Synthetic aperture radar (SAR) images provide all-weather and all-time capabilities for Earth observation, which becomes highly beneficial in the field of intelligent remote sensing (RS) image interpretation. Due to these advantages, SAR images have been widely exploited in automatic building segmentation tasks under poor weather conditions, especially when disasters happen. However, compared to optical images, the semantics inherent to SAR images are less rich and interpretable due to factors such as speckle noise and imaging geometry. In this scenario, most state-of-the-art methods are focused on designing advanced network architectures or loss functions for building footprint extraction. However, few works have been oriented toward improving segmentation performance through knowledge transfer from optical images. In this article, we propose a novel method based on the DisOptNet network, which can distill the useful semantic knowledge from optical images into a network only trained with SAR data. Specifically, we first analyze the multilevel feature discrepancies between multiple stages of the networks pretrained on the two image modalities. We observe that feature discrepancies start to increase as the encoding stage gradually changes from low level to high level. Based on such observation, we reuse the early stage features and construct parallel convolutional neural network (CNN) branches that are responsible for capturing high-level domain-specific knowledge for each image modality. The optical branch is aimed at mimicking feature generation at the optical pretrained network given the input SAR images. Then, an aggregation module is introduced to calibrate and fuse the features from different modalities while generating the building segments. Extensive experiments were conducted on a large-scale multisensor all-weather building segmentation dataset with state-of-the-art methods used for comparison. Our experimental results validate the effectiveness of DisOptNet , which demonstrates great potential in the task of weather-independent building footprint generation under real scenarios. The codes of this article will be made publicly available at https://github.com/jiankang1991/TGRS_DisOptNet .

Studying the impact of social events is important for the sustainable development of society. Given the growing popularity of social media applications, social sensing networks with users acting as smart social sensors provide a unique channel for understanding social events. Current research on social events through geo-tagged social media is mainly focused on the extraction of information about when, where, and what happened, i.e., event detection. There is a trend towards the machine learning of more complex events from even larger input data. This research work will undoubtedly lead to a better understanding of big geo-data. In this study, however, we start from known or detected events, raising further questions on how they happened, how they affect people’s lives, and for how long. By combining machine learning, natural language processing, and visualization methods in a generic analytical framework, we attempt to interpret the impact of known social events from the dimensions of time, space, and semantics based on geo-tagged social media data. The whole analysis process consists of four parts: (1) preprocessing; (2) extraction of event-related information; (3) analysis of event impact; and (4) visualization. We conducted a case study on the “2014 Shanghai Stampede” event on the basis of Chinese Sina Weibo data. The results are visualized in various ways, thus ensuring the feasibility and effectiveness of our proposed framework. Both the methods and the case study can serve as decision references for situational awareness and city management.

Sea-ice segmentation is of great importance for environmental research, ship navigation, and ice hazard forecasting. Remote sensing (RS) images have been a unique data source for rapid and large-scale sea-ice monitoring. The 2021 Gaofen Challenge has offered a track of sea-ice segmentation based on optical RS images. For the initial competition, our team ranked 3rd place ( deepjoker ) in the accuracy leaderboard and the solution has been the most efficient algorithm to achieve a segmentation score above 97.79%. In this article, we briefly introduce our three strategies of the achievement including: 1) decoding the partial pretrained networks which can simultaneously capture the complex boundaries of sea ices and decrease the computational cost without the performance drop; 2) employing the classwise Dice loss for solving the gradient vanishing problem when most ground-truth maps are backgrounds; and 3) replacing the commonly exploited decoder with the one proposed by Silva et al. (2021). The main contributions are twofold: 1) an efficient and effective sea-ice segmentation method is proposed and 2) the gradient vanishing problem of binary Dice loss is investigated under some scenarios and solved by introducing its classwise version. Comparison and ablation experiments demonstrate the effectiveness of the proposed method with respect to other commonly adopted deep segmentation models.

Regional development differences are a universal problem in the economic development process of countries around the world. In recent decades, China has experienced rapid urban development since the implementation of the reform and opening-up policy. However, development differs across regions, triggering the migration of laborers from underdeveloped areas to developed areas. The interaction between regional development differences and Spring Festival has formed the world’s largest cyclical migration phenomenon, Spring Festival travel. Studying the migration pattern from public spatiotemporal behavior can contribute to understanding the differences in regional development. This paper proposes a geospatial network analytical framework to quantitatively characterize the imbalance of urban/regional development based on Spring Festival travel from the perspectives of complex network science and geospatial science. Firstly, the urban development difference is explored based on the intercity population flow difference ratio, PageRank algorithm, and attractiveness index. Secondly, the community detection method and rich-club coefficient are applied to further observe the spatial interactions between cities. Finally, the regional importance index and attractiveness index are used to reveal the regional development imbalance. The methods and findings can be used for urban planning, poverty alleviation, and population studies.

The spatial pattern is a kind of typical structural knowledge that reflects the distribution characteristics of object groups. As an important semantic pattern of road networks, the city center is significant to urban analysis, cartographic generalization and spatial data matching. Previous studies mainly focus on the topological centrality calculation of road network graphs, and pay less attention to the delineation of main centers. Therefore, this study proposes an automatic recognition method of main center pattern in road networks. We firstly extract the main clusters from road nodes by improving the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) with fuzzy set theory. Moreover, the center area is generated with road meshes according to the area ratio with the covering discs of the main clusters. This proposed algorithm is applied to the road networks of a monocentric city and polycentric city respectively. The results show that our method is effective for identifying the main center pattern in the road networks. Furthermore, the contrast experiments demonstrate our method’s higher accuracy.