544
vegetation on salinized soils (81.4%), pure reed vegetation (76.9%), reed vegetation
on open plaur (87.3%). On the other hand, the class ‘reed on compact plaur’ exhibited lower performance in the mapping results, yielding an accuracy of 59.7%
(Table 17.3).
By integrating the Sentinel-1 time series with optical images such as Sentinel-2,
the quality of the habitat maps of the restoring areas in the Danube Delta can be
considerably improved (Fig. 17.16).
Data integration between the Sentinel-1 and Sentinel-2 images provides classification with an overall accuracy of 97.1% and very good class accuracies ranging
Fig. 17.16 Multi-sensor data integration Sentinel-1 radar time series and Sentinel-2 optical sensor. Five classes of reed vegetation and less confusion between these classes. The restored areas:
(a) Babina-Cernovca; (b) Popina; (c) Dranov-Holbina
S. Niculescu et al.
vegetation on salinized soils (81.4%), pure reed vegetation (76.9%), reed vegetation
on open plaur (87.3%). On the other hand, the class ‘reed on compact plaur’ exhibited lower performance in the mapping results, yielding an accuracy of 59.7%
(Table 17.3).
By integrating the Sentinel-1 time series with optical images such as Sentinel-2,
the quality of the habitat maps of the restoring areas in the Danube Delta can be
considerably improved (Fig. 17.16).
Data integration between the Sentinel-1 and Sentinel-2 images provides classification with an overall accuracy of 97.1% and very good class accuracies ranging
Fig. 17.16 Multi-sensor data integration Sentinel-1 radar time series and Sentinel-2 optical sensor. Five classes of reed vegetation and less confusion between these classes. The restored areas:
(a) Babina-Cernovca; (b) Popina; (c) Dranov-Holbina
S. Niculescu et al.