Abstract
This article investigates and demonstrates the suitability of the Sentinel-1 interferometric coherence for land cover and vegetation mapping. In addition, this study analyzes the performance of this feature along with polarization and intensity products according to different classification strategies and algorithms. Seven different classification workflows were evaluated, covering pixel- and object-based analyses, unsupervised and supervised classification, different machine-learning classifiers, and the various effects of distinct input features in the SAR domain—interferometric coherence, backscattered intensities, and polarization. All classifications followed the Corine land cover nomenclature. Three different study areas in Europe were selected during 2015 and 2016 campaigns to maximize diversity of land cover. Overall accuracies (OA), ranging from 70% to 90%, were achieved depending on the study area and methodology, considering between 9 and 15 classes. The best results were achieved in the rather flat area of Donana wetlands National Park in Spain (OA 90%), but even the challenging alpine terrain around the city of Merano in northern Italy (OA 77%) obtained promising results. The overall potential of Sentinel-1 interferometric coherence for land cover mapping was evaluated as very good. In all cases, coherence-based results provided higher accuracies than intensity-based strategies, considering 12 days of temporal sampling of the Sentinel-1 A stack. Both coherence and intensity prove to be complementary observables, increasing the overall accuracies in a combined strategy. The accuracy is expected to increase when Sentinel-1 A/B stacks, i.e., six-day sampling, are considered.
Highlights
L AND cover classification and vegetation mapping are important applications of remote sensing data
Any parameter summarizing a classification from the confusion matrix must suffer from different sorts of inconsistencies [47], in this case, the comparisons are performed within the same sites, i.e., the class distribution remains equal from one methodology to another
First and foremost, the results of this study indicate that the interferometric coherence provided in multitemporal matrices is a formidable source of information for land cover mapping, as has been proven by the fact that three different methodologies, developed by three different research groups, produced an Overall accuracies (OA) of over 75% for all three study areas
Summary
L AND cover classification and vegetation mapping are important applications of remote sensing data. In the frame of the GEO Task US-09-01a, the Group of Earth Observations (GEO) [1] addressed the identification of critical earth observation priorities considering land cover, vegetation and forest covers, and vegetation type or land use as observation priorities with an impact on different societal benefit areas (SBAs), such as, for instance, agriculture, ecosystems, or biodiversity. Land cover classification and vegetation mapping are important indicators of the interaction between humans and the natural environment. The use of this information in land use management plays a key role in the sustainable development and efficient exploitation of the earth’s natural resources. The availability and accessibility of accurate and.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
