Accurate forecasting of carbon emissions at the county level is critical to support China’s dual-carbon goals. However, most current studies are limited to national or provincial scales, employing traditional statistical methods inadequate for capturing complex nonlinear interactions and spatiotemporal dynamics at finer resolutions. To overcome these limitations, this study develops and validates a high-resolution predictive model using advanced gradient boosting algorithms—Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM)—based on socioeconomic, industrial, and environmental data from 2732 Chinese counties during 2008–2017. Key variables were selected through correlation analysis, missing values were interpolated using K-means clustering, and model parameters were systematically optimized via grid search and cross-validation. Among the algorithms tested, LightGBM achieved the best performance (R² = 0.992, RMSE = 0.297), demonstrating both robustness and efficiency. Spatial–temporal analyses revealed that while national emissions are slowing, the eastern region is approaching stabilization, whereas emissions in central and western regions are projected to continue rising through 2027. Furthermore, SHapley Additive exPlanations (SHAP) were applied to interpret the marginal and interaction effects of key variables. The results indicate that GDP, energy intensity, and nighttime lights exert the greatest influence on model predictions, while ecological indicators such as NDVI exhibit negative associations. SHAP dependence plots further reveal nonlinear relationships and regional heterogeneity among factors. The key innovation of this study lies in constructing a scalable and interpretable county-level carbon emissions model that integrates gradient boosting with SHAP-based variable attribution, overcoming limitations in spatial resolution and model transparency.