Towards a Quasi-Global Accuracy Assessment of Built-Up Surface Estimates Derived From Sentinel-2 Multispectral Data

The reliable quantification of the global built-up surface distribution and its dynamics using Earth Observation data is a fundamental task for many scientific and policy-related applications. The emergence of various global geospatial datasets on human settlements derived from high-resolution Earth Observation data allows practitioners to choose from a variety of global datasets, for which detailed knowledge on data accuracy and semantics is crucial. Herein, we employ novel, quasi-global building footprint data as reference data and develop a framework to assess the accuracy of global EO-derived human settlement data, such as the Global Human Settlement Layer (GHSL), and others. We present preliminary results of these accuracy assessments, at different analytical scales and stratified across different dimensions. Our analyses reveal that for continuous, sub-pixel built-up surface estimation, the GHSL outperforms other global settlement-related datasets under test and provides a reliable baseline for geospatial analyses supporting scientific research and decision making.