Urbanization in the 21st century has reshaped carbon stock distributions through the expansion of cities. By using the PLUS and InVEST models, this study predicts land use and carbon stocks in Wuhan in 2050 using three future scenarios. Employing local Moran’s I, we analyze carbon stock clustering under these scenarios, and the Getis–Ord Gi* statistic identifies regions with significantly higher and lower carbon-stock changes between 2020 and 2050. The results reveal a 2.5 Tg decline in Wuhan’s carbon stock from 2000 to 2020, concentrated from the central to the outer city areas along the Yangtze River. By 2050, the ecological conservation scenario produced the highest carbon stock prediction, 77.48 Tg, while the economic development scenario produced the lowest, 76.4 Tg. High-carbon stock-change areas cluster in the north and south, contrasting with low-change area concentrations in the center. This research provides practical insights that support Wuhan’s sustainable development and carbon neutrality goals.

This study proposes the Urban Landscape Emotion Analysis Framework (ULEAF) based on images of urban parks shared on social media. This framework integrates an emotion recognition module driven by a convolutional neural network (ConvNeXt Tiny) with a semantic extraction module supported by multimodal semantic matching models (CLIP and DeepSentiBank ANP lexicon). It constructs a systematic analysis pathway from semantic understanding to emotional perception, effectively overcoming the limitations of traditional research methods. Results indicate that positive emotion images predominantly correlate with nature, health, and openness, while negative emotion images are closely associated with the characteristics of decay, abandonment, and oppression, as well as loneliness and calmness, estrangement and disharmony, and gloom and bleakness. Findings reveal trends consistent with prior research, further validating the stable association between urban landscape visual features and emotional perception. The analytical framework developed in this study facilitates the systematic revelation of semantic characteristics and affective perception mechanisms in large-scale urban park imagery, providing scientific reference for optimizing urban park landscapes and implementing emotion-oriented design.