In this study, random forest (RF) and support vector machine (SVM) models were developed to evaluate different input variables for predicting and mapping soil drainage classes in the a part of Charmahal & Bakhtiari Province, central Iran. Input variables included digital elevation model (DEM) derived topographic attributes, remote sensing-derived vegetation indices and diffuse reflectance spectroscopy-derived soil color qualifiers (chroma and value). Three soil drainage classes, comprising poorly drained (PD), moderately well drained (MWD) and well drained (WD) were identified. Totally, 102 profiles were described and soil samples were collected from various genetic horizons. Results showed that the best classification results were acquired for two extreme drainage classes (WD and PD) with 100% user accuracy and the greatest misclassification for MWD. Chroma following NDVI and SAVI were the most efficient predictors of soil drainage. The best performance of models was acquired when the topographic attributes, NDVI, SAVI, chroma and value were included as input variables for predicting soil drainage classes. The prediction overall accuracy and the Kappa coefficient of drainage classification were 0.83 and 0.73 for RF and 0.86 and 0.74 for SVM, respectively. In overall, results indicated that color qualifiers combined with topographic attributes and vegetation indices can be employed to successfully predict soil drainage classes cost-effectively with acceptable overall accuracy.

在这项研究中，开发了随机森林（RF）和支持向量机（SVM）模型来评估伊朗中部Charmahal＆Bakhtiari省一部分地区不同的输入变量，以预测和绘制土壤排水类别。输入变量包括数字高程模型（DEM）派生的地形属性，遥感派生的植被指数和漫反射光谱法派生的土壤颜色定性值（色度和值）。确定了三种土壤排水类别，包括排水不良（PD），排水良好（MWD）和排水良好（WD）。总共描述了102个剖面，并从各种遗传视野收集了土壤样品。结果表明，对于两种极端排水类别（WD和PD），具有100％的用户准确度和对MWD的最大误分类获得了最佳分类结果。NDVI和SAVI之后的色度是土壤排水的最有效预测因子。当将地形属性，NDVI，SAVI，色度和值作为输入变量来预测土壤排水类别时，可以获得模型的最佳性能。RF的预测总体准确度和排水分类的Kappa系数对于RF分别为0.83和0.73，对于SVM为0.86和0.74。总体而言，结果表明，可以将颜色限定符与地形属性和植被指数相结合，以具有可接受的总体精度的成本效益地成功预测土壤排水类别。NDVI和SAVI之后的色度是土壤排水的最有效预测因子。当将地形属性，NDVI，SAVI，色度和值作为预测土壤排水类别的输入变量时，可获得最佳模型性能。RF的预测总体准确度和排水分类的Kappa系数对于RF分别为0.83和0.73，对于SVM为0.86和0.74。总体而言，结果表明，可以将颜色限定符与地形属性和植被指数相结合，以具有可接受的总体精度的成本效益地成功预测土壤排水类别。NDVI和SAVI之后的色度是土壤排水的最有效预测因子。当将地形属性，NDVI，SAVI，色度和值作为预测土壤排水类别的输入变量时，可获得最佳模型性能。RF的预测总体准确度和排水分类的Kappa系数对于RF分别为0.83和0.73，对于SVM为0.86和0.74。总体而言，结果表明，可以将颜色限定符与地形属性和植被指数相结合，以具有可接受的总体精度的成本效益地成功预测土壤排水类别。色度和色度作为预测土壤排水等级的输入变量包括在内。RF的预测总体准确度和排水分类的Kappa系数对于RF分别为0.83和0.73，对于SVM为0.86和0.74。总体而言，结果表明，可以将颜色限定符与地形属性和植被指数相结合，以具有可接受的总体精度的成本效益地成功预测土壤排水类别。色度和值作为预测土壤排水等级的输入变量包括在内。RF的预测总体准确度和排水分类的Kappa系数对于RF分别为0.83和0.73，对于SVM为0.86和0.74。总体而言，结果表明，可以将颜色限定符与地形属性和植被指数相结合，以具有可接受的总体精度的成本效益地成功预测土壤排水类别。