This paper describes the use of deep belief networks (DBNs) based on the conjugate gradient (CG) update algorithm for hyperspectral classification. DBNs perform two processes: unsupervised pre-training and supervised fine-tuning. The parameter update method in the fine-tuning stage plays a key role in optimizing the classification model. The proposed method employs CG-based fine-tuning to avoid the “zig-zagging” problem with the gradient descent algorithm and to accelerate the DBN convergence. First, the spectral features and pixel-centric spectral block features are extracted from hyperspectral images for use as the input vectors. The update variables are then calculated based on a CG algorithm and the 2-norm, and the parameters are updated during the backpropagation step of the proposed CGDBN. Two models with different CG methods are applied to a public hyperspectral image benchmark for classification experiments and analysis, and the results are compared with those from several classification methods that are currently in use. The experimental results show that the proposed classification models have advantages in terms of model convergence and low sensitivity to certain parameters. In addition, application to a hyperspectral image of coastal wetlands in the Yellow River Delta produces a satisfactory classification. The results of this study demonstrate that the proposed CG-update-based DBN provides a new approach for hyperspectral dataset classification.

Hyperspectral unmixing (HU) is widely used to process mixed pixels as an essential technology. Among them, the nonnegative matrix factorization (NMF)-based approach is one typical of the blind unmixing techniques, which can achieve endmembers and abundances simultaneously. Considering the physical meaning of the extracted endmembers, the archetypal analysis (AA) method constructs a new matrix decomposition structure with stronger interpretability than NMF. However, AA ignores the significant sparse property of abundance in unmixing. Therefore, we propose the L ₁ sparsity-constrained AA algorithm for HU. To solve the new optimization problem, we explore a new optimization method for optimizing abundance. The alternating direction method of multipliers (ADMM) is used to increase the strong convexity and convergence of the problem. Then the fast gradient method (FGM) instead of traditional gradient descent is used to speed up algorithm convergence. The experimental results in both the synthesized and real datasets show that the proposed method outperforms several sparse NMF-based and AA-based methods.

Class-incremental learning has recently received extensive research interest in remote sensing scene classification (CI-RSSC). The existing CI-RSSC methods’ superior performance seriously relies on old (base classes) and new classes (incremental classes) sampled independently from an identical distribution (dataset). In real-world RSSC scenarios, there exist significant distribution shifts between old and new classes, leading to the existing CI-RSSC methods being unable to adjust flawlessly to these new classes. In this paper, we propose a novel cross-domain class-incremental RSSC framework to solve the above-mentioned problems, termed CDCI-RSSC. Specifically, a modular sharing-based dynamic extension module is first designed, which only updates specialized modules to extract new class feature embeddings for reducing memory footprint. Then, an effective dynamic alignment guided domain adaptive module is further proposed to calculate the dynamic weights of each sample in various fields, which can minimize distribution shifts between source and target domains. Finally, a foreground enhancement module is introduced to alleviate the issue of complex background interference in RSSC by increasing the weight of critical regions. Compared with the existing CI-RSSC and CD-RSSC, our proposed CDCI-RSSC framework surmounts the challenge of handling the distribution shifts between source (base session) and target domains (incremental session) while alleviating the limitations of continuous learning of new classes. Extensive experiments on three CDCI scenarios show that the CDCI-RSSC model achieves significant performance improvements in comparison to existing CI-RSSC and CD-RSSC methods.

Wang, J.B.; Ren, G.B.; Lin, Z.Y.; Wang, A.D.; Hu, Y.B.; Li, X.M.; Wu, P.Q.; Ma, Y., and Zhang, J., 2020. Estimation and analysis of nitrogen contents in the yellow river estuary wetland using Gaofen-1 remote sensing data. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Geospatial Research of Coastal Environments. Journal of Coastal Research, Special Issue No. 102, pp. 1-10. Coconut Creek (Florida), ISSN 0749-0208.Nitrogen storage is a key indicator of vegetation growth, and the spatial distribution of nitrogen storage provides important information about the ecological status of wetland ecosystems. In this study, the aboveground vegetation nitrogen content (AVNC) in the Yellow River estuary wetland is estimated based on GaoFen-1 wide field of view (GF-1 WFV) image. Based on the spatial distribution of vegetation and the fractional vegetation coverage (FVC), the characteristics of AVNC are analyzed. On the basis of this study, the best model for estimating AVNC based on vegetation indices is the sample rate index (SRI), whose determination coefficient (R2) is 0.72 and root mean square error (RMSE) is 1.5 g/m2. Per the results of this model, the total AVNC of the study area is obtained, which is 620.6 tons.The total ANVC for freshwater Phragmites australis (FPA), Tamarix chinesis shrub (TCS), Spartina alterniflora (SA), Suaeda salsa (SS), and tidal flat Phragmites australis (TFPA) communities are 296.2 t, 115.3 t, 97.1 t, 86.3 t and 25.7 t, respectively. The average AVNC per unit area for SA, FPA, TCS, TFPA, and SS communities are 4.2 g/m2, 4.8 g/m2, 3.1 g/m2, 1.7 g/m2 and 1.4 g/m2, respectively. The correlation between FVC and AVNC is also analyzed, from which, the spatial distribution of AVNC and FVC is found to be in good agreement. Results of this study thus provide a valuable reference for determining AVNC in coastal wetland ecosystems with implications for ecological health and other ecological characteristics.