GIS-fuzzy logic technique in modeling soil depth classes: Using parts of the Clay Belt and Hornepayne region in Ontario, Canada as a case study

摘要: Abstract Globally, there is a growing desire to predict and map the spatial distribution of soil depth on landscape due its numerous roles in areas such as agriculture, forestry, hydrology ecological land classification. The aim this study was develop technique model classes based GIS-fuzzy logic modeling approach examine mapping accuracy with classes' derived using randomForest approach. This carried out for portion Clay Belt Hornepayne region Ontario, Canada case study. performed soil-environment (case-based reasoning rule-based reasoning) 10 m LiDAR-derived Digital Elevation Model (DEM) derivatives curvature, slope, aspect, slope position classification, smooth multi-path wetness index surface roughness combination mode deposition observations information. A digital deep (> 120 cm), moderately (> 60 ≤ 120 cm), shallow (> 15 ≤ 60 cm) very (≤ 15 cm) predicted across 430,076 ha. An overall 94% validation obtained from relative 88% technique. could be readily implemented various landscapes.