Urban parks are an important component of public urban spaces, which directly impact the living experiences of residents and the urban image. High-quality urban parks are crucial for enhancing the well-being of residents. This study selected Fukuoka, Japan, as the study site. Five urban parks were chosen to evaluate landscape visual quality by using the Scenic Beauty Estimation (SBE) method. The Semantic Differential (SD) method was used to get sample subjective landscape features. Meanwhile, sample objective landscape features were obtained by using semantic segmentation techniques in deep learning and combined with spatial analysis to understand their distribution. A regression model was established, which used the SBE values as the dependent variable and subjective landscape features as the independent variables to analyze the relationship between urban park landscape visual quality and subjective landscape features. The regression analysis revealed that sense of layering, harmony, interestingness, sense of order, and vitality were the core factors influencing visual quality. All five features had a significant positive impact on landscape visual quality. The sense of order was the most influential factor, which would be the key to enhancing the landscape perception experience. Moreover, the XGBoost model and SHAP value from machine learning were used to reveal the nonlinear relationships and significant threshold effects between urban park visual quality and five objective landscape features: openness, greenness, enclosure, vegetation diversity, and Shannon–Wiener diversity index. This study showed that when openness exceeded 0.27, the positive effect was significant. The optimal threshold for the greenness was 0.38. Vegetation diversity and enclosure had to be below 0.82 and 0.58, respectively, to have a positive impact. Meanwhile, the positive influence of the Shannon–Wiener diversity index reached its maximum at a value of 1.37. This study not only establishes a systematic method for diagnosing landscape problems and evaluating landscape visual quality but also provides both theoretical support and practical guidance for urban park landscape optimization.

Coastal historic and cultural districts are distinctive urban public spaces which reflect the urban cultural and historical narratives. As an important symbol, coastal historic and cultural districts’ building colors play a crucial role in enhancing the historic and cultural districts’ visual quality and shaping the urban coastal landscape. Japan was one of the earliest countries to research urban color and building color regulation. This study selected Mojiko in Japan as the study site using street-view images, semantic segmentation technology, and ColorImpact4 software to collect information about the street building color. Based on the Moon–Spencer (M–S) color coordination theory and applied psychology methods, this study evaluated the building color quality and street color harmony from objective and subjective perspectives. It explored the impact of the building color on the coastal historic and cultural districts’ landscape quality. The results indicated that the building color of Mojiko generally presented a harmonious and unified characteristic. Most street buildings were soft, warm color tones, with higher color harmony and continuity. However, there were some problems, such as colors disrupting the overall street color environment, or color combinations were overly uniform. This study proposed a comprehensive method for building color analysis and evaluation, which is a reference value for guiding the color planning and construction for coastal historic and cultural districts’ landscape control.

Close contact with nature helps moderate public emotions and enhance happiness. As an important space for the public to connect with nature, the urban park waterfront environment plays a significant role. Studying the characteristics of landscape elements contributes to the optimization of the urban park natural environment. In this study, the waterfront spaces of 23 urban parks in Shenyang were selected in order to categorize urban park waterfront spaces from the perspective of landscape elements and to explore the relationship between the characteristics of landscape elements in different types of waterfront spaces and public visual satisfaction. Using qualitative analysis, typical spatial types were identified based on differences in landscape elements. Content analysis was used to extract and quantify the characteristics of landscape elements for various waterfront spaces. Through orthogonal experimental design, virtual scenarios were created to evaluate public satisfaction. Methods such as the least significant difference multiple comparison analysis (LSD) were applied to explore the effects of landscape element characteristics on satisfaction in different types and differences within groups. Among the four types of waterfront spaces identified in the experiment, the landscape elements that influenced spatial satisfaction were primarily concentrated in plant characteristics and pavement characteristics. In different types of spaces, the impact of landscape element factors at different levels varied. The study introduced virtual experiments to analyze the characteristics of landscape elements in waterfront spaces, which provided a new method for the satisfaction research of waterfront spaces. The results are a valuable guidance for the scientific classification of urban park waterfront spaces. A new perspective for enhancing the urban park waterfront landscape was supplied.