Home > Research > Publications & Outputs > Ensembling geophysical models with Bayesian Neu...
View graph of relations

Ensembling geophysical models with Bayesian Neural Networks

Research output: Contribution to journalConference articlepeer-review

Published
Close
<mark>Journal publication date</mark>7/10/2020
<mark>Journal</mark>Advances in Neural Information Processing Systems
Volume33
Number of pages13
Pages (from-to)1-13
Publication StatusPublished
<mark>Original language</mark>English

Abstract

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.