Mapping the Distribution of Coffee Plantations from Multi-Resolution, Multi-Temporal, and Multi-Sensor Data Using a Random Forest Algorithm

Indonesia is the world’s fourth largest coffee producer. Coffee plantations cover 1.2 million ha of the country with a production of 500 kg/ha. However, information regarding the distribution of coffee plantations in Indonesia is limited. This study aimed to assess the accuracy of classification model and determine its important variables for mapping coffee plantations. The model obtained 29 variables which derived from the integration of multi-resolution, multi-temporal, and multi-sensor remote sensing data, namely, pan-sharpened GeoEye-1, multi-temporal Sentinel 2, and DEMNAS. Applying a random forest algorithm (tree = 1000, mtry = all variables, minimum node size: 6), this model achieved overall accuracy, kappa statistics, producer accuracy, and user accuracy of 79.333%, 0.774, 92.000%, and 90.790%, respectively. In addition, 12 most important variables achieved overall accuracy, kappa statistics, producer accuracy, and user accuracy 79.333%, 0.774, 91.333%, and 84.570%, respectively. Our results indicate that random forest algorithm is efficient in mapping coffee plantations in an agroforestry system.