# Ensembling geophysical models with Bayesian Neural Networks

arXiv: https://arxiv.org/abs/2010.03561 · HTML: https://mlsanity.com/paper/2010.03561/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling](https://mlsanity.com/paper/2102.13156/) (2021)
- [Uncertainty Quantification in Seismic Inversion Through Integrated Importance Sampling and Ensemble Methods](https://mlsanity.com/paper/2409.06840/) (2024)
- [Physics-integrated generative modeling using attentive planar normalizing flow based variational autoencoder](https://mlsanity.com/paper/2404.12267/) (2024)
- [mloz: A Highly Efficient Machine Learning-Based Ozone Parameterization for Climate Sensitivity Simulations](https://mlsanity.com/paper/2509.20422/) (2025)
- [Online parameter inference for the simulation of a Bunsen flame using heteroscedastic Bayesian neural network ensembles](https://mlsanity.com/paper/2104.13201/) (2021)
- [Deep Learning with Physics Priors as Generalized Regularizers](https://mlsanity.com/paper/2312.08678/) (2023)
- [Modeling Weather Uncertainty for Multi-weather Co-Presence Estimation](https://mlsanity.com/paper/2403.20092/) (2024)

## Abstract (arXiv)

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.