 This study assessed the accuracy of five different approaches for producing crop type maps from high-resolution satellite imagery. The results showed that a random forest classifier was able to achieve overall accuracies above 80% for most sites tested. Two sites had lower performance, likely due to the presence of small fields or mixed crops slash trees in the field. The approach is based on supervised machine learning techniques, which require in-situ data collection for the training phase, but the map production is fully automated. This article was authored by Jordy Inglada, Marcella Arias, Benjamin Tardy, and others.