Accurate, detailed, and up-to-date information on cropland extent is crucial for provisioning food security and environmental sustainability. However, because of the complexity of agricultural landscapes and lack of sufficient training samples, it remains challenging to monitor cropland dynamics at high spatial and temporal resolutions across large geographical extents, especially for regions where agricultural land use is changing dramatically. Here we developed a cost-effective annual cropland mapping framework that integrated time-series Landsat satellite imagery, automated training sample generation, as well as machine learning and change detection techniques. We implemented the proposed scheme to a cloud computing platform of Google Earth Engine and generated a novel dataset of China's annual cropland at a 30 m spatial resolution (namely CACD). Results demonstrated that our approach was capable of tracking dynamic cropland changes in different agricultural zones. The pixel-wise F₁ scores for annual maps and change maps of CACD were 0.79 ± 0.02 and 0.81, respectively. Further cross-product comparisons, including accuracy assessment, correlations with statistics, and spatial details, highlighted the precision and robustness of CACD compared with other datasets. According to our estimation, from 1986 to 2021, China's total cropland area expanded by 30 300 km² (1.79 %), which underwent an increase before 2002 but a general decline between 2002 and 2015, and a slight recovery afterward. Cropland expansion was concentrated in the northwest while the eastern, central, and southern regions experienced substantial cropland loss. In addition, we observed 419 342 km² (17.57 %) of croplands that were abandoned at least once during the study period. The consistent, high-resolution data of CACD can support progress toward sustainable agricultural use and food production in various research applications. The full archive of CACD is freely available at https://doi.org/10.5281/zenodo.7936885 (Tu et al., 2023a).

Greenspace exposure metrics can allow for comparisons of green space supply across time, space, and population groups, and for inferring patterns of variation in opportunities for people to enjoy the health and recreational benefits of nearby green environments. A better understanding of greenspace exposure differences across various spatial scales is a critical requirement for lessening environmental health disparities. However, existing studies are typically limited to a single city or across selected cities, which severely limits the use of results in measuring systemic national and regional scale differences that might need policy at above individual city planning level. To close this knowledge gap, our study aims to provide a holistic assessment of multi-scale greenspace exposure across provinces, cities, counties, towns, and land parcels for the whole of China. We mapped the nationwide fractional greenspace coverage at 10 m with Sentinel-2 satellite imagery, and then modeled population-weighted greenspace exposure to examine variation of greenspace exposure across scales. Our results show a prominent scaling effect of greenspace exposure across multi-scale administrative divisions in China, suggesting, as expected, an increase in heterogeneity with finer spatial scales. We also identify an asymmetric pattern of the difference between greenspace exposure and greenspace coverage, across a geo-demographic demarcation boundary (i.e., along the Heihe-Tengchong Line). In general, the greenspace coverage rate will overestimate more realistic human exposure to greenspace in East China while underestimating in West China. We further found that, in China, more recently urbanized areas have much better greenspace exposure than older urban areas. Our study provides a spatially explicit greenspace exposure metric for discovering multi-scale greenspace exposure difference, which will enhance governments' capacity to quantify environmental justice, detect vulnerable greenspace exposure risk hotspots, prioritize greenspace management at the supra-city scale, and monitor the balance between greenspace supply and demand.

Economic, social and environmental infrastructure forms a fundamental pillar of societal development. Ensuring equitable access to infrastructure for all residents is crucial for achieving the Sustainable Development Goals, yet knowledge gaps remain in infrastructure accessibility and inequality and their associations with human health. Here we generate gridded maps of economic, social and environmental infrastructure distribution and apply population-weighted exposure models and mixed-effects regressions to investigate differences in population access to infrastructure and their health implications across 166 countries. The results reveal contrasting inequalities in infrastructure access across regions and infrastructure types. Global South countries experience only 50–80% of the infrastructure access of Global North countries, whereas their associated inequality levels are 9–44% higher. Both infrastructure access and inequality are linked to health outcomes, with this relationship being especially pronounced in economic infrastructure. These findings underscore the necessity of informed decision-making to rectify infrastructure disparities for promoting human well-being.

Understanding distributions of urban land use is of great importance for urban planning, decision support, and resource allocation. The first mapping results of essential urban land use categories (EULUC) in China for 2018 have been recently released. However, such kind of national maps may not sufficiently meet the growing demand for regional analysis. To address this shortcoming, here we proposed a segmentation-based framework named EULUC-seg to improve the mapping results of EULUC at the city scale. An object-based segmentation approach was first applied to generate the basic mapping units within urban parcels. Multiple features derived from high-resolution remotely sensed and social sensing data were updated and then recalculated within each unit. Random forest was adopted as the machine learning algorithm for classifying urban land use into five Level I classes and twelve Level II classes. Finally, an accuracy assessment was carried out based on a collection of manually interpreted samples. Results showed that our derived map achieved an overall accuracy of 87.58% for Level I, and 73.53% for Level II. The accurate and refined map of EULUC-seg is expected to better support various applications in the future.

Land cover information is critically essential for nature conservation, social management, and sustainable development. Recent advances have shown great potentials of remote sensing data in generating high-resolution land cover maps, but it remains unclear how different models, data sources, and inclusive features affect the classification results. Informing these issues, here we developed a robust framework to improve the mapping results of 10-m resolution land cover classification in Guangdong Province, China using thousands of manually collected samples, multi-source remote sensing data (Sentinel-1, Sentinel-2, and Luojia-1), and the Random Forest (RF) algorithm with a free cloud-based platform of Google Earth Engine. Results showed that an overall accuracy of 86.12% and a Kappa coefficient of 0.84 could be achieved for land cover classification in Guangdong for 2019. We found that RF models achieved better performance than classification and regression trees (CART), minimum distance (MD), and support vector machine (SVM) models. We also found that features derived from Sentinel-1 data and Sentinel-2 spectral indices greatly contributed to the classification process, while the feature of Luojia-1 data was not as much important as other configurations. A comparison between our results and several existing land cover products in terms of classification accuracy and visual interpretation further validated the effectiveness and robustness of the proposed framework. Our experiments and findings not only systematically elucidate the role of classification methods and data sources in deriving more accurate and reliable land cover maps, but also provide certain guidelines for future land cover mapping from regional to global scales.