Background: Assessing the spatial dynamics of soil organic carbon (SOC) is essential for carbon monitoring. Since, variability of SOC is mainly attributed to biophysical land surface variables, integrating a compressive set of such indices may support the pursuit for optimum set of predictor variables. Therefore, this study was aimed at predicting the spatial distribution of SOC in relation to remotely-sensed variables and other covariates. Hence, the land surface variables were combined from remote sensing, topographic, and soil spectral sources. Moreover, the most influential variables for prediction were selected using the RF and Classification and Regression Tree (CART).Results: The results indicated that the RF model has good prediction performance with corresponding R2 and RMSE values of 0.96, and 0.91 mg/g, respectively. The distribution of SOC content showed variability across landforms (CV=78.67%), land-use (CV=93%), and lithology (CV=64.67%). Forestland had the highest SOC (13.60 mg/g) followed by agriculture (10.43 mg/g), urban (9.74 mg/g), and water body (4.55 mg/g) land-uses. Furthermore, bauxite and laterite lithology had the highest SOC content (14.69 mg/g) followed by fluvial (14.52 mg/g) and shale (13.57 mg/g), whereas the lowest was predicted in sandstone (5.53mg/g). The mean SOC concentration was 11.70 mg/g, where the majority of area was classified as humous and organo-humus, distributing in the mountainous regions. The biophysical land surface indices, brightness removed vegetation indices, topographic indices (, and soil spectral bands, respectively were the most influential predictors of SOC. Conclusion: The spatial variability of SOC may be influenced by landform, land-use, and lithology of the study area. Remotely-sensed predictors including land moisture, land surface temperature and built-up indices added valuable information for prediction of SOC. Hence, the land surface indices may provide new insights into SOC modeling in complex landscapes of warm sub-tropical urban regions.