Knowledge on spatial distribution of soil depth, coarse fragments and texture are crucial for land resource management and environmental soil modeling. Digital soil mapping approach helps in prediction of spatial soil information by establishing the relationship between soil and environmental covariates. In the present study, we assessed spatial distribution of soil depth, coarse fragments (CF) and soil textural classes over 0.13 M sq.km area of Tamil Nadu state. About 2100 samples were used for the prediction of soil properties using random forest model (RF). Out of which, 80 per cent samples were used for training and 20 percent samples were used for testing. Different environmental covariates such as digital elevation model outputs, landsat data and bioclimatic variables were related to predict the soil properties. The predicted soil depth and CF ranged from 46-200 cm and 1-42 per cent respectively. The RF model performed well by explaining the variability (R 2 ) of 43% for soil depth and 21% for coarse fragments with RMSE of 38 cm and 13%, respectively. The RF classifier classified the soil textural classes with 64% overall accuracy and 43% kappa index. Variable importance ranking of Random forest model showed that elevation, MrVBF are the important predictors used for prediction of soil depth and CF, whereas remote sensing vegetation indices such as NDVI, EVI were acted as primary variable for prediction of soil textural classes. In this study, 250 m resolution detailed soil depth, CF and textural class maps were prepared which will be useful for different environmental modeling and proper agricultural management purposes.