Amid rapid urbanization and globalization, rural zones in many countries have undergone dramatic shifts. Although the future development of cultural landscapes is clear, their planning and management are uncertain. The Chengdu Plain is one of the most prosperous in China, which is home to well-developed irrigation and drainage systems, with the earliest history of planting found in Sichuan Province. The Chengdu Plain’s unique farming landscape is an important human resource that represents the natural integration of the material and spiritual forms in the farming era. This study takes the unique farming settlements in Dujiangyan Irrigation District as the research object and analyzes the culture, human environment, and spatial order of the Linpan settlement based on the system theory. From the hierarchical structure of each individual Linpan settlement to the spatial layout of the Linpan community, the changes in the relationship between humans and land in the farming area are explored to explain the sustainability of the rural cultural landscape. With long-term field research, the rural geographic information database is built as a basis for the identification and classification of Linpan Cultural landscape types. The results show that between 2005−2018, the Linpan of Juyuan Town illustrated a decreasing trend, and about six Linpan settlements disappeared per square kilometer. The change in the type of Linpan landscape is spatially unbalanced, which is mainly due to the difference between regional development and residents’ needs. This study introduces the concept of “demand” and “restriction” in sustainable development to explore a future strategy of maintaining the cultural landscape, which is expected to provide a basis for future policy formulation to protect the traditional rural landscape.

Quantitative assessment of urban vibrancy is crucial to understanding urban development and promoting sustainability, especially for rapidly developing areas and regions that have experienced post-disaster reconstruction. Taking Dujiangyan City, the hardest-hit area of the earthquake, as an example, this paper quantifies the urban economic, social, and cultural vibrancy after reconstruction by the use of multi-source data, and conducts a geographic visualization analysis. The purpose is to establish an evaluation framework for the relationship between the urban built environment elements and vibrancy in different dimensions, to evaluate the benefits of post-disaster restoration and reconstruction. The results show that the urban vibrancy reflected by classified big data can not be completely matched due to the difference in the data generation and collection process. The Criteria Importance Though Inter-criteria Correlation and entropy (CRITIC-entropy) method is used to construct a comprehensive model is a better representation of the urban vibrancy spatial characteristics. On a global scale, comprehensive vibrancy demonstrates high continuity and a bi-center structure. In the old town, the distribution of various urban vibrancies show diffusion characteristics, while those in the new district demonstrated a high degree of aggregation, and the comprehensive vibrancy is less sensitive to land-use mixture and more sensitive to residential land.

Housing reconstruction plays a crucial role in renovating disaster-hit areas. Rural areas are considerably different from urban areas in terms of geographic environment, building size, residential culture, and social organization. Therefore, post-disaster recovery and reconstruction models for urban areas cannot be applied directly to disaster-hit rural areas. This study, based on the experience of rural housing reconstruction after the Wenchuan earthquake, identified key strategic issues in housing reconstruction that must be addressed to achieve the goal of “building back better” in the future. By taking the experience of Dujiangyan as our reference, the study found that the following strategies are important for successful housing reconstruction in rural areas: (1) actively involve disaster victims through a participatory institutional design; (2) coordinate the interests of governments, markets, and disaster victims and the functions of living, production, and ecology through a classified housing reconstruction system; and (3) activate the quota for rural collective construction land and create a new source of funding for housing reconstruction through the market circulation of urban-rural land. Additionally, in the context of urban-rural integration, changes in land use can lead to rural spatial reconstruction and sustainable regional development, providing a reference for formulating optimal post-disaster reconstruction strategies.

Urban-safety perception is crucial for urban planning and pedestrian street preference studies. With the development of deep learning and the availability of high-resolution street images, the use of artificial intelligence methods to deal with urban-safety perception has been considered adequate by many researchers. However, most current methods are based on the feature-extraction capability of convolutional neural networks (CNNs) with large-scale annotated data for training, mainly aimed at providing a regression or classification model. There remains a lack of interpretable and complete evaluation systems for urban-safety perception. To improve the interpretability of evaluation models and achieve human-like safety perception, we proposed a complete decision-making framework based on reinforcement learning (RL). We developed a novel feature-extraction module, a scalable visual computational model based on visual semantic and functional features that could fully exploit the knowledge of domain experts. Furthermore, we designed the RL module—comprising a combination of a Markov decision process (MDP)-based street-view observation environment and an intelligent agent trained using a deep reinforcement-learning (DRL) algorithm—to achieve human-level perception abilities. Experimental results using our crowdsourced dataset showed that the framework achieved satisfactory prediction performance and excellent visual interpretability.

Ongoing global climate change, marked by sustained warming and extreme weather events, poses a severe threat to both the Earth’s ecosystems and human communities. Traditional settlements that underwent natural selection and evolution developed a unique set of features to adapt to and regulate the local climate. A comprehensive exploration of the spatial patterns and mechanisms of the adaptation of these traditional settlements is crucial for investigating low-energy climate adaptation theories and methods as well as enhancing the comfort of future human habitats. This study used numerical simulations and field measurements to investigate the air temperature, relative humidity, wind speed, wind direction, and thermal comfort of traditional settlements in Western Sichuan Plain, China, and uncovered their climate suitability characteristics to determine the impact mechanisms of landscape element configurations (building height, building density, tree coverage, and tree position) and spatial patterns on microclimates within these settlements. The results revealed the structural and layout strategies adopted by traditional settlements to adapt to different climatic conditions, providing valuable insights for future rural protection and planning and enhancing climate resilience through natural means. These findings not only contribute to understanding the climate adaptability of Earth’s ecosystems and traditional settlements but also offer new theories and methods to address the challenges posed by climate change.