Applying Machine Learning to Extract New Knowledge in Precision Agriculture Applications

We are considering a facet of precision agriculture that concentrates on plant-driven crop management. By monitoring soil, crop and climate in a field and providing a decision support system that is able to learn, it is possible to deliver treatments, such as irrigation, fertilizer and pesticide application, for specific parts of a field in real time and proactively. In this context, we have applied machine learning techniques to automatically extract new knowledge in the form of generalized decision rules towards the best administration of natural resources like water. The machine learning application model suggested in this paper is based on an inductive and iterative process of discovering knowledge on the basis of which, patterns and associations having arisen initially are re-examined to expand the pre-existing knowledge. The result of this study was the creation of an effective set of decision rules used to predict the plants´ state and the prevention of unpleasant impacts from the water stress in plants.