Modeling and identification of fertility maps using artificial neural networks

The application of agricultural fertilizers using variable rates along the field can be made through fertility maps previously elaborated or through real-time sensors. In most of the cases previously elaborated maps are applied. These maps are identified from analyses done in soil samples collected regularly (a sample for each field cell) or irregularly along the field. Mathematical interpolation methods such as nearest neighbor, local average, weighted inverse distance, contouring and kriging are currently used for predicting the variables involved with elaboration of fertility maps. However, some of these methods present deficiencies that can generate different fertility maps for the same data set. Moreover, such methods can generate imprecise maps. Artificial neural networks have been applied for elaboration and identification of precise fertility maps which can reduce the production costs and environmental impact