The wetland ecosystem is an important organic carbon pool on earth, and rich carbon storage and high carbon density are present in wetland vegetation and soil. However, large areas of wetlands have been drained, the area of wetlands has shrunk, and the degree of fragmentation has intensified due to rapid urbanization in the past 20 years. Enhancing ecological carbon sequestration capacity is a key task of carbon peaking and neutrality, and studying the carbon sequestration function of urban wetland is urgently needed. In this work, the wetland in Wuhan was taken as the main research object. The landscape pattern index of Wuhan wetland was calculated and the evolution characteristics of landscape pattern were analyzed using the remote sensing image interpretation data from 2000 to 2020. CASA model was used to estimate the carbon sequestration of wetlands and explore the spatial and temporal distribution pattern of carbon sequestration. Spearman correlation was used to study the effects of different landscape pattern parameters on carbon sequestration. Results indicate the following: (1) From 2000 to 2020, the total wetland area in Wuhan has been reduced by 158.99 km², among which the area of lakes, reservoirs and marshes decreased by 60.65 km², 55.51 km² and 41.77 km², respectively. The density of wetland patches and the degree of fragmentation and irregularity increased, and the LPI, aggregation degree and diversity decreased. (2) In the past 20 years, the total carbon sequestration amount of wetland in Wuhan first decreased and then increased, among which the carbon sequestration in wetland was the lowest in 2010 (571,900 t). The amount of carbon sequestration in 2020 was the same as that in 2000, reaching 800,000 t. (3) A larger wetland area means more concentrated and denser distribution, more complex shape, more diverse type, and stronger carbon sequestration capacity for Wuhan wetland. On the contrary, the distribution of wetlands becomes more fragmented and regular, and the disordered planning leads to the reduction in wetland types in a unit area, which will decrease the carbon sink capacity of urban wetlands.

Building cycling-friendly street environments is crucial for promoting sustainable urban mobility. However, existing studies exploring the influence of the built environment on cycling have paid limited attention to the three-dimensional characteristics of street landscapes and have mostly relied on linear assumptions. To address these gaps, this study employs street view imagery and interpretable machine learning methods to investigate the nonlinear and interaction effects of street landscape elements on residents’ cycling preferences in Xiamen Island, China. The results reveal that the visual indices of buildings, sky, vegetation, and roads are the most influential variables affecting cycling preferences. These factors exhibit pronounced nonlinear relationships with cycling preference. For instance, buildings exhibit a threshold effect, with positive influences on cycling preference when the building index is below 0.12 and negative effects when it exceeds 0.12. A low sky index significantly suppresses cycling preference, whereas higher values offer only limited additional benefits, with an optimal range of 0.1–0.25. Vegetation contributes positively only at relatively high levels, suggesting that its index should ideally exceed 0.3. The road index shows a V-shaped relationship: values between 0.15 and 0.25 reduce cycling preference, whereas values below 0.15 or above 0.25 enhance it. Moreover, clear interaction effects among these variables are observed, suggesting that the combined visual composition of the streetscape plays an important role in shaping cycling preferences. These findings deepen the understanding of how street landscape characteristics influence cycling behavior and provide nuanced, practical insights for designing cycling-friendly streets and promoting sustainable travel in urban environments.