Ensembling geophysical models with Bayesian Neural Networks
This work addresses the need for more accurate and uncertainty-aware projections in geophysical modeling, particularly for ozone prediction, though it is incremental as it builds on existing ensembling methods with a novel data-driven approach.
The authors tackled the problem of improving accuracy and uncertainty quantification in geophysical model ensembles by developing a Bayesian Neural Network ensemble (BayNNE) method, which achieved a 49.4% reduction in RMSE for temporal extrapolation and a 67.4% reduction for polar data voids compared to a weighted mean.
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% reduction in RMSE for temporal extrapolation, and a 67.4% reduction in RMSE for polar data voids, compared to a weighted mean. Uncertainty is also well-characterized, with 90.6% of the data points in our extrapolation validation dataset lying within 2 standard deviations and 98.5% within 3 standard deviations.