Abstract: Soil organic carbon (SOC) density is a critical soil attribute that not only sustains soil fertility and regulates terrestrial carbon cycles but also influences regional food security and agricultural management decisions. While previous research on SOC density prediction have primarily relied on natural environmental variables, such as climate, topography, and vegetation, they have often overlooked the role of anthropogenic disturbances, especially in heavily human-impacted areas where human activities significantly alter soil properties. This study focuses on the Huang-Huai-Hai Plain (HHH Plain), a major grain-producing region in China characterized by intensive agriculture and urbanization. To improve SOC density prediction accuracy for cultivated land, a random forest (RF) algorithm, integrating 24 environmental covariates (climate, soil parent materials, topography, vegetation, land surface thermal conditions, and soil properties) were integrated with four human activity variables (population density, built-up volume, road network density, and hourly anthropogenic heat flux). Model parameters were optimized using five-fold cross-validation (n_estimators=100 and max_depth=4) and performance was assessed via mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R²), and Lin’s Concordance Correlation Coefficient (LCCC). The baseline model using only environmental covariates (Model 1) explained 35% of SOC density variation. In contrast, the integrated model (Model 6) incorporating both environmental and all four human activity variables improved prediction performance: R² and LCCC increased by 37.14% and 19.67%, respectively, while MAE and RMSE decreased by 8.47% and 9.88%, respectively. This model accounted for 48% SOC density variation, highlighting the indispensable role of anthropogenic factors. Among all predictors, daytime land surface temperature was the most influential environmental factor, while hourly anthropogenic heat flux emerged as the most critical human activity factor, contributing 8.25% to prediction importance, surpassing population density (2.90%), built-up volume (0.58%), and road network density (0.06%). These findings demonstrate that integrating human activity factors, particularly hourly anthropogenic heat flux, is essential for accurate SOC density predictions in the HHH Plain. This study provides a scientific basis for regional soil carbon management, sustainable agricultural development, and ecological protection, while offering a reference for similar studies in human-dominated agricultural regions globally.