High resolution native forest map of Eastern Arc Mountains

doi:doi:10.1594/PANGAEA.914420

High resolution native forest map of Eastern Arc Mountains

This study aims to develop more accurate method for mapping closed canopy evergreen natural forest (CCEF) of the Eastern Arc Mountains (EAM) ecoregion in Tanzania and Kenya, to update the knowledge on its spatial extent, level of fragmentation and conservation status. We tested 1023 model possibilities stemming from combination of Sentinel-1(S1) and Sentinel-2(S2) satellite imagery, spatial texture of S1 and S2, seasonality derived from Landsat-8 time series and topographic information, using random forest modelling approach. The CCEF model has moderate accuracy measured in True Skill Statistic (0.57), and it clearly outperforms other similar products from the region. Based on this model, there are about 296000 ha of Eastern Arc Forests (EAF) left, which is 16-27% less than estimated by previous products. Furthermore, acknowledging small forest fragments (1-10 ha) implies that the EAFs are more fragmented than previously considered. The generated CCEF model should be used to design updates and more informed and detailed conservation allocation plans, to balance this situation

BibTex:

@dataset{Koskikala_Joni_and_Kukkonen_Markus_and_Käyhkö_Niina_2020,
    abstract = {This study aims to develop more accurate method for mapping closed canopy evergreen natural forest (CCEF) of the Eastern Arc Mountains (EAM) ecoregion in Tanzania and Kenya, to update the knowledge on its spatial extent, level of fragmentation and conservation status. We tested 1023 model possibilities stemming from combination of Sentinel-1(S1) and Sentinel-2(S2) satellite imagery, spatial texture of S1 and S2, seasonality derived from Landsat-8 time series and topographic information, using random forest modelling approach. The CCEF model has moderate accuracy measured in True Skill Statistic (0.57), and it clearly outperforms other similar products from the region. Based on this model, there are about 296000 ha of Eastern Arc Forests (EAF) left, which is 16-27% less than estimated by previous products. Furthermore, acknowledging small forest fragments (1-10 ha) implies that the EAFs are more fragmented than previously considered. The generated CCEF model should be used to design updates and more informed and detailed conservation allocation plans, to balance this situation},
    author = {Koskikala, Joni and Kukkonen, Markus and Käyhkö, Niina},
    doi = {10.1594/PANGAEA.914420},
    institution = {PANGAEA (Land Surface)},
    keyword = {'Conservation', 'East Africa', 'Eastern Arc', 'forest remote sensing', 'machine learning', 'multi', 'sensor'},
    title = {High resolution native forest map of Eastern Arc Mountains},
    url = {https://service.tib.eu/ldmservice/vdataset/png-doi-10-1594-pangaea-914420},
    year = {2020}
}