A SAR and Optical Based Land Cover Classification Methodology to Support Informing on Sustainable Development Goal 15.2.1

Abstract:

Panama is a signatory to the United Nations Sustainable Development Goals (SDG) and has been working towards informing on SDG 15.2.1 – “progress towards sustainable forest management”, which consists in tracking net forest area change. Their efforts have been based on the use of optical imagery to generate landcover maps of the country, however cloud cover has been a great challenge, resulting in approximately 10% of each annual mosaic blocked by clouds over areas primarily covered with forests.

While optical sensors are sensitive to the spectral properties of the land surface and allow for classification of different land cover classes based on their spectral signatures, synthetic aperture radar (SAR) data are ideal over the tropics because of their almost all-weather capability, ability to penetrate through the vegetation canopy, and sensitivity to moisture and vegetation structure. In this study, we present a land cover classification methodology that utilizes the best attributes from optical (Landsat and Sentinel-2) and SAR (Sentinel-1 and PALSAR) data to generate annual landcover maps for the country based on a decision tree classification algorithm - Random Forest. We validate these maps through comparison with in situ data and other validated remote sensing-based products (e.g. Landsat and MODIS). Results support informing on SDG 15.2.1.

Portions of this work were carried out at the Jet Propulsion Laboratory, California Institute of Technology and the University of Maryland, Baltimore County, under contract with the National Aeronautics and Space Administration.