-
EC-JRC
-
Abu, Itohan-Osa; Szantoi, Zoltan; Brink, Andreas; Thiel, Michael (2020): Cocoa Map (44 804 KB) for Cote d'Ivoire and Ghana. PANGAEA, https://doi.org/10.1594/PANGAEA.917473
-
-
Creative Commons Attribution 4.0 International
-
2019
-
Not Updated
-
Ghana and Côte d'Ivoire
-
10m
-
In this study, a multi-feature Random Forest (RF) algorithm was developed to map cocoa farms from other classes. Normalized difference vegetation index (NDVI) and second-order texture features were input variables for the RF model to discriminate cocoa farms in both countries. The estimated area for cocoa in Cote d'Ivoire was 4.8Mha and 2.3Mha for Ghana. The Produce Accuracy (PA) and User Accuracy (UA) of the RF model were 95.08% and 83.69% respectively. The results demonstrate that a combination of the RF model and multi-feature classification can accurately discriminate cocoa plantations, effectively reduce feature dimensions and improve classification efficiency.
-
The cocoa maps are precursor products of the Copernicus Global Land High Resolution Hot Spot Monitoring activity. As demonstration datasets, they may be used for visualization purposes, but not for detailed statistical analyses.
-
GOAL 15: Life on land, GOAL 12: Responsible Consumption and Production, GOAL 2: Zero Hunger
-