Given their nature, extreme events are difficult to model for most Machine Learning algorithms when the data is not abundant. More specifically, daily Earth Observations from satellite data back only twenty years, making the data driven approach to extremes more complex. My goal is to investigate the ability of a relatively modern architecture, called Reservoir Computing, to deal with this kind of situations. Based on a fixed internal layer, the model is based on an expansion of the input data onto a higher dimension. The training is done by simple regression, slashing computational costs and time while providing state of the art results in time series forecasting.