AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Ensembling geophysical models with Bayesian Neural Networks

Ushnish Sengupta, Matt Amos, Scott Hosking, Carl Edward Rasmussen, Matthew Juniper, Paul Young

NeurIPS 2020 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
BayNNE instead of multi model meanozone ensembling · Temporal extrapolationRMSE (DU): 15.7 -> 4.4Improved
BayNNE instead of spatially weighted meanozone ensembling · South polar extrapolationRMSE (DU): 19.6 -> 6.6Improved
BayNNE instead of spatially weighted meanozone ensembling · North polar extrapolationRMSE (DU): 6.6 -> 4.7Improved
BayNNE instead of multi model meanozone ensembling · North polar extrapolationRMSE (DU): 8.8 -> 4.7Improved
BayNNE instead of spatially weighted meanozone ensembling · Tropics interpolationRMSE (DU): 5.5 -> 2.7Improved
BayNNE instead of spatiotemporal kriginginterpolation · Tropics interpolationRMSE (DU): 7.0 -> 2.7Improved
BayNNE instead of bilinear interpolationinterpolation · Tropics interpolationRMSE (DU): 31.2 -> 2.7Improved
BayNNE instead of bilinear interpolationinterpolation · Satellite voids interpolationRMSE (DU): 1.7 -> 2.1Hurt
BayNNE instead of spatiotemporal kriginginterpolation · Satellite voids interpolationRMSE (DU): 2.2 -> 2.1No clear effect
BayNNE instead of kriginginterpolation · Small features interpolationRMSE (DU): 3.4 -> 3.2No clear effect
BayNNE instead of weighted meanozone ensembling · Temporal extrapolationRMSE (DU): 8.7 -> 4.4Improved
BayNNE instead of multi model meanozone ensembling · South polar extrapolationRMSE (DU): 30.5 -> 6.6Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy