Characterizing ecosystem structural and functional properties in the central Kalahari using multi-scale remote sensing
Understanding, monitoring and managing savanna ecosystems require characterizing both functional and structural properties of vegetation. Due to functional diversity and structural heterogeneity in savannas, characterizing these properties using remote sensing is methodologically challenging. Focusing on the semi-arid savanna in the central Kalahari, the objective of this dissertation was to combine in situ data with multi-scale satellite imagery and two image analysis approaches (i.e. Multiple Endmember Spectral Mixture Analysis (MESMA) and Object Based Image Analysis (OBIA)) to : (i) determine the superior method for estimating fractional photosynthetic vegetation (fPV), non-photosynthetic vegetation (fNPV) and bare soil (fBS) when high spatial resolution multispectral imagery is used, (ii) examine the suitability of OBIA for mapping vegetation morphology types using a Landsat TM imagery, (iii) examine the impact of changing spatial resolution on magnitude and accuracy of fractional cover and (iv) examine how the fractional cover magnitude and accuracy are spatially associated with vegetation morphology. Using the GeoEye-1 imagery, MESMA provided more accurate fractional cover estimates than OBIA. The increasing segmentation scale in OBIA resulted in a consistent increase in error. While areas under woody cover produced lower errors even at coarse segmentation scales, those with herbaceous cover provided low errors only at the fine segmentation scale. Vegetation morphology type mapping results suggest that classes with dominant woody life forms attained higher accuracy at fine segmentation scales, while those with dominant herbaceous vegetation reached higher classification accuracy at coarse segmentation scales. Contrarily, for bare areas accuracy was relatively unaffected by changing segmentation scale. Multi-scale fractional cover mapping results indicate that increasing pixel size caused consistent increases in variance of and error in fractional cover estimates. Even at a coarse spatial resolution, fPV was estimated with higher accuracy compared to fNPV and fBS. At a larger pixel size, in areas with dominant woody vegetation, fPV was overestimated at the cost of mainly underestimating fBS; in contrast, in areas with dominant herbaceous vegetation, fNPV was overestimated with a corresponding underestimation of both fPV and fBS. These results underscore that structural and functional heterogeneity in savannas impact retrieval of fractional cover, suggesting that comprehensive remote sensing of savannas needs to take both structure and cover into account.