This document describes the validation of the SENSAGRI added-value proof-of-concept service for the identification of tillage changes over agricultural areas from S1&S2 data. The classification algorithm, described in D6.13, implements a two scale temporal change detection on S1-VH backscatter applied over bare or scarcely vegetated fields identified through the S2-NDVI. The validation has been carried out by comparing the classified binary maps identified with reference maps built using ground data collected over the SENSAGRI test sites. Results indicated an Overall Accuracy that ranges between 68% (Castile and León) and 82% (Apulian Tavoliere).
Validation of Tilled Change Maps (D7.13)
Francesco Mattia;Giuseppe Satalino;Anna Balenzano;Francesco Lovergine;
2019
Abstract
This document describes the validation of the SENSAGRI added-value proof-of-concept service for the identification of tillage changes over agricultural areas from S1&S2 data. The classification algorithm, described in D6.13, implements a two scale temporal change detection on S1-VH backscatter applied over bare or scarcely vegetated fields identified through the S2-NDVI. The validation has been carried out by comparing the classified binary maps identified with reference maps built using ground data collected over the SENSAGRI test sites. Results indicated an Overall Accuracy that ranges between 68% (Castile and León) and 82% (Apulian Tavoliere).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
