Zhidian Jiang

Blue–green infrastructure (BGI) is an important nature-based solution for mitigating urban overheating, and machine learning (ML) techniques offer strong potential in capturing the complex, nonlinear relationships between influencing factors and BGI cooling effects. This study presents a systematic review of 54 journal articles published between 2015 and 2025 that applied ML to assess the cooling performance of BGI. We classified BGI into seven types across three spatial scales, evaluated the metrics and indicators used to characterize the BGI cooling effects, and examined the ML algorithms, model performance, and data sources adopted in reviewed studies. We found that 2D BGI morphology metrics and BGI physical and biological metrics are most frequently used as model inputs, whereas 3D morphology metrics are used less. Surface temperature-related indicators dominate model outputs, while air temperature and human heat stress indicators, which better reflect heat health hazards, remain underutilized. In terms of methodology, ML applications are primarily based on artificial neural networks for temporal regression and tree ensemble algorithms for spatial regression. Building on these findings, we identify key research gaps and advocate that future research should develop comprehensive multi-source and multi-scale BGI databases, improve model transparency and generalizability, and integrate energy-balance information into BGI-ML studies. Finally, we propose a systematic BGI-ML modeling framework to guide future research in this field.

Open residential neighbourhood (ORN) and vertical greening system (VGS) are two emerging urban design strategies in Southern Chinese cities. This paper numerically analysed the potential in thermal comfort improvement of these strategies. The strength and limitations of the ENVI-met model is understood through a validation against field-measured data. Then we conducted parameterized numerical simulation on the combined impacts of four types of building layout and six types of vertical greening on outdoor microclimate in a traditional urban block under renovation in Shanghai. Results indicate that the semi-enclosed layout with small building height difference and the enclosed layout are relatively beneficial; For different combinations of layout and greenery, the south-oriented vertical greening scenario yields the best thermal benefit per unit installed area, followed by the east-orientated scenario; overall, south-facing green facade allocated in semi-enclosed building layout with small height difference and enclosed building layout are recommended for optimizing pedestrian thermal comfort.

Shrinking cities have spread across the globe in recent decades, characterizing significant population loss, economic decline, and decay in spatial quality. To maintain global economic prosperity in the context of urban shrinkage and support decision making in the direction, it is necessary to accurately identify shrinking cities on a global scale. We utilize redefined natural city boundaries and the LandScan dataset to identify and map shrinking cities experiencing population loss on the globe. As a result, we have identified 5004 shrinking cities worldwide, with a total area of 126,930 km ² during 2000–2019. The ratio of which in number and in area is 27% and 22%, respectively. The shrinking cities are clustered and mainly located in Europe, Eastern Asia, and northeastern United States. There are 41 countries with more than 20 shrinking cities on the globe. The number of shrinking cities in China reached 679, which is the most. Among the 41 countries, the median value of the natural cities’ shrinking ratios of Iraq, Iran, Austria, South Africa, Russia, Georgia, and Belarus is >50%, indicating that the urban population loss in these countries is relatively serious. Our findings can be used to inform decision makers and urban planners to adjust the “growth-oriented” planning paradigm and adopt precise strategies, to form a healthier urban development.

Although there has been a rapid urbanization in China since the 1980s, the simultaneous urban shrinkage phenomenon has existed for a long time. The study of shrinking cities is particularly important for China as the current urban development has changed from physical expansion to built-up area improvement. After redefining what constitutes a city (what we term a natural city), we compared the adjusted nightlight intensity of National Polar-orbiting Partnership Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) data between 2013 and 2016 to accurately identify shrinking cities throughout China. The results indicate that there are 2,862 redefined natural cities in China and that the total area reaches 53,275 km², about 0.5% of the national territory. Based on this, we identified 798 shrinking cities with a total area of 13,839 km². After analyzing the relative position of shrinking cities and internal shrinking pixels in the geometric space, the morphological characteristics of shrinking cities were systematically classified into six patterns. The majority of shrinking cities belong to scatter shrinkage, central shrinkage, and local shrinkage; only 5% are complete shrinkage; the rest are unilateral shrinkage and peripheral shrinkage. In addition, six shrinkage causes were quantitatively classified and summarized by referring to multiple-source urban data and municipal yearbooks. To enrich the methodological system for urban shrinkage, the research provides a reminder of the need to consider the other side of urbanization (i.e., dissolution of social networks) and proposes appropriate strategies and policies to address shrinkage issues.