Sensibility studies are necessary to evaluate if an existing method is optimizable. The present method for classification of land cover uses the course of information about an observed region during one year. The progress of the natural cover of an observed region gets visible by using weekly composites of NDVI measurements. Filling this data in a diagram results in a time curve. This time series can be characterized by minimum, maximum, amplitude, average and standard deviation of the curve and by other parameters. The analysis of this values, for example by utilization of Recursive Partitioning and Regression Trees (RPART) allows a classification of the vegetation. In the sensibility study the effects of the variation of several criteria like temporal segmentation, pre-utilization of curve smoothing are analyzed. Also the impact of changing training data on the classification of specific target classes and the possibility of predicting classes are an objective of this sensibility studies. Therefore the software, developed in a dissertation at the University of Würzburg, is changed and adopted to be able to apply statistics on the input data to provide the output for the analysis.The gained knowledge shows in which extent the results can be used to optimize the existing method. This results are more interesting in the field of segmentation, harmonics, and prediction than in curve smoothing. It is indicated that the correctness of the classification changes a lot by changing the training regions and that segmentation is very a promising approach.