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.
With the rapid urbanization of China in recent years, urban development has entered a new stage that focuses on improving the quality of growth. During this process, the excessive emphasis on economic growth and the neglect of spiritual and cultural aspects have led to various issues, such as cultural homogenization and urban identity crises. This study examined the development patterns behind this phenomenon by focusing on land specifically designated for urban cultural functions. Through the lens of cultural urban land use (CULU), a comparative study was conducted between the ancient city of Xi’an and the emerging city of Shenzhen. The study collected and processed point of interest (POI) and area of interest (AOI) data from both Xi’an and Shenzhen and analyzed the spatial characteristics of CULU using quantitative statistical methods. The analysis revealed multidimensional differentiation between the two cities in terms of value characteristics, historical characteristics, functional characteristics, and social consensus characteristics. Furthermore, the study applied the Spatial Circle Layer model (SCL) to analyze the spatial distribution differences in these characteristics between Xi’an and Shenzhen and identified key factors influencing these characteristics, such as the “formation and spatial distribution of key CULU” and the “historical continuity of urban space”. These findings were synthesized into the “anchoring–layering mechanism”. Our research explores why land designated for urban cultural functions exhibits different patterns in different cities, providing effective theoretical support for the planning and construction of such land in future urban development.