Mapping and monitoring fractional woody vegetation cover in the arid savannas of Namibia using LiDAR training data, machine learning and ALOS PALSAR data

Abstract

Namibia is a very arid country, but experienced significant bush encroachment which has decreased ivestock productivity. Therefore, it is essential to monitor bush encroachment and widespread debushing activities. The aim of study was to develop a system to map and monitor fractional woody cover (FWC) at national scales (50m and 75m resolution) using SAR satellite data (ALOS PALSAR global mosaics, 2009, 2010, 2015, 2016) and ancillary variables (mean annual precipitation - MAP, elevation), with machine learning models that were trained with diverse airborne LiDAR data sets (244 032 ha, 2008-2014). When only the SAR variables were used, an average R2 of 0.65 (RSME = 0.16) was attained. Adding either elevation or MAP, or both ancillary variables, increased the mean R2 to 0.75 (RSME = 0.13), and 0.79 (RSME = 0.12). The inclusion of MAP addressed the overestimation of FWC in very arid areas, but resulted in some anomalies that were related to the geographic distribution and representativeness of the LiDAR training data. Additional targeted LiDAR acquisitions could address this issue. FWC change maps provided insightful regional patterns and detailed local patterns related to debushing activities, wildfires and regrowth and can help inform national rangeland policies and debushing programs.