DEEP LEARNING MONITORING OF WOODY VEGETATION DENSITY IN A SOUTH AFRICAN SAVANNAH REGION
- 1Department of Natural Sciences, Manchester Metropolitan University, Manchester, M1 5GD, UK
- 2School of Electrical and Computer Engineering, National Technical University of Athens, Athens 15780, Greece
Keywords: Fractional woody vegetation cover, bush encroachment monitoring, South Africa, Landsat, spatiotemporal metrics, deep learning, CNN, U-Net
Abstract. Bush encroachment in African savannahs has been identified as a land degradation process, mainly due to the detrimental effect it has on small pastoralist communities. Mapping and monitoring the extent covered by the woody component in savannahs has therefore become the focus of recent remote sensing-based studies. This is mainly due to the large spatial scale that the process of woody vegetation encroachment is related with and the fact that appropriate remote sensing data are now available free of charge. However, due to the nature of savannahs and the mixture of land cover types that commonly make up the signal of a single pixel, simply mapping the presence/absence of woody vegetation is somewhat limiting: it is more important to know whether an area is undergoing an increase in woody cover, ever if it is not the dominant cover type. More recent efforts have, therefore, focused in mapping the fraction of woody vegetation, which, clearly, is much more challenging. This paper proposes a methodological framework for mapping savannah woody vegetation and monitoring its evolution though time, based on very high-resolution data and multi-temporal medium-scale satellite imagery. We tested our approach in a South African savannah region, the Northwest Province (> 104,000 km2), 0.5m-pixel aerial photographs for sampling and validation and Landsat data.