No abstract

This work aims to establish a relationship between volume and biomass with interferometric and radiometric SAR (Synthetic Aperture Radar) response from planted Eucalyptus saligna forest stands, using multi-variable regression techniques. X and P band SAR images from the airborne OrbiSAR-1 sensor, were acquired at the study area in the southeast region of Brazil. The interferometric height (Hint = difference between interferometric digital elevation model in X and P bands), contributed to the models developed due to fact that Eucalyptus forest is composed of individuals whose structure is predominantly cylindrical and vertically oriented, and whose tree heights have great correlation with volume and biomass. The volume model showed that the stand volume was highly correlated with the interferometric height logarithm (Log 10 Hint), since Eucalyptus tree volume has a linear relationship with the vegetation height. The biomass model showed that the combination of both Hint 2 and Canopy Scattering Index-CSI (relation of °V V by the sum of °V V and °H H , which represents to the canopy interaction) were used in this model, due to the fact that the Eucalyptus biomass and the trees height relationship is not linear. Both models showed a prediction error of around 10% to estimate the Eucalyptus biomass and volume, which represents a great potential to use this kind of technology to help establish Eucalyptus forest inventory for large areas.

This study proposes a workflow for land use and land cover (LULC) classification of Advanced Land Observing Satellite-2 (ALOS-2) Phased Array type L-band Synthetic Aperture Radar-2 (PALSAR-2) images of the Brazilian tropical savanna (Cerrado) biome. The following LULC classes were considered: forestlands; shrublands; grasslands; reforestations; croplands; pasturelands; bare soils/straws; urban areas; and water reservoirs. The proposed approach combines polarimetric attributes, image segmentation, and machine-learning procedures. A set of 125 attributes was generated using polarimetric ALOS-2/PALSAR-2 images, including the van Zyl, Freeman–Durden, Yamaguchi, and Cloude–Pottier target decomposition components, incoherent polarimetric parameters (biomass indices and polarization ratios), and HH-, HV-, VH-, and VV-polarized amplitude images. These attributes were classified using the Naive Bayes (NB), DT J48 (DT = decision tree), Random Forest (RF), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) algorithms. The RF, MLP, and SVM classifiers presented the most accurate performances. NB and DT J48 classifiers showed a lower performance in relation to the RF, MLP, and SVM. The DT J48 classifier was the most suitable algorithm for discriminating urban areas and natural vegetation cover. The proposed workflow can be replicated for other SAR images with different acquisition modes or for other types of vegetation domains.

No abstract

No abstract