The management of wheat yield behavior in agricultural areas is a very important task because it influences and specifies the wheat yield production. An efficient knowledge-based approach utilizing an efficient Machine Learning algorithm for characterizing wheat yield behavior is presented in this research work. The novelty of the method is based on the use of Supervised Self Organizing Maps to handle existent sensor information by using a supervised learning algorithm so as to assess measurement data and update initial knowledge. The advent of precision farming generates data which, because of their type and complexity, are not efficiently analyzed by traditional methods. The Supervised Self Organizing Maps have been proved from the literature efficient and flexible to analyze sensor information and by using the appropriate learning algorithms can update the initial knowledge. The Self Organizing models that are developed consisted of input nodes representing the main factors in wheat crop production such as biomass indicators, Organic Carbon (OC), pH, Mg, Total N, Ca, Cation Exchange Capacity (CEC), Moisture Content (MC) and the output weights represented the class labels corresponding to the predicted wheat yield.