Main Article Content
Several methods have been proposed to perform site classification for timber production. Frequently, however, there is need to assess site productive capacity before the forest establishment. This has motivated the application of the Artificial Neural Network (ANN) for site classification. Hereby, the traditional guide curve (GC) procedure was compared to the ANN with no stand feature as input. In addition, different ANN settings were tested to assess the best setting for site classification. The variables used to train the ANN’s were: climatic variables, soil types, spacing and genetic material. The results from the ANN and the GC methods were compared to the observed classes the Kappa coefficient (K) and descriptive analysis. The results showed that the cost function “Cross Entropy” and the output activation function “Softmax” were the best for this purpose. The ANN classification resulted in substantial agreement with the observed indices against a moderate agreement of the GC procedure. The change in growth patterns throughout the rotation may have hindered the proper classification by the CG method, which does not happen with the ANN. However, in the cases in which data from stands at the age close to the reference age are available, the GC method should be prioritized instead of ANN using no stand feature.