Estimation of the soil organic carbon (SOC) content is of utmost importance in understanding the chemical, physical, and biological functions of the soil. This study proposes machine learning algorithms of support vector machines (SVM), artificial neural networks (ANN), regression tree, random forest (RF), extreme gradient boosting (XGBoost), and conventional deep neural network (DNN) for advancing prediction models of SOC. Models are trained with 1879 composite surface soil samples, and 105 auxiliary data as predictors. The genetic algorithm is used as a feature selection approach to identify effective variables. The results indicate that precipitation is the most important predictor driving 14.9% of SOC spatial variability followed by the normalized difference vegetation index (12.5%), day temperature index of moderate resolution imaging spectroradiometer (10.6%), multiresolution valley bottom flatness (8.7%) and land use (8.2%), respectively. Based on 10-fold cross-validation, the DNN model reported as a superior algorithm with the lowest prediction error and uncertainty. In terms of accuracy, DNN yielded a mean absolute error of 0.59%, a root mean squared error of 0.75%, a coefficient of determination of 0.65, and Lin’s concordance correlation coefficient of 0.83. The SOC content was the highest in udic soil moisture regime class with mean values of 3.71%, followed by the aquic (2.45%) and xeric (2.10%) classes, respectively. Soils in dense forestlands had the highest SOC contents, whereas soils of younger geological age and alluvial fans had lower SOC. The proposed DNN (hidden layers = 7, and size = 50) is a promising algorithm for handling large numbers of auxiliary data at a province-scale, and due to its flexible structure and the ability to extract more information from the auxiliary data surrounding the sampled observations, it had high accuracy for the prediction of the SOC base-line map and minimal uncertainty.

Understanding the spatial distribution of soil organic carbon (SOC) content over different climatic regions will enhance our knowledge of carbon gains and losses due to climatic change. However, little is known about the SOC content in the contrasting arid and sub-humid regions of Iran, whose complex SOC–landscape relationships pose a challenge to spatial analysis. Machine learning (ML) models with a digital soil mapping framework can solve such complex relationships. Current research focusses on ensemble ML models to increase the accuracy of prediction. The usual ensemble method is boosting or weighted averaging. This study proposes a novel ensemble technique: the stacking of multiple ML models through a meta-learning model. In addition, we tested the ensemble through rescanning the covariate space to maximize the prediction accuracy. We first applied six state-of-the-art ML models (i.e., Cubist, random forests (RF), extreme gradient boosting (XGBoost), classical artificial neural network models (ANN), neural network ensemble based on model averaging (AvNNet), and deep learning neural networks (DNN)) to predict and map the spatial distribution of SOC content at six soil depth intervals for both regions. In addition, the stacking of multiple ML models through a meta-learning model with/without rescanning the covariate space were tested and applied to maximize the prediction accuracy. Out of six ML models, the DNN resulted in the best modeling accuracies, followed by RF, XGBoost, AvNNet, ANN, and Cubist. Importantly, the stacking of models indicated a significant improvement in the prediction of SOC content, especially when combined with rescanning the covariate space. For instance, the RMSE values for SOC content prediction of the upper 0–5 cm of the soil profiles of the arid site and the sub-humid site by the proposed stacking approaches were 17% and 9% respectively, less than that obtained by the DNN models—the best individual model. This indicates that rescanning the original covariate space by a meta-learning model can extract more information and improve the SOC content prediction accuracy. Overall, our results suggest that the stacking of diverse sets of models could be used to more accurately estimate the spatial distribution of SOC content in different climatic regions.

Land suitability assessment is essential for increasing production and planning a sustainable agricultural system, but such information is commonly scarce in the semi-arid regions of Iran. Therefore, our aim is to assess land suitability for two main crops (i.e., rain-fed wheat and barley) based on the Food and Agriculture Organization (FAO) “land suitability assessment framework” for 65 km² of agricultural land in Kurdistan province, Iran. Soil samples were collected from genetic layers of 100 soil profiles and the physical-chemical properties of the soil samples were analyzed. Topography and climate data were also recorded. After calculating the land suitability classes for the two crops, they were mapped using machine learning (ML) and traditional approaches. The maps predicted by the two approaches revealed notable differences. For example, in the case of rain-fed wheat, results showed the higher accuracy of ML-based land suitability maps compared to the maps obtained by traditional approach. Furthermore, the findings indicated that the areas with classes of N2 (≈18%↑) and S3 (≈28%↑) were higher and area with the class N1 (≈24%↓) was less predicted in the traditional approach compared to the ML-based approach. The major limitations of the study area were rainfall at the flowering stage, severe slopes, shallow soil depth, high pH, and large gravel content. Therefore, to increase production and create a sustainable agricultural system, land improvement operations are suggested.