Multi-source Mapping of Peatland Types using Sentinel-1, Sentinel-2 and
Terrain Derivatives - A Comparison Between Five High-latitude Landscapes
Abstract
Mapping wetland types in northern-latitude regions with Earth
Observation (EO) data is important for several practical and scientific
applications, but at the same time challenging due to the variability
and dynamic nature in wetland features introduced by differences in
geophysical conditions. The objective of this study was to better
understand the ability of Sentinel-1, Sentinel-2 and terrain derivatives
derived from Copernicus DEM to distinguish three main peatland types,
two upland classes, and surface water, in five contrasting landscapes
located in the northern parts of Alaska, Canada and Scandinavia. The
study also investigated the potential benefits for classification
accuracy of using regionalized classification models constructed from
region-specific training data compared to a global classification model
based on pooled reference data from all five sites. Overall, the results
show high promise for classifying peatland types and the three other
land cover classes using the fusion approach that combined all three EO
data sources (Sentinel-1, Sentinel-2 and terrain derivatives). Overall
accuracy for the individual sites ranged between 84% to 92%. Class
specific accuracies for the peatland types were also high overall, but
differed between the five sites as well as between the three classes
bog, fen and swamp. A key finding is that the regionalized
classification models consistently outperformed the global
classification by producing significantly higher classification
accuracies for all five sites. This opens for promising progress in
terms of identifying effective approaches for stratifying
northern-latitude areas for continental scale peatland classification.