Applicability of the global TanDEM-X elevation data for terrain modelling of a forested karst area: a case study from Slovak Karst

Abstract

New interferometric radar data of the TanDEM-X space mission have become recently available as a global digital elevation model providing 0.4 arc second spatial resolution (ca. 12 meters). The TanDEM-X dataset brings new options into geoscientific research across multiple scales. However, the accuracy and suitability of this data have not been evaluated in such an extensive manner as, for example, the widely used SRTM data which resolution is 1 arc second (ca. 30 m). We present a validation of the vertical accuracy of TanDEM-X DEM product and an evaluation of its suitability for landform classification in a forested karst area. The DEM segmentation using geomorphons was used for the automated object-based landform classification. We focused on the identification of dolines for which polygons of dolines mapped by an expert-driven approach were used for validation. Airborne lidar data in the form of DSM and DTM were used as the reference dataset for validation of the TanDEM-X DEM vertical accuracy. The results from the study area show that the vertical RMSE of the TanDEM-X data is 3.42 m with respect to the lidar DSM and 9.64 m in comparison with lidar DTM. The identification of dolines by the geomorphon approach achieved 73 % with TanDEM-X, lower than for the lidar DTM (85 %). The TanDEM-X elevation errors were strongly correlated with the canopy height derived from the lidar data suggesting limited suitability of the TanDEM-X data for mapping fine-scale geomorphological features under forests while there was a good match with the lidar DTM terrain in open areas. URL: https://www.gcass.science.upjs.sk/