With the shift of urbanization from large-scale expansion to high-quality transformation, the 15-minute community life circle (15-minute CLC) has emerged as a significant research focus. Enhancing the quality of 15-minute CLCs has become a critical issue requiring immediate attention. Based on the humanistic perspective, this study systematically analyzes the concept of 15-minute CLC and deeply analyzes the actual demands of residents. In this way, it constructs a 15-minute CLC quality measurement system covering three dimensions: public service facility allocation, public space quality, and pedestrian environment quality. The study takes the central area of Qingdao as the research object. It uses GIS spatial analysis, big data mining, and deep learning to measure the quality of 25 15-minute CLCs in the study area. The results reveal significant spatial heterogeneity in quality metrics across different 15-minute CLCs. This study advances a scientific approach to measuring 15-minute CLC quality and provides evidence-based decision support for targeted urban renewal strategies. Its findings hold substantial practical implications for fostering high-quality 15-minute CLC development.

Under the background of urban stock renewal, the quality improvement of public spaces in aged residential areas is confronted with challenges such as inefficient data collection, disconnection between subjective and objective evaluations, and insufficient dynamic adaptability. To address these issues, this study develops and applies a data-driven framework to achieve an objective, precise, and diagnostically powerful evaluation. Focusing on the Zhongshan Road Sub-district of Qingdao and based on 46 typical public space samples, we utilize a Fully Convolutional Network (FCN) for the semantic segmentation of panoramic images, deriving nine objective spatial indicators. We then combine morphological classification and Principal Component Analysis (PCA) to uncover latent correlations and use K-means clustering to pinpoint framework blind spots and heterogeneous spatial types. The results not only diagnose the specific vitality deficits of different spatial types but also demonstrate the method’s capacity to support targeted renewal strategies. This data-driven approach provides a reference framework for achieving precise and objective assessment in urban renewal, moving beyond subjective assumptions to offer a robust theoretical and empirical foundation for governance.

This study aims to reveal the long-term ecological evolution in the Qingdao West Coast New Area (QWCNA) and predict future trends to support its sustainable development. Firstly, it employed GIS-based land use dynamic indices and transfer matrix analyses to assess land use changes from 1990–2020. Secondly, this study assessed ecological sensitivity (1990–2020) using an Analytic Hierarchy Process (AHP) weighted 7-factor system covering the natural environment, land cover, and accessibility. Thirdly, the Patch-Generating Land Use Simulation (PLUS) model predicted 2030 land use under Natural Development (ND), Urban Development (UD), and Ecological Protection (EP) scenarios, which were subsequently used to evaluate future ecological sensitivity patterns. The main results indicate that a drastic land use transformation occurred between 1990 and 2020, marked by a significant expansion of construction land and forestland. This expansion primarily displaced cultivated land, grassland, water bodies, and unused land, driven by rapid urbanization. Furthermore, spatially distinct ecological sensitivity patterns evolved; lower sensitivity areas increased alongside urban expansion, while higher sensitivity zones (High and Extremely High), concentrated around the Xiaozhu, Dazhu, and Cangma–Tiejue Mts, expanded notably. The expansion of these higher sensitivity zones suggests potential environmental improvement attributed to enhanced conservation efforts. Future simulations show that the EP scenario best aligns with sustainability goals, maximizing the extent of High and Extremely High sensitivity areas by 2030 compared to the ND and UD scenarios.