Urban forest parks offer valuable spaces for walking activities that benefit both physical and mental health. However, trails in current park designs are often underutilised, and the scene layout does not fully meet the preferences of walkers. Therefore, understanding the connection between scene characteristics and walking preferences is essential. This study aimed to develop an ensemble protocol to assess the role of scene characteristics in walking preferences, using Shanghai Gongqing Forest Park as an illustrative example. A walking preference heat map was created using a combination of crowdsourced GPS data. The scene characteristics were quantified using panoramic photographs, drone orthophotos, computer vision, and deep learning techniques. Taking spatial dependence into account, the key findings include the following: (1) From an overhead view, the shortest paths, waterbody density, and recreational facility selection positively influenced walking preferences, while secondary asphalt trails had a negative effect. (2) At the eye level, aesthetically pleasing landscape elements, such as flowers and bridges, attracted more pedestrians, while closed trails were less favoured. (3) Eye-level features explained 43.5% of the variation in walking preference, with a stronger influence on walking preference compared to 22.4% for overhead features. (4) Natural elements were generally more significant than artificial ones; the feature ranking of significant impact was flowers > NACHr1000 > visual perception > water body density > bridge > SVF > retail > entertainment > asphalt. This study proposes a flexible protocol that provides urban forest park managers and planners with practical tools to create a more walker-friendly environment and more accurate trail alignment, as well as a solid empirical basis for assessing the use of urban forest parks.

Rapid urbanization has made urban forest scenes scarce resources, leading to a surge in the demand for high-quality rural forest scenes as alternative outdoor recreation spaces. Previous studies mainly applied survey methods, focusing on visitors’ feedback for different types of scenes from the perspective of visual quality evaluation. Nevertheless, the explanations of the relationships between various factors of scenes and visitors’ preferences are relatively superficial. This study sought to explore the distribution and characteristics of preferred rural forest scenes based on visitor reviews from social media, and using Geodetector, a geospatial statistics tool, to quantitatively analyzed the reasons for visitors’ preferences in terms of factors obtained from multi-source geospatial data. The findings are that (1) visitors are already satisfied with the natural environment but expect scenes that reflect the culture of tea; (2) spatial factor has a more robust interpretation of visitors’ preference, and although the Normalized Difference Vegetation Index (NDVI) and non-consumption indicators barely explain visitors’ preference solely when each of them is combined with other indicators, they can produce non-linear enhancement effects. Consequently, this study synthesizes visitors’ feedback and factors in rural forest scenes to understand visitors’ preferences, thus providing insights into human-centered planning.