The black soil region of northeast China is a critical global grain production base. The dynamic variations in soil organic carbon (SOC) are directly linked to the regional food security. To accurately monitor SOC content and evaluate the potential of integrating Landsat-9 and GF-1 satellite data for SOC inversion, we developed a machine learning framework that combines data from both satellite sources to model SOC. Using the typical black soil region of northeast China in the Tongken River Basin as the study area, we compared the MLR, PLSR, RF, and XGBoost algorithms. And XGBoost demonstrated the highest performance (R² = 0.9130; RMSE = 0.3834%). Based on the optimal model, SOC in the study area was projected from 2020 to 2024. The multi-year average SOC exhibited an initial increase followed by a subsequent decline, with an overall increase of 22.78%. Spearman correlation analysis identified parent material as the dominant factor controlling SOC variation at the watershed scale (correlation coefficient = 0.38) while also modulating the influence of land use types on SOC dynamics. The “space–ground” multi-source collaborative inversion framework developed in this study offers a high-precision technical approach for the monitoring of SOC in black soil regions.

Soil organic carbon (SOC) is central to terrestrial carbon cycling, soil health and sustainable land utilization. However, in Northeast China’s black soil region, the quantitative synergistic regulatory mechanisms of soil geochemical background, climate, and topography on SOC spatial heterogeneity remain poorly understood, limiting targeted sustainable soil carbon management. This study took the Hulan River Basin with a complete soil geochemical gradient as the study area. Based on eight major soil elements and pH data, we divided the basin into five geochemical zones via PCA and K-means clustering (cumulative variance contribution: 83.02%). SOC content differed significantly among zones, peaking in strongly acidic residual-slope zones and bottoming in alkaline saline–alkali alluvial zones. Geodetector results showed aridity (q = 0.57), mean annual temperature (q = 0.50), and geochemical zone (q = 0.46) dominated SOC differentiation. The non-linear interaction between geochemical zone and aridity exhibited the strongest explanatory power (q = 0.63), far exceeding individual effects, as revealed by the interaction detector. A dual regulatory mechanism was identified: iron–manganese oxides stabilize SOC via organo–mineral complexation, while high pH and base cations accelerate SOC decomposition by disrupting soil aggregates. This study clarifies the synergistic controls of pedogeochemistry, climate and topography on black soil SOC patterns, highlighting the underestimated dominant role of geochemical background. The findings support precise regional carbon stock assessment and differentiated carbon sequestration strategies.