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.

Deep learning models, especially the convolutional neural networks (CNNs), are very active in hyperspectral remote sensing image classification. In order to better apply the CNN model to hyperspectral classification, we propose a CNN model based on Fletcher–Reeves algorithm (F–R CNN), which uses the Fletcher–Reeves (F–R) algorithm for gradient updating to optimize the convergence performance of the model in classification. In view of the fact that there are fewer optional training samples in practical applications, we further propose a method of increasing the number of samples by adding a certain degree of perturbed samples, which can also test the anti-interference ability of classification methods. Furthermore, we analyze the anti-interference and convergence performance of the proposed model in terms of different training sample data sets, different batch training sample numbers and iteration time. In this paper, we describe the experimental process in detail and comprehensively evaluate the proposed model based on the classification of CHRIS hyperspectral imagery covering coastal wetlands, and further evaluate it on a commonly used hyperspectral image benchmark dataset. The experimental results show that the accuracy of the two models after increasing training samples and adjusting the number of batch training samples is improved. When the number of batch training samples is continuously increased to 350, the classification accuracy of the proposed method can still be maintained above 80.7%, which is 2.9% higher than the traditional one. And its time consumption is less than that of the traditional one while ensuring classification accuracy. It can be concluded that the proposed method has anti-interference ability and outperforms the traditional CNN in terms of batch computing adaptability and convergence speed.

Climate change has profoundly affected global ecological security. The most vulnerable region on Earth is the high-latitude Arctic. Identifying the changes in vegetation coverage and glaciers in high-latitude Arctic coastal regions is important for understanding the process and impact of global climate change. Ny-Ålesund, the northern-most human settlement, is typical of these coastal regions and was used as a study site. Vegetation and glacier changes over the past 35 years were studied using time series remote sensing data from Landsat 5/7/8 acquired in 1985, 1989, 2000, 2011, 2015 and 2019. Site survey data in 2019, a digital elevation model from 2009 and meteorological data observed from 1985 to 2019 were also used. The vegetation in the Ny-Ålesund coastal zone showed a trend of declining and then increasing, with a breaking point in 2000. However, the area of vegetation with coverage greater than 30% increased over the whole study period, and the wetland moss area also increased, which may be caused by the accelerated melting of glaciers. Human activities were responsible for the decline in vegetation cover around Ny-Ålesund owing to the construction of the town and airport. Even in areas with vegetation coverage of only 13%, there were at least five species of high-latitude plants. The melting rate of five major glaciers in the study area accelerated, and approximately 82% of the reduction in glacier area occurred after 2000. The elevation of the lowest boundary of the five glaciers increased by 50–70 m. The increase in precipitation and the average annual temperature after 2000 explains the changes in both vegetation coverage and glaciers in the study period.