Comparison of non-homogeneous regression models for probabilistic wind speed forecasting

By Sebastian Lerch, Thordis Linda Thorarinsdottir. 2013

103 citations recorded by the source corpus.

In weather forecasting, non-homogeneous regression (NR) is used to statistically post-process forecast ensembles in order to obtain calibrated predictive distributions. For wind speed forecasts, the regression model is given by a truncated normal (TN) distribution, where location and spread derive from the ensemble. This article proposes two alternative approaches which utilise the generalised extreme value (GEV) distribution. A direct alternative to the TN regression is to apply a predictive distribution from the GEV family, while a regime-switching approach based on the median of the forecast ensemble incorporates both distributions. In a case study on daily maximum wind speed over Germany with the forecast ensemble from the European Centre for Medium-Range Weather Forecasts (ECMWF), all three approaches significantly improve the calibration as well as the overall skill of the raw ensemble with the regime-switching approach showing the highest skill in the upper tail.

Subfields: Atmospheric Science, Electrical and Electronic Engineering, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/745d812ca6b6d40122589f8c59ebc732681d7ff3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Electrical and Electronic Engineering

In Environmental Engineering

Citations in the corpus

Bayesian Nonparametric Calibration and Combination of Predictive Distributions (2015, methodology): “-t), linear pooling (NC) and beta mixture calibration (BMC) over the sample period from January 1, 2007 to December 31, 2008. 6.2 Wind speed The second empirical example considers the dataset used in Lerch and Thorarinsdottir (2013).5 It consists of 50 ensemble member predictions (Molteni et al., 19”
Spatial Postprocessing of Ensemble Forecasts for Temperature Using Nonhomogeneous Gaussian Regression (2014, methodology): “While the Gaussian assumption is not appropriate for all weather variables, the basic idea of NGR can also be used with other types of predictive distributions (Thorarinsdottir and Gneiting, 2010; Thorarinsdottir and Johnson, 2012; Lerch and Thorarinsdottir, 2013; Scheuerer, 2014).”
Neural networks for post-processing ensemble weather forecasts (2018, background): “(3) Over the past decade, the EMOS framework has been extended from temperature to other weather variables including wind speed (Thorarinsdottir and Gneiting, 2010; Lerch and Thorarinsdottir, 2013; Baran and Lerch, 2015; Scheuerer and Möller, 2015) and precipitation (Messner et al.”