Valid Error Bars for Neural Weather Models using Conformal Prediction

Neural weather models have shown immense potential as inexpensive and accurate alternatives to physics-based models. However, most models trained to perform weather forecasting do not quantify the uncertainty associated with their forecasts. This limits the trust in the model and the usefulness of t...

Full description

Saved in:
Bibliographic Details
Main Authors Gopakumar, Vignesh, Oskarrson, Joel, Gray, Ander, Zanisi, Lorenzo, Pamela, Stanislas, Giles, Daniel, Kusner, Matt, Deisenroth, Marc
Format Journal Article
LanguageEnglish
Published 20.06.2024
Subjects
Computer Science - Learning
Online AccessGet full text

Cover

More Information
Summary:Neural weather models have shown immense potential as inexpensive and accurate alternatives to physics-based models. However, most models trained to perform weather forecasting do not quantify the uncertainty associated with their forecasts. This limits the trust in the model and the usefulness of the forecasts. In this work we construct and formalise a conformal prediction framework as a post-processing method for estimating this uncertainty. The method is model-agnostic and gives calibrated error bounds for all variables, lead times and spatial locations. No modifications are required to the model and the computational cost is negligible compared to model training. We demonstrate the usefulness of the conformal prediction framework on a limited area neural weather model for the Nordic region. We further explore the advantages of the framework for deterministic and probabilistic models.
DOI:10.48550/arxiv.2406.14483