Physical urban boundaries (PUBs) are basic geographic information data for defining the spatial extent of urban landscapes with non-agricultural land and non-agricultural economic activities. Accurately mapping PUBs provides a spatiotemporal database for urban dynamic monitoring, territorial spatial planning, and ecological environment protection. However, traditional extraction methods often have problems, such as subjective parameter settings and inconsistent cartographic scales, making it difficult to identify PUBs objectively and accurately. To address these problems, we proposed a self-supervised learning approach for PUB extraction. First, we used nighttime light and OpenStreetMap road data to map the initial urban boundary for data preparation. Then, we designed a pretext task of self-supervised learning based on an unsupervised mutation detection algorithm to automatically mine supervised information in unlabeled data, which can avoid subjective human interference. Finally, a downstream task was designed as a supervised learning task in Google Earth Engine to classify urban and non-urban areas using impervious surface density and nighttime light data, which can solve the scale inconsistency problem. Based on the proposed method, we produced a 30 m resolution China PUB dataset containing six years (i.e., 1995, 2000, 2005, 2010, 2015, and 2020). Our PUBs show good agreement with existing products and accurately describe the spatial extent of urban areas, effectively distinguishing urban and non-urban areas. Moreover, we found that the gap between the national per capita GDP and the urban per capita GDP is gradually decreasing, but regional coordinated development and intensive development still need to be strengthened.

Knowing the distributions and changes in global wetlands and their conversion to other land cover types could facilitate our understanding of wetland development, causes of variations, and decision-making for restoration and protection. This study aimed to comprehensively analyze the changes in wetland distributions at global, continental, typical regional, and national scales and the conversions between wetlands and other land cover types in the last 20 years. This study used GlobeLand30 (GL30) data with a 30 m resolution for the years 2000, 2010, and 2020. The main findings of this study are as follows: (1) the area of wetlands continued to increase globally from 2000 to 2020, with a total increase of approximately 4%. Wetland changes from 2010 to 2020 were more significant than those from 2000 to 2010. The regions with significant wetland changes were mainly in the north middle- and high-latitude, and the equatorial middle- and low-latitude, and Oceania and North America were the continents with the highest increase and decrease, respectively; (2) the major conversion of wetlands was mainly natural land cover types, including forest, grassland, water, and tundra, and there were minor conversions due to human activities, including the conversion of wetlands to cropland (~4600 km²) and artificial land (~3400 km²); (3) from 2000 to 2020, the increase in global wetlands was uneven, while the decrease was nearly even at a national scale. Australia had the highest increase due to the conversions from grass, bare land, and water, and Canada had the highest decrease due to the conversion into tundra and forest. The analysis results could more comprehensively characterize the distributions and changes of global wetlands, which may provide basic information and knowledge for related research work and policymaking.

Map annotation interpretation is crucial for geographic information extraction and intelligent map analysis. This study addresses the challenges associated with interpreting Chinese map annotations, specifically visual complexity and data scarcity issues, by proposing a hybrid intelligence-based multi-source unstructured Chinese map annotation interpretation method (HI-CMAIM). Firstly, leveraging expert knowledge in an innovative way, we constructed a high-quality expert knowledge-based map annotation dataset (EKMAD), which significantly enhanced data diversity and accuracy. Furthermore, an improved annotation detection model (CMA-DB) and an improved annotation recognition model (CMA-CRNN) were designed based on the characteristics of map annotations, both incorporating expert knowledge. A two-stage transfer learning strategy was employed to tackle the issue of limited training samples. Experimental results demonstrated the superiority of HI-CMAIM over existing algorithms. In the detection task, CMA-DB achieved an 8.54% improvement in Hmean (from 87.73% to 96.27%) compared to the DB algorithm. In the recognition task, CMA-CRNN achieved a 15.54% improvement in accuracy (from 79.77% to 95.31%) and a 4-fold reduction in NED (from 0.1026 to 0.0242), confirming the effectiveness and advancement of the proposed method. This research not only provides a novel approach and data support for Chinese map annotation interpretation but also fills the gap of high-quality, diverse datasets. It holds practical application value in fields such as geographic information systems and cartography, significantly contributing to the advancement of intelligent map interpretation.