The application process of fluid fertilizers through variable rates implemented by classical techniques needs a flow meter in the primary controlled variable. This paper proposes an inferential control system based on Artificial Neural Network of the type multilayer perceptron for the identification and control the fertilizer flow rate. In this approach, there is no flow meter since the control is made through secondary variables. The neural network training is made by the algorithm of Levenberg-Marquardt with training data obtained from measurements. The results indicate a fast, stable and low cost control system for precision farming. Levenberg-Marquardt with training data obtained from measurements. The results indicate a fast, stable and low cost control system for precision farming.