Period: 1998 – present
Sensor: SPOT-VGT and PROBA-V
Frequency: 10 days
Data can be accessed here.
Algorithm description: The algorithm is based on neural network and similar to that for GEOv1 canopy cover product. However, novel temporal compositing is implemented using time series data from GEOv1 so as to reduce gaps in the dataset.
Accuracy: GEOV2 FCOVER product have been found to reduce gaps in the GEOv1 products, while maintaining good accuracy (RMSE = 0.14 against ground based observations)
- The temporal gap filling may be challenging for long periods of missing data.
- Validation has only been attempted on few sites.
Verger, F. Baret, and M. Weiss, “Algorithm Theorethical Basis Document: LAI, FAPAR, FCOVER- Collection 1 Version 2,” Issue I1.40, Jan. 2017.
A. Verger, F. Baret, and M. Weiss, “Near Real-Time Vegetation Monitoring at Global Scale,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 7, no. 8, pp. 3473–3481, Aug. 2014.