Abstract: Data assimilation is an essential step for improving space weather forecasting by means of a weighted combination between observational and simulated data. In the present work data assimilation methods based on Kalman filter and artificial neural networks are applied to a three-wave model of auroral radio emissions. We present a novel data assimilation method, whereby a multilayer Perceptron neural network is trained to emulate a Kalman filter for data assimilation by using cross validation. The results obtained render support for the use of neural networks as an assimilation technique for space weather prediction.