Disentangling the effects of the built environment on urban vitality at the scale of community life circles is crucial for informing precise urban planning and design, particularly in the context of urban renewal. However, studies examining the complex relationships and spatial heterogeneity in these effects remain limited, hindering the identification of built environment characteristics that may generate sustainable benefits. Therefore, this study took Xi’an, a typical high-density city in Northwest China, as an example. The eXtreme Gradient Boosting (XGBoost) model and the SHapley Additive exPlanations (SHAP) method were utilized to reveal threshold effects and spatial correlations between the built environment and community life circles’ vitality across varying buffer zones. The results show that (1) there is a significant spatial correlation between the built environment and the core–periphery structure of community life circles’ vitality. (2) Indicators, such as facility accessibility, the floor area ratio, intersection density, and the residential land use ratio, contribute significantly to community life circles’ vitality. (3) While the micro-built environment and socio-economic factors show limited contributions, their collaboration with the macro-built environment can enhance their individual effects, highlighting the necessity of taking them into account together. These findings provide new insights into supporting community life circles’ vitality through urban planning and design.

Insufficient public service facilities in rural areas, which leads to failures in meeting the needs of villagers, has become a significant barrier to the high-quality development of rural regions. This issue is particularly acute in the Loess Plateau area, where the complex topography leads to scattered and independent village layouts, making it challenging to allocate service facilities based simply on distance and population. Aiming to arrange public service facilities efficiently and intensively from a “bottom-up” approach, this study, from the perspective of living circles, attempts to summarize the current usage and needs of villagers at the “village–town–county” levels, as well as to seek strategies for facility allocation in villages. This provides a scientific basis for optimizing the configuration of service facilities in the Loess Plateau area. Through field surveys based on questionnaires and interviews with over 60 households and more than 100 villagers, this study authentically reproduces a picture of their daily lives and summarizes their needs for well-configured services and facilities. The findings of this study include the following: (1) The village domain serves as a space of daily production and living for villagers, necessitating facilities for everyday purchases, activities, and elderly care; the town domain supplements the daily production and living needs of villagers, with a higher demand for production materials; the county domain, integrating urban and rural spaces, provides higher-level medical, educational, and other service facilities. (2) Within the village domain, villagers’ demands for facilities lean towards miniaturization and integration. With the increasingly aging population, the demand for elderly care and health facilities is becoming more urgent. Facilities such as activity rooms, fitness equipment, and stores with a wide range of products at reasonable prices can effectively improve levels of convenience and happiness in villagers’ lives. This study summarizes, from a “bottom-up” approach, the villagers’ facility layout needs within the rural living circle, providing a scientific basis for establishing a human-centered rural living circle and enhancing the quality of rural living environments.

As a result of China’s rapid urbanization, new urban districts are characterized by a superblock development paradigm that contrasts sharply with core urban areas, where service facilities remain largely congruent with the population distribution. This planning approach has resulted in a pronounced spatial mismatch, with an intensive concentration of public service facilities within commercial cores and a critical lack of facilities proximate to high-density residential clusters. Within the framework of the 15 min community life circle policy, evaluating and optimizing these configurations is imperative for mitigating such structural imbalances. Using Xi’an’s Qujiang New District as a representative empirical case, this study integrates Point of Interest (POI) geospatial data with 330 resident behavioral questionnaires to assess facility distribution and utilization patterns. The findings reveal a distinct spatial pattern of core–periphery polarization, which is significantly influenced by cultural landscapes and commercial land values. Furthermore, the utilization patterns differ markedly across age groups. The reliance of young and middle-aged groups on digital life circles should be viewed not only as a lifestyle preference but also as an adaptation to mitigate physical facility deficits. While digital services compensate for physical facility shortages, they mask the actual lack of community spaces. This further disadvantages older adults, who still rely heavily on walking to access daily services. Addressing the unique characteristics of new urban districts, this study proposes a synergistic physical–digital dual-tier system in which physical infrastructure safeguards the equity baseline, while digital platforms enhance operational efficiency, providing a scientific basis for constructing age-friendly communities.

Urban green spaces (UGSs) are considered crucial for enhancing older adults’ subjective well-being. However, limited studies have explored the synergistic effects of UGS quality and quantity on satisfaction across green spaces, residential environments, and life domains, making it challenging to uncover the multifaceted sustainable benefits of UGSs on older adults’ subjective well-being. This study drew on multi-source data and place attachment theory to depict neighborhood-accessible UGS quantity (provision, accessibility, and visibility) and quality (cognition, behavior, and affect). Through the geographical visualization of bivariate SHapley Additive exPlanations (SHAP) interaction values extracted from the trained eXtreme Gradient Boosting (XGBoost) model, and the comparison of bivariate SHAP maps with univariate SHAP maps, the study revealed the nonlinear geographic associations between UGS quantity and quality and three types of satisfaction. The results showed that when UGS quantity and quality coexisted, variations in the impact of quantity on older adults’ satisfaction were associated with quality differences. The gain effect of quality on quantity was more significant in areas with limited green space within a 500 m buffer zone. UGSs made a direct contribution to green space satisfaction, while their indirect association with life satisfaction surpassed that of residential satisfaction due to their provision of emotional qualities. This study calls for neighborhood green planning aimed at improving older adults’ subjective well-being, which should shift focus from quantity to quality and balance the relationship between quantity and quality based on regional characteristics.

Near-surface air temperature (Ta) is essential for urban heat assessment, but ground observations are spatially sparse. This study combined ECOSTRESS land surface temperature (LST), concurrent Ta and built-environment (BE) indicators in four local climate zone (LCZ) categories in central Xi’an. The analysis comprised 176 site-overpass records from 123 sites across six events. Under ten repetitions of site-grouped five-fold cross-validation, LST-only CatBoost yielded RMSEs of 2.69, 1.63, 4.41 and 2.22 °C in LCZ5-II, LCZ4, LCZ2 and LCZ6-II, respectively. OLS performed better in LCZ4 (1.41 °C). Adding 14 screened BE variables increased the equal-weight mean RMSE across LCZs from 2.74 to 3.29 °C; this disadvantage persisted across the tested model capacity settings in LCZ5-II, LCZ4 and LCZ6-II. In event-held-out tests, the LST-only RMSE rose to 5.84, 6.57 and 7.12 °C in those three LCZs. The dominant LCZ2 event lacked sufficient training support for evaluation. LCZ2’s inverse prediction–observation association arose predominantly between event means, and all tested site-grouped CatBoost configurations retained negative predictive R² values. Within this small sample, additional BE inputs offered limited predictive value, and errors increased substantially when transferring to new events.