Ensembling geophysical models with Bayesian Neural Networks
share
Ensembles of geophysical models improve projection accuracy and express uncertainties. We develop a novel data-driven ensembling strategy for combining geophysical models using Bayesian Neural Networks, which infers spatiotemporally varying model weights and bias while accounting for heteroscedastic uncertainties in the observations. This produces more accurate and uncertainty-aware projections without sacrificing interpretability. Applied to the prediction of total column ozone from an ensemble of 15 chemistry-climate models, we find that the Bayesian neural network ensemble (BayNNE) outperforms existing ensembling methods, achieving a 49.4 in RMSE for temporal extrapolation, and a 67.4 data voids, compared to a weighted mean. Uncertainty is also well-characterized, with 90.6 validation dataset lying within 2 standard deviations and 98.5 standard deviations.
READ FULL TEXT