Ensemble Methods for Neural Network?Based Weather Forecasts

Ensemble weather forecasts enable a measure of uncertainty to be attached each forecast, by computing the ensemble's spread. However, generating an ensemble with good spread-error relationship is far from trivial, and wide range approaches achieve this have been explored—chiefly in context numerical prediction models. Here, we aim transform deterministic neural network forecasting system into system. We test four methods generate ensemble: random initial perturbations, retraining network, use dropout creation perturbations singular vector decomposition. The latter method widely used models, but yet tested on networks. mean obtained these all beat unperturbed forecasts, yielding highest improvement. skill systematically lower than that state-of-the-art