Please use this identifier to cite or link to this item:
|Title:||How good is the map? A multi-scale cross-comparison framework for global settlement layers: Evidence from Central Europe|
|Authors:||KLOTZ Martin; KEMPER Thomas; GEISS Christian; ESCH Thomas; TAUBENBOECK Hannes|
|Citation:||REMOTE SENSING OF ENVIRONMENT vol. 178 p. 191-212|
|Publisher:||ELSEVIER SCIENCE INC|
|Type:||Articles in periodicals and books|
|Abstract:||Mapping of settlement areas from space is entering a new era. With the recently developed Global Urban Footprint (based on radar data from TanDEM-X) and the Global Human Settlement Layer (based on optical data), two new initiatives that promise to map complex settlement patterns at global scales and unprecedented spatial resolutions are about to enter the scientific and map user community. However, comparative studies on these layers' strengths and weaknesses, especially in terms of their potential added value with regard to existing lower resolution maps, as well as their assessed accuracy are still absent. In this regard, we introduce a multi-scale cross-comparison framework that uses the best existing urban maps as a benchmark. To paint a complete picture, we simultaneously address several components of map accuracy including relative inter-map agreement, absolute accuracies and pattern-based classification differences. This framework is applied to present regionally representative results from two Central European test sites. In this, we find that the new base maps bring decisive advancements in preserving the small-scale complexity of global human settlement patterns beyond urban core areas. Relative inter-map comparison exposes low density settlement regions traditionally under-represented by lower resolution maps that are now recognized. Absolute metrics such as the Kappa coefficient of agreement (K ) show that accuracies of the new high resolution layers (View the MathML sourceK¯ = 0.56–0.58) nearly double those of existing products. Beyond, they feature substantial consistency between urban (View the MathML sourceK¯ = 0.46–0.50) and rural landscapes (View the MathML sourceK¯ = 0.41–0.45). Results from pattern-based exploration further reveal significant correlation of accuracies with physical pattern variations such as settlement density and mark a clear shift of accuracies from large to medium and small patch sizes. This differentiated view on classification accuracies shows that the new generation of urban maps constitutes a significantly enhanced spatial representation of large-scale settlement patterns.|
|JRC Directorate:||Space, Security and Migration|
Files in This Item:
There are no files associated with this item.
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.