The real-time, accurate, and refined monitoring of urban green space status information is of great significance in the construction of urban ecological environment and the improvement of urban ecological benefits. The high-resolution technology can provide abundant information of ground objects, which makes the information of urban green surface more complicated. The existing classification methods are challenging to meet the classification accuracy and automation requirements of high-resolution images. This paper proposed a deep learning classification method for urban green space based on phenological features constraints in order to make full use of the spectral and spatial information of green space provided by high-resolution remote sensing images (GaoFen-2) in different periods. The vegetation phenological features were added as auxiliary bands to the deep learning network for training and classification. We used the HRNet (High-Resolution Network) as our model and introduced the Focal Tversky Loss function to solve the sample imbalance problem. The experimental results show that the introduction of phenological features into HRNet model training can effectively improve urban green space classification accuracy by solving the problem of misclassification of evergreen and deciduous trees. The improvement rate of F1-Score of deciduous trees, evergreen trees, and grassland were 0.48%, 4.77%, and 3.93%, respectively, which proved that the combination of vegetation phenology and high-resolution remote sensing image can improve the results of deep learning urban green space classification.

The ship detection task using optical remote sensing images is important for in maritime safety, port management and ship rescue. With the wide application of deep learning to remote sensing, a series of target detection algorithms, such as faster regions with convolution neural network feature (R-CNN) and You Only Look Once (YOLO), have been developed to detect ships in remote sensing images. These detection algorithms use fully connected layer direct regression to obtain coordinate points. Although training and forward speed are fast, they lack spatial generalization ability. To avoid the over-fitting problem that may arise from the fully connected layer, we propose a fully convolutional neural network, SDGH-Net, based on Gaussian heatmap regression. SDGH-Net uses an encoder–decoder structure to obtain the ship area feature map by direct regression. After simple post-processing, the ship polygon annotation can be obtained without non-maximum suppression (NMS) processing. To speed up model training, we added a batch normalization (BN) processing layer. To increase the receptive field while controlling the number of learning parameters, we introduced dilated convolution and added it at different rates to fuse the features of different scales. We tested the performance of our proposed method using a public ship dataset HRSC2016. The experimental results show that this method improves the recall rate of ships, and the F-measure is 85.05%, which surpasses all other methods we used for comparison.

Eliminating poverty, reducing inequality, and achieving balanced development are one of the United Nations Sustainable Development Goals. Objectively and accurately measuring regional economic vitality and development equilibrium is a pressing scientific issue that needs to be addressed in order to achieve common prosperity. Nighttime light (NTL) remote sensing data have been proven to be a good proxy variable for socio-economic development, and are widely used due to their advantages of convenient access and wide spatial coverage. Based on multi-source data, this study constructs an Economic Development Index (EDI) that comprehensively reflects regional economic vitality from two aspects, economic quality and development potential, combines the Nighttime Light Development Index (NLDI) as the evaluation indicators to measure the economic vitality and development equilibrium, analyzes the economic vitality and development equilibrium of 300 district and county units in China’s three major urban agglomerations from 2000 to 2020 and their temporal and spatial variation characteristics, and discusses the connotation of EDI and its availability. The results show the following: (1) From 2000 to 2020, the average growth rate of EDI in China’s three major urban agglomerations reached 36.32%, while the average decrease rate of NLDI reached 38.75%; both economic vitality and the development equilibrium have been continuously enhanced. Among them, the Yangtze River Delta (YRD) urban agglomeration experienced the fastest economic growth, while the Guangdong–Hong Kong–Macao Greater Bay Area (GBA) exhibited the strongest economic strength. (2) Both economic vitality and the development equilibrium in these three urban agglomerations exhibited distinct spatial agglomeration characteristics, namely center-surrounding distribution, coastal–inland distribution, and radial belt–pole distribution, respectively. (3) Over the past two decades, the economic development of these three urban agglomerations has progressed towards the pattern of regional coordinated development, pole-driven development and urban–rural integrated development. The research results can provide new research perspectives and scientific support for promoting regional balanced development, achieving sustainable development goals, and reducing inequality.

