This study presents a preliminary assessment of the potentialities of the COSMO-SkyMed® (CSK®) satellite constellation to accurately classify different crops. The experiment is focused on the main crops grown in the agricultural region of Marchfeld (Austria) namely carrot, corn, potato, soybean and sugar beet. A Support Vector Machine (SVM) classifier was fed with temporally dense series of backscattering coefficients extracted from a stack of CSK® GTC products. In particular, twenty one CSK® dual polarization (11 HH, 10 VH) images were acquired over the site for the growing season (early April – mid October) in Stripmap Himage mode, with a nominal incidence angle at scene center of 40°. A comparison of the classifications obtained at the two different polarizations are reported and the result are analyzed in terms of the achieved accuracies. The SVM method was able to classify all five crop types with an overall accuracy of 81.6% (Kappa 0.77) at VH polarization and of 84.5% (Kappa 0.80) at HH polarization. Sugar beet, potato and carrot were accurately identified with OA never less than 83% at both polarizations, whereas corn and soybean showed remarkably differences in terms of producer’s and user’s accuracies, probably due to particular agricultural practices adopted for these two crop species. These first results show that the CSK® capability of acquiring temporally dense data sets can accurately identify several crop types.
This work aims at investigating the capability of COSMO-SkyMed® (CSK®) constellation of Synthetic Aperture Radar
(SAR) system to monitor the Leaf Area Index (LAI) of different crops. The experiment was conducted in the Marchfeld
Region, an agricultural Austrian area, and focused on five crop species: sugar beet, soybean, potato, pea and corn. A
linear regression analysis was carried out to assess the sensitivity of CSK® backscattering coefficients to crops changes
base on LAI values. CSK® backscattering coefficients were averaged at a field scale (<σ°dB>) and were compared to the
DEIMOS-1 derived values of estimated LAI. LAI were as well averaged over the corresponding fields (<LAIest>). CSK®
data acquired at three polarizations (HH, VV and VH), four incidence angles (23°, 33°, 40° and 57°) and at different
pixel spacings (2.5 m and 10 m) were tested to assess whether spatial resolution may influence results at a field scale and
to find the best combination of polarizations and CSK® acquisition beams which indicate the highest sensitivity to crop
LAI values. The preliminary results show that sugar beet can be well monitored (r = 0.72 - 0.80) by CSK® by using any
of the polarization acquisition modes, at moderate to shallow incidence angles (33° - 57°). Slightly weaker correlations
were found, at VH polarization only, between CSK® < σ°dB> and <LAIest> for potato (r = 0.65), pea (r = 0.65) and
soybean (r = -0.83). Shallower view incidence angles seem to be preferable to steep ones in most cases. CSK®
backscattering coefficients were no sensitive at all to LAI changes for already developed corn fields.