Coping with imbalanced data problem in digital mapping of soil classes

An unsolved problem in the digital mapping of categorical soil variables and soil types is the imbalanced number of observations, which leads to reduced accuracy and the loss of the minority class (the class with a significantly lower number of observations compared to other classes) in the final map. So far, synthetic over- and under-sampling techniques have been explored in soil science; however, more efficient approaches that do not have the drawbacks of these techniques and guarantee retention of the minority classes in the produced map are essentially required. Such approaches suggested in the present study for digital mapping of soil classes include machine learning models of ensemble gradient boosting, cost-sensitive learning and one-class classification (OCC) of the minority class combined with multi-class classification. In this regard, extreme gradient boosting (XGB) as an ensemble gradient learner, a cost-sensitive decision tree (CSDT) within the C5.0 algorithm, and a one-class support vector machine combined with multi-class classification (OCCM) were investigated to map eight soil great groups with a naturally imbalanced frequency of observations in northwest Iran. A total of 453 profile data points were used for mapping the soil great groups of the study area. A data split was done manually for each class separately, which resulted in an overall 70% of the data for calibration and 30% for validation. The bootstrapping approach of calibration (with 10 runs) was performed to produce multiple maps for each model. The 10 bootstraps were evaluated against the hold-out validation dataset. The average values of accuracy measures, including Kappa (K), overall accuracy (OA), producer's accuracy (PA) and user's accuracy (UA), were explored. In addition, the results of this study were compared with a previous study in the same area, in which resampling techniques were used to deal with imbalanced data for digital soil class mapping. The findings show that all three suggested methods can deal well with the imbalanced classification problem, with OCCM showing the highest K (= 0.76) and OA (= 82) in the validation stage. Also, this model can guarantee the retention of the minority classes in the final map. Comparing the present approaches with the previous study approach demonstrates that the three newly suggested methods can remarkably increase both overall and individual class accuracy for mapping.     

Lateral and Vertical Variations of Soil Organic and Inorganic Carbon Content in Aridisols and Entisols of a Rangeland

Eurasian Soil Science - The influence of biological and physicochemical soil properties on the variations in soil organic and inorganic carbon (OC and IC) contents at the soil surface was studied....     

Integration of ANP and Fuzzy set techniques for land suitability assessment based on remote sensing and GIS for irrigated maize cultivation

Land suitability assessment can inform decisions on land uses suitable for maximizing crop yield while making best use, but not impairing the ability of natural resources such as soil to support growth. We assessed the suitability of maize to be produce in 12,000 ha land of Dasht-e-Moghan region of Ardabil province, northwest of Iran. Suitability criteria included soil depth, gypsum (%), CaCO₃ (%), pH, electrical conductivity (EC), exchangeable sodium percentage (ESP), slope (%) and climate data. We modified and developed a novel set of techniques to assess suitability: fuzzy set theory, analytic network process (ANP), remote sensing and GIS. A map of suitability was compared a map created using a traditional suitability technique, the square root method. The coefficient of determination between the land suitability index and observed maize yield for square root and ANP-fuzzy methods was 0.747 and 0.919, respectively. Owing to greater flexibility to represent different data sources and derive weightings for meaningful land suitability classes, the ANP-fuzzy method was a superior method to represent land suitability classes than the square root method.