Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful in plenty of remote sensing tasks. The current deep learning-based change detection method is mainly based on conventional long short-term memory (Conv-LSTM), which does not have spatial characteristics. Since change detection is a process with both spatiality and temporality, it is necessary to propose an end-to-end spatiotemporal network. To achieve this, Conv-LSTM, an extension of the Conv-LSTM structure, is introduced. Since it shares similar spatial characteristics with the convolutional layer, L-UNet, which substitutes partial convolution layers of UNet-to-Conv-LSTM and Atrous L-UNet (AL-UNet), which further using Atrous structure to multiscale spatial information is proposed. Experiments on two data sets are conducted and the proposed methods show the advantages both in quantity and quality when compared with some other methods.

Coastal zones, where land meets ocean, are home to a large portion of the global population and play a crucial role in human survival and development. These regions are shaped by complex geological processes and influenced by both natural and anthropogenic factors, making effective management essential for addressing population growth, environmental degradation, and resource sustainability. However, the inherent complexity of coastal zones complicates their study, and traditional in situ methods are often inefficient. Remote sensing technologies have significantly advanced coastal zone research, with different sensors providing diverse perspectives. These sensors are typically used for classification tasks (e.g., coastline extraction, coastal classification) and retrieval tasks (e.g., aquatic color, wetland monitoring). Recent improvements in resolution and the advent of deep learning have led to notable progress in classification, while platforms like Google Earth Engine (GEE) have enabled the development of high-quality, global-scale products. This paper provides a comprehensive overview of coastal zone interpretation, discussing platforms, sensors, spectral characteristics, and key challenges while proposing potential solutions for future research and management.

Remote sensing building extraction is of great importance to many applications, such as urban planning and economic status assessment. Deep learning with deep network structures and back-propagation optimization can automatically learn features of targets in high-resolution remote sensing images. However, it is also obvious that the generalizability of deep networks is almost entirely dependent on the quality and quantity of the labels. Therefore, building extraction performances will be greatly affected if there is a large intra-class variation among samples of one class target. To solve the problem, a subdivision method for reducing intra-class differences is proposed to enhance semantic segmentation. We proposed that backgrounds and targets be separately generated by two orthogonal generative adversarial networks (O-GAN). The two O-GANs are connected by adding the new loss function to their discriminators. To better extract building features, drawing on the idea of fine-grained image classification, feature vectors for a target are obtained through an intermediate convolution layer of O-GAN with selective convolutional descriptor aggregation (SCDA). Subsequently, feature vectors are clustered into new, different subdivisions to train semantic segmentation networks. In the prediction stages, the subdivisions will be merged into one class. Experiments were conducted with remote sensing images of the Tibet area, where there are both tall buildings and herdsmen’s tents. The results indicate that, compared with direct semantic segmentation, the proposed subdivision method can make an improvement on accuracy of about 4%. Besides, statistics and visualizing building features validated the rationality of features and subdivisions.

Currently, the world is in a period of urbanization that will accelerate the processes of land-use cover and ecological change. Thus, establishing a land-use and land-cover change (LUCC) prediction and simulation model is of great significance for understanding the process of urban change and assessing its ecological impact. In previous studies, LUCC prediction models have been mainly based on cellular automata structures that calculate a future state pixel by pixel through transition rules. Because these transition rules are usually based on the global state and each pixel is calculated according to these fixed rules, the results of these methods have room for improvement in terms of generating details and heterogeneity. In this article, a generative adversarial network (GAN)-based LUCC prediction model using multiscale local spatial information is proposed. The model is based on a pix2pix GAN and an attention structure that predicts future land use through multiscale local spatial information. To validate our model, Shenzhen, a region that is experiencing rapid urbanization, was chosen as the source of the experimental data. The results indicate that the proposed method achieved the highest accuracy in both short-time interval and long-time interval scenarios. In addition, the results of the proposed method were also closest to the ground truth from the perspective of the landscape pattern.

Nearshore bathymetry plays an essential role in various applications, and satellite-derived bathymetry (SDB) presents a promising approach due to its extensive coverage and comprehensive bathymetric map production capabilities. Nevertheless, existing retrieval techniques, encompassing physics-based and pixel-based statistical methodologies such as support vector regression (SVR), band ratio, and Kriging regression, exhibit limitations stemming from the intricate water reflectance process and the under-exploitation of the spatial component inherent in SDB. To surmount these obstacles, we introduce employment of deep convolutional networks (DCNs) for SDB in this study. We assembled multiple scenes utilizing networks with varying scale emphasis and an assortment of satellite datasets characterized by distinct spatial and spectral resolutions. Our findings reveal that these deep learning models yield high-caliber bathymetry outcomes, with nonlinear normalization further mitigating residuals in shallow water regions and substantially enhancing retrieval performance. A comparative analysis with the prevalent SVR technique substantiates the efficacy of the proposed methodology.