Based on annual average PM_2.5 gridded dataset, this study first analyzed the spatiotemporal pattern of PM_2.5 across Mainland China during 1998–2012. Then facilitated with meteorological site data, land cover data, population and Gross Domestic Product (GDP) data, etc., the contributions of latent geographic factors, including socioeconomic factors (e.g., road, agriculture, population, industry) and natural geographical factors (e.g., topography, climate, vegetation) to PM_2.5 were explored through Geographically Weighted Regression (GWR) model. The results revealed that PM_2.5 concentrations increased while the spatial pattern remained stable, and the proportion of areas with PM_2.5 concentrations greater than 35 μg/m³ significantly increased from 23.08% to 29.89%. Moreover, road, agriculture, population and vegetation showed the most significant impacts on PM_2.5. Additionally, the Moran’s I for the residuals of GWR was 0.025 (not significant at a 0.01 level), indicating that the GWR model was properly specified. The local coefficient estimates of GDP in some cities were negative, suggesting the existence of the inverted-U shaped Environmental Kuznets Curve (EKC) for PM_2.5 in Mainland China. The effects of each latent factor on PM_2.5 in various regions were different. Therefore, regional measures and strategies for controlling PM_2.5 should be formulated in terms of the local impacts of specific factors.

Deep learning (DL) has shown great potential for hyperspectral image (HSI) classification due to its powerful ability of nonlinear modeling and end-to-end optimization. However, DL models easily get trapped into overfitting due to limited training labels since the labeling process is time-consuming and laborious in a real classification scenario. To overcome this issue, we propose a novel spectral–spatial Siamese network (S3Net) for few-shot HSI classification. First, a lightweight spectral–spatial network (SSN) composed of 1-D and 2-D convolution is proposed to extract spectral–spatial features. Second, S3Net is constructed by two SSNs in dual branches, which can augment the training set by feeding sample pairs into each branch and thus enhancing the model separability. To provide more features for the model, differentiated patches are fed into each branch, where negative samples are randomly selected to avoid redundancy. Finally, a weighted contrastive loss is designed to promote the model to fit in the right direction by focusing on sample pairs that are hardly to be identified. Moreover, another adaptive cross-entropy loss is conceived to learn the fusion ratio of the two branches. Experiments based on three commonly used HSI datasets demonstrate that S3Net outperforms traditional and state-of-the-art DL-based HSI classification methods under a few-shot training scenario. In addition, the weighted contrastive loss and the adaptive cross-entropy loss jointly improve the discrimination power of the model.

Convolutional neural network (CNN) has exhibited enormous potentials in hyperspectral image (HSI) classification owing to excellent locally modeling ability. Although excellent performance of CNN-based methods has been witnessed, there still have some limitations of their internal network backbone. On the one hand, modeling long-distance context dependencies is an inborn defect, which leads to receptive field limitation and insufficient feature capture in HSI. On the other hand, CNN-based methods usually need various sample distribution to train and cannot infer dynamically, which may not capture the inherent changes of HSI data well. To overcome the abovementioned issues, we propose a novel local transformer with spatial partition restore network (SPRLT-Net) for HSI classification. First, local transformer is introduced to obtain the spatial attention weights dynamically by measuring the similarity between related pixel pairs. Second, a spatial partition restore (SPR) module is designed to split the input patch into several overlapping continuous subpatches as sequential. With the obtained attention weights at hand, the SPR module restores the sequential to the original patch. Finally, a fully connected layer is used for classification. SPRLT-Net can capture global context dependencies, and the dynamical attention weights can adapt the inherent changes of HSI spatial pixels. Experimental results based on spatially disjoint samples and randomly selected samples of five benchmark datasets demonstrate that SPRLT-Net outperforms the other state-of-the-art methods in terms of classification accuracy, generalization performance, and computational complexity.

Recently, deep learning (DL) is of great interest in hyperspectral image (HSI) classification. Although many effective frameworks exist in the literature, the generally limited availability of training samples poses great challenges in applying DL to HSI classification. In this paper, we present a novel DL framework, namely, semisupervised stacked autoencoders (Semi-SAEs) with cotraining, for HSI classification. First, two SAEs are pretrained based on the hyperspectral features and the spatial features, respectively. Second, fine-tuning is alternatively conducted for the two SAEs in a semisupervised cotraining fashion, where the initial training set is enlarged by designing an effective region growing method. Finally, the classification probabilities obtained by the two SAEs are fused using a Markov random field model solved by iterated conditional modes. Experimental results based on three popular hyperspectral data sets demonstrate that the proposed method outperforms other state-of-the-art DL methods.

Deep learning (DL) has exhibited huge potentials for hyperspectral image (HSI) classification due to its powerful nonlinear modeling and end-to-end optimization characteristics. Although the superior performance of DL-based methods has been witnessed, some limitations can still be found. On the one hand, existing DL frameworks usually resorted to first-order statistical features, whereas they rarely considered second-order or higher order statistical features. On the other hand, the optimization of complex hyperparameters (e.g., the layer number and convolutional kernel size) is time-consuming and a very tough task, making the designed DL framework unexplainable. To overcome these challenges, we propose a novel attention-based second-order pooling network (A-SPN). First, a first-order feature operator is designed to model the spectral–spatial information of HSI. Second, an attention-based second-order pooling (A-SOP) operator is designed to model discriminative and representative features. Finally, a fully connected layer with softmax loss is used for classification. The proposed framework can obtain second-order statistical features in an end-to-end manner. In addition, A-SPN is free of complex hyperparameters tuning, making it more explainable and easily equipped for classification tasks. Experimental results based on three common hyperspectral data sets demonstrate that A-SPN outperforms other traditional and state-of-the-art DL-based HSI classification methods in terms of generalization performance with limited training samples, classification accuracy, convergence rate, and computational complexity.