Productivity data (commonly known as apparent fertility) of the initial part of the river Pardo-SP watershed was analyzed and classified with Artificial Neural Networks (ANNs), in order to classify lands for irrigation. Soil attributes as pH, CEC (cation exchange capacity), V% (base saturation index), P (phosphorus), Mg (magnesium) and K (potassium) were defined in five classes: very high, high, medium, low and very low. Apparent fertility classification taking into account the five classes was performed by using Multiple Layers Perceptron (MLP). Backpropagation algorithm was performed with the training set. One hidden layer with 5 neurons was the situation that best performed.
artificial intelligence; pattern recognition; multilayer perceptron
