Assessing the potential of multi-temporal WorldView-2 imagery for mapping West African agroforestry tree species
2015 (English)Manuscript (preprint) (Other academic)
Agroforestry tree species in the West Africa parklands are subject to increasing pressure from climate change and land use change, with potentially detrimental effects on local livelihoods and the environment. Methods that enable detailed and efficient mapping of individual trees are therefore needed, both for natural resource monitoring and ecological research. This study investigates the capability of multi-temporal WorldView-2 imagery to map five dominant tree species/groups in a parkland landscape in central Burkina Faso. The Random Forest algorithm is used for object based tree species classification and for assessing the relative importance of predictors. The classification accuracies from using wet season, dry season and multi-temporal datasets are compared to gain insights about the optimal timing for image acquisition. The multi-temporal dataset produced the most accurate classifications, with an overall accuracy (OA) of 82.4% (K = 0.77). For classifications based on single date imagery, the dry season (OA = 76.3%; K = 0.70) proved to be more suitable than the wet season (OA = 66.6%; K = 0.57). The predictors that contributed most to the classification success were based on visible wavelengths, in particular green, yellow and red, as well as the red edge band. It was therefore concluded that WorldView-2 with its unique band configuration represents a suitable data source for tree species mapping in West African parklands. Theseresults are particularly promising when considering the recently launched WorldView-3, which provides data both at higher spatial and spectral resolution, including additional shortwave infrared bands.
Place, publisher, year, edition, pages
Tree species mapping, WorldView-2, agroforestry, parkland, Sudano-Sahel
Environmental Sciences related to Agriculture and Land-use
IdentifiersURN: urn:nbn:se:liu:diva-121533OAI: oai:DiVA.org:liu-121533DiVA: diva2:856214