Ensemble neural network forecasts with singular value decomposition

by   Sebastian Scher, et al.

Ensemble weather forecasts enable a measure of uncertainty to be attached to each forecast by computing the ensemble's spread. However, generating an ensemble with a good error-spread relationship is far from trivial, and a wide range of approaches to achieve this have been explored. Random perturbations of the initial model state typically provide unsatisfactory results when applied to numerical weather prediction models. Singular value decomposition has proved more successful in this context, and as a result has been widely used for creating perturbed initial states of weather prediction models. We demonstrate how to apply the technique of singular value decomposition to purely neural-network based forecasts. Additionally, we explore the use of random initial perturbations for neural network ensembles, and the creation of neural network ensembles via retraining the network. We find that the singular value decomposition results in ensemble forecasts that have some probabilistic skill, but are inferior to the ensemble created by retraining the neural network several times. Compared to random initial perturbations, the singular value technique performs better when forecasting a simple general circulation model, comparably when forecasting atmospheric reanalysis data, and worse when forecasting the lorenz95 system - a highly idealized model designed to mimic certain aspects of the mid-latitude atmosphere.


page 11

page 13


Singular Value Decomposition and Neural Networks

Singular Value Decomposition (SVD) constitutes a bridge between the line...

SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models

Probabilistic forecasting is crucial to decision-making under uncertaint...

Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models

We present an ensemble prediction system using a Deep Learning Weather P...

Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks

Statistical postprocessing is used to translate ensembles of raw numeric...

A computationally efficient neural network for predicting weather forecast probabilities

The success of deep learning techniques over the last decades has opened...

Learning the Pseudoinverse Solution to Network Weights

The last decade has seen the parallel emergence in computational neurosc...

Bad and good errors: value-weighted skill scores in deep ensemble learning

In this paper we propose a novel approach to realize forecast verificati...

Please sign up or login with your details

Forgot password? Click here to reset