The Use of Multifrequency SAR Data for Assessing Levels of Forest Disturbance in Bajo Calima Colombia

Forest disturbances (i.e. deforestation and degradation) are a serious problem significantly contributing to greenhouse emissions and biodiversity loss. This study investigates the potential of integrating multi-frequency Synthetic Aperture Radar (SAR) data: ALOS PalSAR-2, Sentinel-1B and TanDEM-X, in combination with field data to identify and classify different levels of forest disturbance in a secondary forest in Colombia. Disturbances were classified into three classes using a K-Means clustering of the field data. Hereafter, we used SAR data to retrieve those classes by means of a support vector machine (SVM) algorithm. The accuracy assessment showed a Kappa coefficient of 0.72 and an overall accuracy of 66.2%, thus demonstrating the potential of multifrequency SAR data to assess differences in structure related to forest disturbances.