Monitoring spatial accuracy of oil palm cultivation mapping in southern Cameroon from Landsat series images

Résumé En

Studying and mapping palm grove evolution allow understanding the impact related to itscultivation. Our study aims to map industrial palm grove using Landsat series images andmeasures the accuracy of the produced maps. It was carried out in SOCAPALM industrialplantation, located in southern of Cameroon. For the mapping and assessment of accuracy, perpixelclassification and confusion matrix method were used, respectively. We obtained highcorrelated maps (Kappa =0.92 in 2001 vs 0.86 in 2015). However, some confusions wereobserved between vegetation and oil palm classes for the two periods, affecting the mapsaccuracy. These confusions are caused by the presence of mixed pixels resulting from thespatial and spectral characteristics of palm groves, the method used to map and validate themap, and uncertainty related to dada. To increase the accuracy, we suggest (1) to use anothermapping method such as super-resolution mapping, (2) develop a classification system ofcartographic products.