Differentiating oil palm plantations from natural forest to improve land cover mapping in Ghana

Abstract

Tree crops like oil palm present a unique challenge in land cover mapping, as they are often misclassified as natural forest. The area cultivated with oil palm in Ghana has rapidly expanded since 2000, and production is expected to continue to increase. Sentinel-1 and Sentinel-2 satellite data was used as inputs to a random forest classifier in Google Earth Engine to map mature, closed-canopy oil palm extent in 2019 of a Ghana study area that includes both industrial plantations and smallholders. The combination of Sentinel-1 and Sentinel-2 bands and derived indices outperformed either satellite alone for mapping industrial oil palm (90.3% overall accuracy). A separate accuracy assessment for this combined input approach demonstrated high accuracy mapping smallholders as well (80.4% overall accuracy), a key challenge in the West African context. To validate these findings, results were compared with available production information and a global oil palm remote sensing product. The resulting map can inform sustainable oil palm efforts in Ghana, which is understudied in current oil palm remote sensing literature, and the methodology provides an example for future studies of oil palm sourcing areas using only publicly available data.