithm was compared with six detectors including constrained energy minimization (CEM), adaptive coherence estimator (ACE), hierarchical CEM (hCEM), sparsity-based detector (STD), joint sparse representation and MTL detector (JSR-MTL), independent encoding JSR-MTL (IEJSR-MTL) on three datasets. Corresponding to each competitor, it has the average detection performance improvement of about 19.94%, 22.53%, 16.92%, 14.87%, 14.73%, 4.21% respectively. Extensive experimental results demonstrated that MTJSLR-EMAP outperforms several state-of-the-art algorithms.

Satellite hyperspectral imagery is an important data source for large-scale refined land cover classification and mapping, but the high spatial heterogeneity and spectral variability at low spatial resolution and the high computation cost for massive data remain challenges in the research community. In recent years, convolutional neural network (CNN) models with the capability for feature extraction have been widely used in hyperspectral image classification. However, incomplete feature extraction, inappropriate feature fusion, and high time consumption are still the major problems for CNN applications in large-scale fine land cover mapping. In this study, a Spatial-Convolution Spectral-Transformer Interactive Network (SCSTIN) was proposed to integrate 2D-CNN and Transformer into a dual-branch network to enhance feature extraction capabilities by exploring spatial context information and spectral sequence signatures in a targeted manner. In addition, spatial-spectral interactive fusion (SSIF) units and category-adaptive weighting (CAW) as two feature fusion modules were also adopted between and after the two feature extraction branches to improve efficiency in feature fusion. The ZY1-02D hyperspectral imagery was collected to conduct the experiments in the study area of the eastern foothills of the Helan Mountains (EFHLM), covering an area of about 8800 km², which is the largest hyperspectral dataset as far as we know. To explore the potential of the proposed network in terms of accuracy and efficiency, SCSTIN models with different depths (SCSTIN-4 and SCSTIN-2) were performed. The results suggest that compared with the previous eight advanced hyperspectral image classifiers, both SCSTIN models achieved satisfactory performance in accuracy and efficiency aspects with low complexity, where SCSTIN-4 achieved the highest accuracy and SCSTIN-2 obtained higher efficiency. Accordingly, the SCSTIN models are reliable for large-scale fast refined land cover classification and mapping. In addition, the spatial distribution pattern of diverse ground objects in EFHLM is also analyzed.