The applicability of deep learning to remote sensing is rapidly increasing in accordance with the improvement in spatiotemporal resolution of satellite images. However, unlike satellite images acquired in near-real-time over wide areas, there are limited amount of labeled data used for model training. In this article, three kinds of deep learning applications-data augmentation, semisupervised classification, and domain-adapted architecture-were tested in an effort to overcome the limitation of insufficient labeled data. Among the diverse tasks that can be used for classification, rice paddy detection in South Korea was performed for its ability to fully utilize the advantages of deep learning and high spatiotemporal image resolution. In the process of designing each application, the domain knowledge of remote sensing and rice phenology was integrated. Then, all possible combinations of the three applications were examined and evaluated with pixel-based comparisons in various environments and city-level comparisons using national statistics. The results of this article indicated that all combinations of the applications can contribute to increase classification performance, even though the uncertainty involved in imitating or utilizing unlabeled data remains. As the effectiveness of the proposed applications was experimentally confirmed, enhancement in the applicability of deep learning was expected in various remote sensing areas. In particular, the proposed applications would be significant when they are applied to a wide range of study areas and highresolution images, as they tend to require a large amount of learning data from diverse environments, owing to high intraclass heterogeneity.
Industrial and technological development have contributed significantly to causing environmental crises, such as climate change and land degradation. To address these environmental challenges, nature-based solutions (NBS) have gained increased attention over conventional technical responses. This study derived conceptual linkages from NBS application to resilience promotion, and subsequently, to the achievement of sustainable development goals (SDGs). The study was conducted to reveal that NBS activities are an essential approach that determines the balance between human development and nature conservation. In this paper, we compare four case studies, one domestic reforestation project and three international afforestation projects, all of which had forest-related NBS experiences and were conducted by the Republic of Korea. All four projects were found to have an impact on environmental and socio-economic resilience. These impacts were qualitatively assessed through resilience indicator evaluations. Subsequently, the resilience indicators were matched with the targets of the SDGs. NBS initiatives designed to include various natural and social elements promoted the resilience of ecosystems and society and address a broader spectrum of SDGs. Further efforts to establish region-specific promotional models, identify resilience indicators, and collect scientific data are recommended for quantitatively assessing the NBS initiatives.
Faced with the prospect that the impact of the COVID-19 pandemic and climate change will be far-reaching and long-term, the international community is showing interest in urban green space (UGS) and urban green infrastructure utilization as a solution. In this study, we investigated how citizens’ perceptions and use of UGS have changed during COVID-19. We also collected their ideas on how UGS can raise its usability. As a result, more people became to realize the importance of UGS. In particular, the urban environmental purification function from UGS was recognized as giving great benefits to respondents. On the other hand, the patterns of UGS use were mixed with decreasing UGS use to maintain social distancing or increasing UGS use to maintain health or substitute other restricted facilities. More than half of respondents had their UGS visit patterns impacted by COVID-19. In particular, the increase rate of UGS use was rather high in the group that seldom used UGS before COVID-19. In addition, they increased the use of UGS to replace other limited facilities, and thus tended to demand an increase in rest facilities. Based on these results, this paper suggested securing social support and sustainability for the policy by reflecting users’ demand in landscape planning related to the increase of UGS in the city. This study can contribute to improving the resilience of UGS and the sustainability of urban space planning.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.