Supervised machine learning algorithms are used to classify pixels of a multi-sensor remote sensing dataset comprising RADAR and optical measurements for central Sudan. A total of 19 layers were used, 16 RADAR bands from RADARSAT DN, and texture bands acquired on 13 December 2008 (dry season) and on 2 June 2009 (wet season), and three optical bands acquired by Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) on 25 February 2009. Three different machine learning supervised classification algorithms were used to test the advantage of combining RADAR and optical data: a decision rule, a decision tree, and a naive Bayesian. In all the experiments performed, a combination of RADAR and optical bands leads to higher predictive accuracy and better land cover classification than either sensor used independently. The decision rule classifier performed best among the three methods used.