Exploring Nonlinear Effects of Visual Elements on Perceived Landscape Quality in Historical and Cultural Districts: A Deep Learning Case from Wuhan, China

Perceived landscape quality in historical and cultural districts is crucial for reconciling cultural heritage preservation with urban renewal. However, limited attention has been paid to whether street-level visual elements influence public esthetic perception in a nonlinear manner, especially in heritage-sensitive urban environments. Against this backdrop, this study explores the nonlinear effects of natural, artificial, and interfering visual elements on perceived landscape quality in historical and cultural districts. Five districts in Wuhan, China, were selected. Street view images were processed with a U-Net–based semantic segmentation model to extract pixel-level visual elements, and public scenic beauty ratings were collected through an image-based questionnaire survey. The analyses reveal nonlinear perception patterns. The results show that the relationships between visual elements and perceived beauty are nonlinear and heterogeneous. Natural elements have the strongest positive influence on perceived landscape quality, artificial elements require careful density control, and interfering elements are consistently negative contributors. By quantifying these nonlinear mechanisms, this study suggests that esthetic responses in historical districts may depend on threshold-like combinations of visual elements and may offer a useful reference for heritage-sensitive urban renewal and streetscape design.