Abstract : Uncertainty quantification in numerical weather and climate prediction is usually achieved using a Monte Carlo estimation (i.e., ensemble forecasting) of the forecast probability distribution function of the state of the system. In this work, we present a method for uncertainty quantification based on neural networks and using a likelihood-based loss function to train the network. This provides state dependent uncertainty estimation, without the need of integrating an ensemble of forecasts. The method is evaluated with a chaotic low-dimensional model in two scenarios: with stochastic errors only (SE) and systematic and stochastic errors (SSE).
https://hal-imt-atlantique.archives-ouvertes.fr/hal-02942802 Contributor : Pierre TandeoConnect in order to contact the contributor Submitted on : Friday, September 18, 2020 - 12:00:53 PM Last modification on : Monday, April 4, 2022 - 9:28:21 AM Long-term archiving on: : Thursday, December 3, 2020 - 12:27:58 PM
Maximiliano Sacco, yicun Zhen, Pierre Tandeo, Juan Ruiz, Manuel Pulido. Quantification of forecast uncertainty using neural networks. Climate Informatics 2020, Sep 2020, Oxford, United Kingdom. ⟨hal-02942802⟩