Mathematical prediction of the Jatropha curcas L. plant yield: comparing Multiple Linear Regression and Artificial Neural Network Multilayer Perceptron models

Abstract

The aim of this study was to predict the Jatropha~curcas plant yield through an Artificial Neural Network (ANN) Multi-Layer Perceptron (MLP) model. The predictive ability of the developed model was tested against the Multiple Linear Regression (MLR) using performance indexes. According to the performance indexes the use of ANN-MLP model improved J.~curcas plant yield prediction comparatively to MLR model