Introduction: Hospital affiliated green spaces can help patients recover and recover their physical functions, promote physical and mental relaxation, enhance health awareness, and improve overall health. However, there are still significant questions about how to scientifically construct hospital affiliated green spaces. This study examines the impact of hospital green spaces on patient rehabilitation through scientific evaluation methods, providing reference for the scientific construction of hospital affiliated green spaces. Applicability evaluation was conducted on the affiliated green spaces of three hospitals in Harbin. An evaluation system covering plants, space, accessibility, rehabilitation functions, and promotional and educational functions has been constructed. The entropy weight method is used to determine the weight of indicators, and the grey correlation analysis method is used to evaluate the suitability of green space for patient rehabilitation.Methods: The experimental results showed that the landscape accessibility index had the highest weight (0.3005) and the plant index had the lowest weight (0.1628), indicating that caring for special needs is the foundation of hospital landscapes, and plants have subtle and long-term effects on physical and mental health. In the evaluation of the rehabilitation applicability of the affiliated green spaces of various hospitals, the second hospital has the highest grey correlation degree (0.8525), followed by the tumor hospital (0.5306) and the fifth hospital (0.4846). It can be seen that the green space of the second hospital has high applicability for patient rehabilitation, but the green space of the tumor hospital and the fifth hospital needs to be improved and developed.Results and discussion: The evaluation criteria used in this study are comprehensive. The landscaping at the Third Hospital is well-planned with good plant configuration and reasonable spatial layout. However, there is insufficient consideration for accessibility in the landscape design, and the details are lacking. The rehabilitation and educational functions of the landscape are inadequate, with limited outdoor activities and low road safety. The hospital′s affiliated green spaces should adhere to the principle of “appropriate scale, comprehensive functionality, and educational leisure,” integrating rehabilitation and educational functions while increasing the variety of outdoor activities. In the future, emphasis should be placed on exploring the integration of landscape and rehabilitation to provide a functional site that is convenient for visiting, with improved rehabilitation facilities and an educational and enjoyable environment. The design should incorporate elements that contribute to a sense of well-being, including roads and

Traditional visual quality assessments of rural landscapes rely on subjective methods. This study integrates eye-tracking technology with subjective perception evaluation to construct a visual quality assessment model for rural landscapes, aiming to reveal the intrinsic relationship between objective visual behavior and subjective perception, with the aim of providing scientific guidance for rural landscape planning to promote sustainable rural development. Using landscape photographs from nine rural sampling sites in Guangzhou, eye-tracking experiments were conducted to collect participants’ eye movement data, combined with online questionnaires to obtain scenic beauty ratings and landscape characteristic factor evaluations. The findings reveal the following: (1) Eye-tracking experiments and subjective evaluation results showed high consistency, with samples having higher scenic beauty ratings demonstrating more prominent performance in core eye movement indicators such as total fixation duration and count, and total saccade duration, and typically possessing higher landscape characteristic factor values. (2) Urban–suburban-integrated rural landscapes exhibited poorer visual quality, characteristic-preservation rural landscapes elicited more in-depth and sustained visual exploration, and clustered-improvement rural landscapes possessed higher scenic beauty ratings and landscape characteristic factor values. (3) Total saccade duration was the key eye movement indicator for predicting scenic beauty ratings. (4) Multiple landscape characteristic factors significantly influence eye movement behavior.

While objective street metrics derived from imagery or GIS have become standard in urban analytics, they remain insufficient to capture subjective perceptions essential to inclusive urban design. This study introduces a novel Multimodal Street Evaluation Framework (MSEF) that fuses a vision transformer (VisualGLM-6B) with a large language model (GPT-4), enabling interpretable dual-output assessment of streetscapes. Leveraging over 15,000 annotated street-view images from Harbin, China, we fine-tune the framework using Low-Rank Adaptation(LoRA) and P-Tuning v2 for parameter-efficient adaptation. The model achieves an F1 score of 0.863 on objective features and 89.3% agreement with aggregated resident perceptions, validated across stratified socioeconomic geographies. Beyond classification accuracy, MSEF captures context-dependent contradictions: for instance, informal commerce boosts perceived vibrancy while simultaneously reducing pedestrian comfort. It also identifies nonlinear and semantically contingent patterns—such as the divergent perceptual effects of architectural transparency across residential and commercial zones—revealing the limits of universal spatial heuristics. By generating natural-language rationales grounded in attention mechanisms, the framework bridges sensory data with socio-affective inference, enabling transparent diagnostics aligned with Sustainable Development Goal 11(SDG 11). This work offers both methodological innovation in urban perception modeling and practical utility for planning systems seeking to reconcile infrastructural precision with lived experience.

