Constraint optimization for Echo State Networks applied to satellite image forecasting

Abstract

The paper proposes to deal with noisy, sparse or short training data sequences by adding domain knowledge to the learning process of Echo State Networks (ESNs). Known constraints like monotony in the output, periodicity or bounds on output values are encoded as inequality constraints on the output weights to be learned. Exploiting that the output of an ESN is linear in the weights, Quadratic Programming is then used to obtain and optimize these. The method is applied to the prediction of pixel values from monthly, noisy satellite images of a short history of five years, thereby enabling the cleaning of images from clouds or snow.