Multisensoral Topsoil Mapping in the Semiarid Lake Manyara Region, Northern Tanzania

This study pursues the mapping of the distribution of topsoils and surface substrates of the Lake Manyara area of northern Tanzania. The nine soil and lithological target classes were selected through fieldwork and laboratory analysis of soil samples. High-resolution WorldView-2 data, TerraSAR-X int...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2015, Vol.7 (8), p.9563-9586
Main Authors: Bachofer, Felix, Queneherve, Geraldine, Hochschild, Volker, Maerker, Michael
Format: Article
Language:English
Subjects:
ASTER
Calcium carbonate
Classification
Fieldwork
Image classification
Image segmentation
Lakes
Mapping
multiscale
multisensoral
Remote sensing
SAR
Silica
Soil (material)
Soil analysis
Soil profiles
Spectral bands
SVM
topographical indices
Topsoil
topsoil mapping
WorldView-2
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study pursues the mapping of the distribution of topsoils and surface substrates of the Lake Manyara area of northern Tanzania. The nine soil and lithological target classes were selected through fieldwork and laboratory analysis of soil samples. High-resolution WorldView-2 data, TerraSAR-X intensity data, medium-resolution ASTER spectral bands and indices, as well as ENVISAT ASAR intensity and SRTM-X-derived topographic parameters served as input features. Objects were derived from image segmentation. The classification of the image objects was conducted applying a nonlinear support vector machine approach. With the recursive feature elimination approach, the most input-relevant features for separating the target classes were selected. Despite multiple target classes, an overall accuracy of 71.9% was achieved. Inaccuracies occurred between classes with high CaCO3 content and between classes of silica-rich substrates. The incorporation of different input feature datasets improved the classification accuracy. An in-depth interpretation of the classification result was conducted with three soil profile transects.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs70809563