Purpose. This study centers around the Wangzhanghe Country Park located in Jiaozuo City as the research object. Through analysis of the site’s evolution by GPS and its status‐quo by GIS, the map of spatial distribution suitability has been illustrated. Design. Based on the major principle of achieving sustainable development of the ecosystem and the derived concept of building a diversified landscape, we have developed the overall scheme of planning and landscape layout of the country park. Specifically, the area of ecological restoration is further divided into the areas of quarry restoration, bare land restoration, slope protection, vegetation, and dam maintenance, and restorative measures are put forward accordingly. Findings. Our research findings indicate that thanks to the vegetation restoration of the side slope, the area of bare land in mountain farmland has been evidently reduced, whereas the severely damaged ash pits and green spots have also been restored. Originality: in the meantime, we have leveraged the flat space at the foot of the mountain to foster a viewing experience and provide recreational activities for citizens, so that they are able to effectively increase their access to outdoor events and improve their sense of engagement and experience in the events, thereby providing a reference for building a green, diverse, and sustainable system of ecological services for the urban country park.

Rural landscape health assessment, which integrates ecology and culture, is crucial for China’s rural revitalization strategy. However, existing studies primarily focus on large-scale regions, neglecting small-scale areas. This study established a rural landscape health assessment system encompassing ecological conservation, recreational utilization, and socioeconomic production taking nine typical villages in Guangzhou as case studies for exploration. Principal component analysis and the entropy weight method determined indicator weights, and a comprehensive spatial assessment was conducted using a grid-based method. Overall rural landscape health in Guangzhou was relatively low, with the combined area proportion of the “very poor” and “poor” grades > 23.96%; the average area proportion of the “very good” and “good” grades was < 8%, mostly distributed at junctions between patches and corridors with different landscape functions. Significant differences among village types were observed only for the ecological conservation function, with the highest disparity in the area proportion of “very poor” and “poor” grades within villages reaching 48.55%. No significant correlation was found between landscape health and the forest-to-non-forest area ratio; however, a positive correlation with the numerical ratio was identified under ecological conservation and comprehensive functions. The area and numerical ratio maintained a significant positive correlation across all functions. This study reveals the multidimensional characteristics and spatial differentiation of rural landscape health in Guangzhou, providing scientific evidence for targeted optimization. Due to restrictions imposed by urban no-fly zones on drone data collection, this study’s sample only covered nine villages across four districts in Guangzhou. Relying solely on data from the year 2025 and analysis at a single grid scale, it was unable to fully capture spatiotemporal dynamics and multi-scale effects.

In coastal residential areas, the combined effects of high temperature, high humidity, and weak wind conditions during summer intensify outdoor heat exposure and reduce pedestrian thermal comfort. To investigate the influence mechanisms of tree height and spatial layout on pedestrian-level thermal comfort, this study selected a typical residential community in Chengyang District, Qingdao, as the research site. Based on field meteorological observations, an ENVI-met model was established and validated. Using the existing composite greening scenario as the baseline, three tree layout types (row, cluster, and free layouts) and four height scenarios (4 m, 6 m, 8 m, and 10 m) were configured to quantitatively compare variations in physiological equivalent temperature (PET) under different planting schemes. The results indicate that tree configuration significantly affects summer thermal comfort. Its regulatory mechanism is governed not only by air temperature reduction but also by shortwave radiation interception, longwave radiation accumulation, and shading continuity. Although low-to-medium height trees can reduce local air temperature through transpiration, their limited canopy height and shading continuity restrict their ability to effectively attenuate direct shortwave radiation at pedestrian level, and in some cases may even increase mean radiant temperature (Tmrt) and PET. In contrast, 10 m tall trees arranged in row and cluster layouts can form continuous shaded cores, with the 10 m cluster layout demonstrating the best overall performance by significantly reducing Tmrt and PET. The free layout, characterized by dispersed canopies and fragmented shading, provides relatively limited thermal comfort improvement. The findings suggest that residential greening optimization should strengthen the coordination between tree height, canopy structure, and activity spaces. Tall trees should be prioritized in children’s play areas, elderly resting areas, residential entrances, main pedestrian pathways, and west-facing sun-exposed zones, while integrating building shadows and road orientation to create a continuous yet not overly enclosed shading network, thereby enhancing summer thermal adaptability in residential areas.