Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
The recognition of environmental patterns for traditional Chinese settlements (TCSs) is a crucial task for rural planning. Traditionally, this task primarily relies on manual operations, which are inefficient and time consuming. In this paper, we study the use of deep learning techniques to achieve automatic recognition of environmental patterns in TCSs based on environmental features learned from remote sensing images and digital elevation models. Specifically, due to the lack of available datasets, a new TCS dataset was created featuring five representative environmental patterns. We also use several representative CNNs to benchmark the new dataset, finding that overfitting and geographical discrepancies largely contribute to low classification performance. Consequently, we employ a semantic segmentation model to extract the dominant elements of the input data, utilizing a metric-based meta-learning method to enable the few-shot recognition of TCS samples in new areas by comparing their similarities. Extensive experiments on the newly created dataset validate the effectiveness of our proposed method, indicating a significant improvement in the generalization ability and performance of the baselines. In sum, the proposed method can automatically recognize TCS samples in new areas, providing a powerful and reliable tool for environmental pattern research in TCSs.
The recognition of environmental patterns for traditional Chinese settlements (TCSs) is a crucial task for rural planning. Traditionally, this task primarily relies on manual operations, which are inefficient and time consuming. In this paper, we study the use of deep learning techniques to achieve automatic recognition of environmental patterns in TCSs based on environmental features learned from remote sensing images and digital elevation models. Specifically, due to the lack of available datasets, a new TCS dataset was created featuring five representative environmental patterns. We also use several representative CNNs to benchmark the new dataset, finding that overfitting and geographical discrepancies largely contribute to low classification performance. Consequently, we employ a semantic segmentation model to extract the dominant elements of the input data, utilizing a metric-based meta-learning method to enable the few-shot recognition of TCS samples in new areas by comparing their similarities. Extensive experiments on the newly created dataset validate the effectiveness of our proposed method, indicating a significant improvement in the generalization ability and performance of the baselines. In sum, the proposed method can automatically recognize TCS samples in new areas, providing a powerful and reliable tool for environmental pattern research in TCSs.
This paper analyzes the relationship between out-migration from rural areas, sustainable regional development and the conservation of biodiversity. Urbanization is a key challenge for sustainable development. Will the move to cities reduce land use pressures on rural areas, and thus provide opportunities for biodiversity conservation? This paper reviews the literature on the relationship between rural out-migration and biodiversity. Generalizing statements or even predictions are rarely possible, as regional contexts differ greatly and a multitude of factors are at work. It is apparent, however, that traditional land use practices, in particular, are in decline as a result of out-migration. In some cases, this can lead to intensification, in others to abandonment, while some studies do not show any link at all. The paper then considers the case study of a peripheral biosphere reserve in Germany that is characterized by strong out-migration. Here, the urbanization tendency is evident on a smaller scale; the regional urban center consolidates, and the small communities face great challenges. At the same time, new innovative actors are emerging. It is essential for new and established actors to collaborate and jointly develop new narratives for “shrinking” regions.
The increasing trend of farmers abandoning their farmland amid urbanization poses significant challenges to sustainable agricultural development and threatens national food security. This study employs evolutionary game theory to analyze the drivers, constraints, and policy regulation strategies associated with the farmland abandonment by farmers in the context of urbanization and aging in China. The findings indicate that urbanization and demographic aging significantly influence farmers’ decisions to abandon their farmland. Government regulations, including incentives and penalties, face constraints from various factors. Farmers are often drawn to abandon their land because of the higher income potential from urban employment and land rental, coupled with the burden of farming and opportunity costs. Conversely, potential losses from land transfer income, agricultural product revenues, the quality of farmland, and lower levels of aging serve as constraints that affect farmers’ decision-making and land utilization behaviors. Furthermore, proactive regulation by local governments can effectively deter farmers from abandoning their land. However, the success of government policies in protecting farmland relies on a synergistic approach that balances incentives and regulations. Therefore, it is crucial for policymakers to consider multiple factors and adapt policy designs flexibly to align with local conditions. This study aims to provide theoretical insights and practical guidance for developing more effective and scientifically grounded farmland protection policies.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.