| Volumes and Issues Contents of Issue 1 Special Issue |
www.hydrol-earth-syst-sci-discuss.net/7/389/2010/
© Author(s) 2010. This work is distributed
under the Creative Commons Attribution 3.0 License.
The application of GIS based decision-tree models for generating the spatial distribution of hydromorphic organic landscapes in relation to digital terrain data
Department of Agroecology and Environment, Faculty of Agricultural Sciences (DJF), Aarhus University, Blichers Allé 20, P.O. Box 50, 8830 Tjele, Denmark
Abstract. Accurate information about soil organic carbon (SOC), presented in a spatially form, is prerequisite for many land resources management applications (including climate change mitigation). This paper aims to investigate the potential of using geomorphometrical analysis and decision tree modeling to predict the geographic distribution of hydromorphic organic landscapes at unsampled area in Denmark. Nine primary (elevation, slope angle, slope aspect, plan curvature, profile curvature, tangent curvature, flow direction, flow accumulation, and specific catchment area) and one secondary (steady-state topographic wetness index) topographic parameters were generated from Digital Elevation Models (DEMs) acquired using airborne LIDAR (Light Detection and Ranging) systems. They were used along with existing digital data collected from other sources (soil type, geological substrate and landscape type) to statistically explain SOC field measurements in hydromorphic landscapes of the chosen Danish area. A large number of tree-based classification models (186) were developed using (1) all of the parameters, (2) the primary DEM-derived topographic (morphological/hydrological) parameters only, (3) selected pairs of parameters and (4) excluding each parameter one at a time from the potential pool of predictor parameters. The best classification tree model (with the lowest misclassification error and the smallest number of terminal nodes and predictor parameters) combined the steady-state topographic wetness index and soil type, and explained 68% of the variability in field SOC measurements. The overall accuracy of the produced predictive SOC map (at 1:50 000 cartographic scale) using the best tree was estimated to be ca. 75%. The proposed classification-tree model is relatively simple, quick, realistic and practical, and it can be applied to other areas, thereby providing a tool to help with the implementation of pedological/hydrological plans for conservation and sustainable management. It is particularly useful when information about soil properties from conventional field surveys is limited.
Discussion Paper (PDF, 993 KB) Interactive Discussion (Open, 1 Comment)
Citation: Bou Kheir, R., Bøcher, P. K., Greve, M. B., and Greve, M. H.: The application of GIS based decision-tree models for generating the spatial distribution of hydromorphic organic landscapes in relation to digital terrain data, Hydrol. Earth Syst. Sci. Discuss., 7, 389-416, 2010. Bibtex EndNote Reference Manager
