This study analyzed the vertical distribution of gravimetric water content (GWC), relative water content (RWC), and equivalent water thickness (EWT) in winter wheat during heading and early ripening stages, and evaluated the position of leaf number at which Vegetation Indexes (VIs) can best retrieve canopy water-related properties of winter wheat. Results demonstrated that the vertical distribution of these properties followed a near-bell-shaped curve with the highest values at the intermediate leaf position. GWC of the top three or four leaves during the heading stage and the top two or three leaves during the early ripening stage can represent the GWC of the whole canopy, but the RWC and EWT of the whole canopy should be calculated based on the top four leaves. At leaf level, the analysis demonstrated strong relationships between EWT and VIs for the top leaf layer, but for GWC_D, GWC_F, and RWC, the strongest relationships with VIs were found in the intermediate leaf layers. At canopy level, VIs provided the most accurate estimation of GWCfor the top three or four leaves. Water absorption-based VIs could estimate canopy EWT of winter wheat for the top four leaves, but the suitable bands sensitive to water absorptions should be carefully selected for the studied species.

This study quantified the impacts of land-use/cover change (LUCC) on gross primary production (GPP) during 2000–2013 in a typical densely urbanized Chinese city, Wuhan. GPP was estimated at 30-m spatial resolution using annual land cover maps, meteorological data of the baseline year, and the normalized difference vegetation index (NDVI), which was generated with the spatial and temporal adaptive reflectance fusion model (STARFM) based on Landsat and MODIS images. The results showed that approximately 309.95 Gg C was lost over 13 years, which was mainly due to the conversion from cropland to built-up areas. The interannual variation of GPP was affected by the change of vegetation composition, especially the increasing relative fraction of forests. The loss of GPP due to the conversion from forest to cropland fluctuated through the study period, but showed a sharp decrease in 2007 and 2008. The gain of GPP due to the conversion from cropland to forest was low between 2001 and 2009, but increased dramatically between 2009 and 2013. The change rate map showed an increasing trend along the highways, and a decreasing trend around the metropolitan area and lakes. The results indicated that carbon consequences should be considered before land management policies are put forth.

Hyperspectral Images (HSIs) contain enriched information due to the presence of various bands, which have gained attention for the past few decades. However, explosive growth in HSIs’ scale and dimensions causes “Curse of dimensionality” and “Hughes phenomenon”. Dimensionality reduction has become an important means to overcome the “Curse of dimensionality”. In hyperspectral images, labeled samples are more difficult to collect because they require many labor and material resources. Semi-supervised dimensionality reduction is very important in mining high-dimensional data due to the lack of costly-labeled samples. The promotion of the supervised dimensionality reduction method to the semi-supervised method is mostly done by graph, which is a powerful tool for characterizing data relationships and manifold exploration. To take advantage of the spatial information of data, we put forward a novel graph construction method for semi-supervised learning, called SLIC Superpixel-based $l_{2,1}$ -norm Robust Principal Component Analysis (SURPCA_2,1), which integrates superpixel segmentation method Simple Linear Iterative Clustering (SLIC) into Low-rank Decomposition. First, the SLIC algorithm is adopted to obtain the spatial homogeneous regions of HSI. Then, the $l_{2,1}$ -norm RPCA is exploited in each superpixel area, which captures the global information of homogeneous regions and preserves spectral subspace segmentation of HSIs very well. Therefore, we have explored the spatial and spectral information of hyperspectral image simultaneously by combining superpixel segmentation with RPCA. Finally, a semi-supervised dimensionality reduction framework based on SURPCA_2,1 graph is used for feature extraction task. Extensive experiments on multiple HSIs showed that the proposed spectral-spatial SURPCA_2,1 is always comparable to other compared graphs with few labeled samples.

Classification of Hyperspectral Images (HSIs) has gained attention for the past few decades. In remote sensing image classification, the labeled samples are insufficient or hard to obtain; however, the unlabeled ones are frequently rich and of a vast number. When there are no sufficient labeled samples, overfitting may occur. To resolve the overfitting issue, in this present work, we proposed a novel approach for HSI feature extraction, called robust regularized Block Low-Rank Discriminant Analysis (BLRDA), which is a robust and efficient feature extraction method to improve the HSIs’ classification accuracy with few labeled samples. To reduce the exponentially growing computational complexity of the low-rank method, we divide the entire image into blocks and implement the low-rank representation for each block respectively. Due to the symmetric matrix requirements for the regularized graph of discriminant analysis, the k-nearest neighbor is applied to handle the whole low-rank graph integrally. The low-rank representation and the kNN can maximally capture and preserve the global and local geometry of the data, respectively, and the performance of regularized discriminant analysis feature extraction can be apparently improved. Extensive experiments on multi-class hyperspectral images show that the proposed BLRDA is a very robust and efficient feature extraction method. Even with simple supervised and semi-supervised classifiers (nearest neighbor and SVM) and randomly given parameters, the feature extraction method achieves significant results with few labeled samples, which shows better performance than similar feature extraction methods.