Predicting Forest Cover in Distinct Ecosystems: The Potential of Multi-Source Sentinel-1 and -2 Data Fusion
International Max Planck Research School (IMPRS) for Global Biogeochemical Cycles, Max Planck Institute for Biogeochemistry, Hans-Knoell-Str. 10, 07745 Jena, Germany
Department for Earth Observation, Friedrich Schiller University, Grietgasse 6, 07743 Jena, Germany
GIScience Group, Friedrich Schiller University, Grietgasse 6, 07743 Jena, Germany
Department of Statistics, Computational Statistics Group, Ludwig-Maximilian University, 80539 Munich, Germany
Max Planck Institute for Biogeochemistry, Hans-Knoell-Straße 10, 07745 Jena, Germany
German Centre for Integrative Biodiversity Research (iDiv) Halle-Jena-Leipzig, 04103 Leipzig, Germany
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(2), 302; https://doi.org/10.3390/rs12020302
Received: 17 December 2019 / Revised: 14 January 2020 / Accepted: 16 January 2020 / Published: 17 January 2020
(This article belongs to the Special Issue Advances in Remote Sensing for Global Forest Monitoring)
The fusion of microwave and optical data sets is expected to provide great potential for the derivation of forest cover around the globe. As Sentinel-1 and Sentinel-2 are now both operating in twin mode, they can provide an unprecedented data source to build dense spatial and temporal high-resolution time series across a variety of wavelengths. This study investigates (i) the ability of the individual sensors and (ii) their joint potential to delineate forest cover for study sites in two highly varied landscapes located in Germany (temperate dense mixed forests) and South Africa (open savanna woody vegetation and forest plantations). We used multi-temporal Sentinel-1 and single time steps of Sentinel-2 data in combination to derive accurate forest/non-forest (FNF) information via machine-learning classifiers. The forest classification accuracies were 90.9% and 93.2% for South Africa and Thuringia, respectively, estimated while using autocorrelation corrected spatial cross-validation (CV) for the fused data set. Sentinel-1 only classifications provided the lowest overall accuracy of 87.5%, while Sentinel-2 based classifications led to higher accuracies of 91.9%. Sentinel-2 short-wave infrared (SWIR) channels, biophysical parameters (Leaf Area Index (LAI), and Fraction of Absorbed Photosynthetically Active Radiation (FAPAR)) and the lower spectrum of the Sentinel-1 synthetic aperture radar (SAR) time series were found to be most distinctive in the detection of forest cover. In contrast to homogenous forests sites, Sentinel-1 time series information improved forest cover predictions in open savanna-like environments with heterogeneous regional features. The presented approach proved to be robust and it displayed the benefit of fusing optical and SAR data at high spatial resolution.