Ensembling geophysical models with Bayesian Neural Networks

10/07/2020
by   Ushnish Sengupta, et al.
0

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

page 6

page 7

research
12/31/2019

Combining interdependent climate model outputs in CMIP5: A spatial Bayesian approach

Projections of future climate change rely heavily on climate models, and...
research
05/05/2021

PCE-PINNs: Physics-Informed Neural Networks for Uncertainty Propagation in Ocean Modeling

Climate models project an uncertainty range of possible warming scenario...
research
11/17/2022

Fast Uncertainty Estimates in Deep Learning Interatomic Potentials

Deep learning has emerged as a promising paradigm to give access to high...
research
10/10/2019

Late 19th-Century Navigational Uncertainties and Their Influence on Sea Surface Temperature Estimates

Accurate estimates of historical changes in sea surface temperatures (SS...
research
11/16/2019

Exploiting Oxide Based Resistive RAM Variability for Bayesian Neural Network Hardware Design

Uncertainty plays a key role in real-time machine learning. As a signifi...
research
06/21/2020

Learned Uncertainty-Aware (LUNA) Bases for Bayesian Regression using Multi-Headed Auxiliary Networks

Neural Linear Models (NLM) are deep models that produce predictive uncer...
research
02/08/2021

A safety factor approach to designing urban infrastructure for dynamic conditions

Current approaches to design flood-sensitive infrastructure typically as...

Please sign up or login with your details

Forgot password? Click here to reset