Predicting and assessing the vitality of public urban spaces is crucial for effective urban design, aiming to prevent issues such as “ghost streets” and minimize resource wastage. However, existing assessment methods often lack temporal dynamics or heavily rely on historical big data, limiting their ability to accurately predict outcomes for unbuilt projects. To address these challenges, this study integrates previous methodologies with observations of crowd characteristics in public spaces. It introduces the crowd-frequency hypothesis and develops an algorithm to establish a time-dimensional urban vitality dynamic prediction model. Through a case study of the Rundle Mall neighborhood in Adelaide, Australia, the effectiveness of the prediction model was validated using on-site observation sampling and comparative verification. The prediction model framework allows for the determination of urban vitality within specific time ranges by directly inputting basic information, providing valuable support to urban planners and government officials during the design and decision-making processes. It offers a cost-effective approach to achieve sustainable urban vitality construction. Furthermore, machine learning techniques, specifically the decision tree model, were applied to case data to develop a set of preliminary algorithm tools, which enable output of reference urban vitality levels (high-medium-low).

Extreme heat events have become more common and more severe during summer than ever before as a result of the warming climate in Australia. The impact of urban morphology and green coverage on outdoor thermal comfort has been the subject of extensive research, however, their link to suburban developments of different historic periods is still underexplored. This paper investigates and compares the outdoor thermal performance of ten suburban areas constructed since the late nineteenth century in Greater Adelaide, which were built to different planning ideals and concepts of their time. Microclimate models of two precedents for five development eras were constructed in ENVI-met, validated with site data related to a recent heatwave event in 2023, and then used to facilitate further investigation of the impact of development patterns on outdoor thermal comfort. This study examines how these urban patterns perform in scenarios of varying development intensity and greenery ratio. In these case studies, the distance between buildings, streets’ spatial ratio and green coverage has a significant impact on the thermal environment. The results underline the impact of solar exposure on outdoor thermal performance even in lower-density suburban areas. Some of the outcomes of the study are counter-intuitive to conventional assumptions about urban design typologies. In this comparison, for example, one of the “green” model garden city developments did not perform as well as denser 19th-century suburbs. The results can support better decision-making for future urban planning in Australia and other regions with similar climate conditions. The study shows that real performance does not always align with stated green ambitions and, urban design should consider and evaluate heat mitigation through evidence-based testing to achieve real green development.

Over the past decade, biophilic architecture has been widely developed across the Asia–Pacific region. However, there is a notable lack of research based on online public reviews focusing on mid- to high-rise biophilic buildings, especially quantitative studies combining traditional architectural design features. This study aims to fill this gap by analyzing the typical floor plans and online public reviews of nine renowned biophilic buildings in the Asia–Pacific region. Using space syntax and natural language processing tools, the design features of typical floor plans and public feedback will be analyzed separately, and their correlation will be evaluated. Additionally, the content of negative and low-score reviews will be categorized to identify issues in current biophilic building designs. The findings suggest that biophilic design can stimulate widespread public discussion, with large direct blue–green elements receiving overwhelming attention. However, biophilic elements can also lead to negative sentiments due to factors like humidity, high temperatures, mold, and insects. This study provides insights and design recommendations for future biophilic buildings, demonstrating the value of biophilic design in public reviews and emphasizing the need to balance these factors to enhance public satisfaction and acceptance.

Predicting and evaluating the vitality level of public spaces of urban design is crucial before new construction and renewal, especially for developing countries, to avoid failures like "ghost neighborhood" and reduce resource waste. However, existing assessment methods for the urban vitality are either static and ignore changes in the time dimension, or rely on historical big data and are unable to predict unbuilt projects. This study combines previous methods and crowds’ characteristics observation in public space, puts forward the crowd-frequency hypothesis and constructs an algorithm, and establishes a time-dimensional urban vitality dynamic prediction model. Taking the Rundle Mall neighborhood in Adelaide, Australia, as an example, the effec-tiveness of the prediction model was proved through on-site observation sampling comparative verification method. In addition, the decision tree model was used to conduct machine learning on the case data, and a set of algorithm programs were obtained that can directly input some basic information to obtain the urban vitality level (high-medium-low) in a certain period. It can be used as a tool to support the design and decision-making processes of urban planners and government officials, providing a low-cost way to achieve sustainable urban vitality construction of late-developing cities directly.