Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts
Environmental Data Science · 2023 · 2
DOI: 10.1017/eds.2023.7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Data Science, online erschienen am 15.06.2023. Verfasst von Elizabeth A. Barnes und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Directorate for Geosciences.
Abstract (Originalsprache)
A simple method for adding uncertainty to neural network regression tasks in earth science via estimation of a general probability distribution is described. Specifically, we highlight the sinh-arcsinh-normal distributions as particularly well suited for neural network uncertainty estimation. The methodology supports estimation of heteroscedastic, asymmetric uncertainties by a simple modification of the network output and loss function. Method performance is demonstrated by predicting tropical cyclone intensity forecast uncertainty and by comparing two other common methods for neural network uncertainty quantification (i.e., Bayesian neural networks and Monte Carlo dropout). The simple approach described here is intuitive and applicable when no prior exists and one just wishes to parameterize the output and its uncertainty according to some previously defined family of distributions. The authors believe it will become a powerful, go-to method moving forward.
Förderung
- Directorate for Geosciences
Zitieren
APA
Barnes, E. A., Barnes, R. J., & DeMaria, M. (2023). Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts. Environmental Data Science, 2. https://doi.org/10.1017/eds.2023.7
Vancouver
Barnes EA, Barnes RJ, DeMaria M. Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts. Environmental Data Science. 2023;2. doi:10.1017/eds.2023.7
BibTeX
@article{Barnes2023,
author = {Barnes, Elizabeth A. and Barnes, Randal J. and DeMaria, Mark},
title = {Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts},
journal = {Environmental Data Science},
year = {2023},
volume = {2},
doi = {10.1017/eds.2023.7}
}
EUVIMED