Visual Perception Element Evaluation of Suburban Local Landscapes: Integrating Multiple Machine Learning Methods

Comprehensive evaluation of suburban landscape perception is essential for improving environmental quality and fostering integrated urban–rural development. Despite its importance, limited research has systematically extracted local visual features and analyzed influencing factors in suburban landscapes using multi-source data and machine learning. This study investigated Chongming District, a suburban area of Shanghai. Using Baidu Street View 360° panoramic images, local visual features were extracted through semantic segmentation of street view imagery, spatial multi-clustering, and random forest classification. A geographic detector model was employed to explore the relationships between landscape characteristics and their driving factors. The findings of the study indicate (1) significant spatial variations in the green visibility, sky openness, building density, road width, facility diversity, and enclosure integrity; (2) an intertwined spatial pattern of blue, green, and gray spaces; (3) the emergence of natural environment dimension factors as the primary drivers influencing the spatial configuration. In the suburban industrial dimension, the interaction between the GDP and commercial vitality exhibits the highest level of synergy. Based on these findings, targeted strategies are proposed to enhance the distinctive landscape features of Chongming Island. This research framework and methodology are specifically applied to Chongming District as a case study. Future studies should consider modifying the algorithms and index systems to better reflect other study areas, thereby ensuring the validity and precision of the results.