Probabilistic & ensemble forecasting
Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts
In one sentence. Sinh-arcsinh-normal output distributions give neural networks asymmetric, heteroscedastic uncertainty, demonstrated on tropical cyclone intensity forecast errors.
Abstract
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 to 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.
Labels
- Topic
- Probabilistic & ensemble forecasting, Explainability, uncertainty & physics
- Type
- New model or method
- Method
- Other
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.1017/eds.2023.7 OpenAlex:W4380987700
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.