The objective of this study is to predict the sugarcane yield in São Paulo State, Brazil, using metrics derived from normalized difference vegetation index (NDVI) time series from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor and an ensemble model of artificial neural networks (ANNs). Sixty municipalities were selected and spectral metrics were extracted from the NDVI time series for each municipality from 2003 to 2012. A neural network wrapper with sequential backward elimination was applied to remove irrelevant and/or redundant features from the initial data set, reducing over-fitting and improving the prediction performance. Afterwards the sugarcane yield was predicted using a stacking ensemble model with ANN. At the predicted yield, the relative root mean square error (RRMSE) was 6.8% and the coefficient of determination (R²) was 0.61. The last three months were removed from the initial time-series data set to forecast the final sugarcane yield, and the process was repeated. The feature selection (FS) improved again the prediction performance and Stacking improved the FS results: RRMSE increased to 8% and R² to 0.43. The yield was also estimated for the entire State, based on the average of the 60 selected municipalities, which were compared to the official data surveys. The Stacking method was able to estimate the sugarcane yield for São Paulo State with a smaller RMSE than the official data surveys, anticipating the crop forecast by three months before the harvest.

This paper describes a new approach to find the right clustering of a dataset. We have developed a genetic algorithm to perform this task. A simple encoding scheme that yields to constant-length chromosomes is used. The objective function maximizes b