Unraveling Spatiotemporal Patterns and Influencing Factors of Vegetation Net Primary Productivity in the Black Soil Region of Northeast China: An Integrated Framework Combining Improved CASA Model with LightGBM-SHAP Analysis

Against the background of global climate change and intensified human activities, the Black Soil Region of Northeast China (BSRNC)—an ecologically fragile zone and critical grain-producing area—faces mounting pressures on ecosystem stability, productivity sustainability, and black soil conservation. Clarifying the spatiotemporal evolution characteristics of vegetation net primary productivity (NPP) and its associative patterns is crucial for ecological protection and sustainable land management in this region. Based on remote sensing, meteorological, topographic, soil and human activity data, this study employed the improved Carnegie–Ames–Stanford Approach (CASA) model to quantify vegetation NPP—an analytical approach that integrates the CASA model with tree-based machine learning and SHapley Additive exPlanations (SHAP) interpretation. By further combining multiple spatial analysis methods, it characterizes the spatiotemporal dynamics of NPP in the black soil region and innovatively compares seven machine learning algorithms to select the optimal Light Gradient Boosting Machine (LightGBM) model for quantifying the contributions of drivers in this region with high spatial heterogeneity. The results showed that the average annual vegetation NPP in the BSRNC was 301.18 g C·m −2 , exhibiting a fluctuating upward trend at a rate of 1.55 g C·m −2 ·a −1 over the 24-year period. Spatially, NPP displayed significant heterogeneity, climbing gradually from the region’s southwest to its northeast quadrant, with over 90% of the territory showing an upward trajectory. Overall NPP reached a high stability level, though the western and southern regions faced higher degradation risks, and the entire region presented a weak anti-persistent trend. Precipitation was the dominant factor associated with NPP variations, followed by soil moisture, while soil pH had the smallest correlative contribution (0.38). Land-use changes were positively associated with NPP growth, and the interaction of multiple factors showed a significant associative pattern with NPP variations. This study clarifies the spatiotemporal patterns and associative patterns of vegetation NPP in the BSRNC with a 24-year-long time series, and its incremental findings on the coupling of land-use change and multi-factor interaction provide a targeted scientific basis for ecological protection, restoration policies and sustainable management of black soil resources.