Building extraction based on remote sensing images has been widely used in many industries. However, state-of-the-art methods produce an incomplete segmentation of buildings owing to unstable multi-scale context aggregation and a lack of consideration of semantic boundaries, ultimately resulting in large uncertainties in predictions at building boundaries. In this study, efficient fine building extraction methods were explored, which demonstrated that the rational use of edge features can significantly improve building recognition performance. Herein, a fine building extraction network based on a multi-scale edge constraint (MEC-Net) was proposed, which integrates the multi-scale feature fusion advantages of UNet++ and fuses edge features with other learnable multi-scale features to achieve the effect of prior constraints. Attention was paid to the alleviation of noise interference in the edge features. At the data level, according to the improvement of copy-paste according to the characteristics of remote sensing imaging, a data augmentation method for buildings (build-building) was proposed, which increased the number and diversity of positive samples by simulating the construction of buildings to increase the generalization of MEC-Net. MEC-Net achieved 91.13%, 81.05% and 74.13% IoU on the WHU, Massachusetts and Inria datasets, and it has a good inference efficiency. The experimental results show that MEC-Net outperforms the state-of-the-art methods, demonstrating its superiority. MEC-Net improves the accuracy of building boundaries by rationally using previous edge features.

The gridded spatial distribution data of Gross Domestic Product (GDP) has a wide range of application values in many fields, such as regional economic analysis, urban planning, sustainable utilization of resources, and disaster risk assessment. However, currently the publicly accessible GDP grid datasets face limitations in terms of temporal coverage, spatial extent, and accuracy. Therefore, based on the remote sensing data of land use and nighttime light, this study developed two methods: the factor averaging method (FAM) and grid averaging method (GAM), and used Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) algorithms to jointly construct the spatial model of GDP, so as to produce China’s 1 km gridded GDP in 2020. The experimental results show the following: (1) The GAM yields higher R² values than the FAM in modeling the three industries, and therefore, it is adopted as the basis for GDP spatialization modeling. (2) XGBoost achieves higher R² values than RF in modeling primary and secondary industries, but lower R² values in modeling tertiary industry. Consequently, both methods are combined to construct the overall GDP spatialization model. (3) The accuracy of the GDP spatialization results is evaluated based on town-level GDP statistics, with an R² value of 0.78, indicating its reliable predictive capability. (4) Compared with publicly available GDP datasets, our dataset exhibits consistent spatial distribution patterns and aggregation trends. Furthermore, our GDP dataset provides a more detailed depiction of variations within county-level administrative units. Therefore, the method proposed in this study offers a valuable option for generating a gridded GDP dataset, visually displaying the uneven economic development across various regions in China. It helps to uncover economic disparities among regions and provides data support for formulating differentiated support policies, so as to promote balanced regional development among regions. Furthermore, it contributes to promoting sustained, inclusive, and sustainable economic growth (SDG 8) and reducing inequalities within and among countries (SDG 10), thereby providing strong support for urban planning and sustainable development.

The effective refuge area is a key indicator in the study of emergency shelters. Accurately extracting the effective refuge area and analyzing the effectiveness of emergency shelters are of great significance for site selection, spatial distribution, and the evaluation of suitability. Beijing is one of only three capitals in the world located in a high-seismic-intensity zone of magnitude 8. The fast and accurate monitoring of effective refuge areas and an analysis of the effectiveness of emergency shelters are conducive to evacuation planning and disaster prevention and mitigation, and they promote the construction of a resilient city. However, the extraction of effective refuge areas in existing studies is not only a time-consuming and labor-intensive task but also has accuracy and efficiency problems, resulting in less precise validity analyses. In this paper, a remote sensing monitoring technology system for the effective refuge areas of emergency shelters is proposed based on multi-source data. Different methods were used to extract various land features, such as buildings and collapsed areas, water, dense areas of understory vegetation, and steep slope areas that cannot be evacuated, to obtain the effective refuge area at a detailed scale, in combination with the service radius of emergency shelters, the population distribution, and the actual road network, the criteria for effectiveness analysis were established for the effective open space ratio, capacity, per capita accessible effective refuge area, and population allocation gap. Taking the area within the Fifth Ring Road of Beijing as an example, the effectiveness of emergency shelters was analyzed at both the whole scale and a local scale. The results show that the effective refuge areas of different emergency shelters in Beijing vary significantly, with the smallest effective refuge area being located in Rings 2–3 and the largest one being located in Rings 4–5; between different regions, there are differences in the effectiveness. This study provides a feasible method for the fast, accurate, and detailed extraction of the effective refuge areas of emergency shelters and also provides a reference for emergency planning for disaster prevention and mitigation.