Estimation of Urban Above-Ground Vegetation Carbon Density and Analysis of Topography-Modulated Spectral Responses in Shenzhen, China

Accurately estimating urban above-ground vegetation carbon density (UAGVCD) is crucial for assessing urban carbon sinks, but it is difficult due to varying spatial patterns, complex land covers, and differences caused by terrain. This study measures UAGVCD in Shenzhen, China, using an explainable remote sensing and machine-learning approach. We combined Landsat 8 spectral bands, vegetation indices, texture metrics, and terrain-based variables with 195 field measurements of carbon density to develop an Extreme Gradient Boosting (XGBoost) model. We evaluated model performance with spatial block cross-validation, using block sizes of 2 km, 5 km, and 10 km to account for spatial autocorrelation. The results show that the XGBoost model performed reliably during spatially independent validation, with the 5 km block showing the best accuracy (train R2= 0.917 ± 0.086, RMSE= 5.53 ± 3.97 Mg ha−1; validation R2 = 0.617 ± 0.055, RMSE = 10.25 ± 1.39 Mg ha−1). Smaller blocks gave more varied results, while larger blocks led to a significant drop in accuracy (validation R2 = 0.380 ± 0.297 at 10 km). Predictions showed clear differences in UAGVCD, with higher values in mountainous and green areas and lower values in highly developed regions. SHapley Additive exPlanations (SHAP) analyses suggested that both spectral and topographic factors play a significant role in UAGVCD. Additionally, the relationships between spectral data and carbon density showed strong nonlinear responses affected by terrain. These findings highlight the importance of spatially explicit validation and explainable machine learning for reliable urban vegetation carbon mapping.