Neural Network Training for Prediction of Climatological Time Series, Regularized by Minimization of the Generalized Cross-Validation Function

Abstract Neural network (NN) training is the optimization process by which the relation between the NN input and output is established. A new formulation for the NN training is presented where an NN model is reconstructed such that it produces predicted output data optimally fitting the observed ones. The optimal level of fit is determined by minimization of the generalized cross-validation function, which is integrated in the training. The training process is fully automated, does not require the user to set aside data for validation, and enables objective testing and evaluation of the predictions. Results are demonstrated and discussed using synthetic data produced by Lorenz’s low-order circulation model and on real data from the equatorial Pacific.