The EUPPBench postprocessing benchmark dataset v1.0

Demaeyer, Jonathan; Bhend, Jonas; Lerch, Sebastian; Primo, Cristina; Schaeybroeck, Bert Van; Atencia, Aitor; Bouallègue, Zied Ben; Chen, Jieyu; Dabernig, Markus; Evans, Gavin; Pucer, Jana Faganeli; Hooper, Ben; Horat, Nina; Jobst, David; Merše, Janko; Mlakar, Peter; Möller, Annette; Mestre, Olivier; Taillardat, Maxime; Vannitsem, Stéphane

doi:10.5194/essd-15-2635-2023

Cited by 8 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These diurnal-cycle-dependent differences in performance are also found in other studies (see e.g. Dabernig et al, 2017a) but are removed by the comparatively complex Atmosphere NETwork (ANET) model in Demaeyer et al (2023); Mlakar et al (2023). The reason for these variations in performance and which models are suitable to remove them is an interesting question for future research.…”

Section: Comparisonsupporting

confidence: 77%

Lead‐time‐continuous statistical postprocessing of ensemble weather forecasts

Wessel,

Ferro,

Kwasniok

2024

Quart J Royal Meteoro Soc

View full text Add to dashboard Cite

Numerical weather prediction (NWP) ensembles often exhibit biases and errors in dispersion, so they need some form of postprocessing to yield sharp and well‐calibrated probabilistic predictions. The output of NWP models is usually at a multiplicity of different lead times and, even though information is often required on this range of lead times, many postprocessing methods in the literature are applied either at a fixed lead time or by fitting individual models for each lead time. However, this is (1) computationally expensive because it requires the training of multiple models if users are interested in information at multiple lead times and (2) prohibitive because it restricts the data used for training postprocessing models and the usability of fitted models. This article investigates the lead‐time dependence of postprocessing methods in the idealized Lorenz'96 system as well as temperature and wind‐speed forecast data from the Met Office Global and Regional Ensemble Prediction System (MOGREPS‐G). The results indicate that there is substantial regularity between the models fitted for different lead times and that one can fit models that are lead‐time‐continuous that work for multiple lead times simultaneously by including lead time as a covariate. These models achieve similar and, in small data situations, even improved performance compared with the classical lead‐time‐separated models, whilst saving substantial computation time.

show abstract

Section: Comparisonsupporting

confidence: 77%

Lead‐time‐continuous statistical postprocessing of ensemble weather forecasts

Wessel,

Ferro,

Kwasniok

2024

Quart J Royal Meteoro Soc

View full text Add to dashboard Cite

show abstract

“…We also investigate visibility data from the EUPPBench benchmark dataset (Demaeyer et al, 2023), where besides the 51‐member operational ECMWF ensemble, the high‐resolution (HRES) forecast is also available. The studied dataset consists of ensemble forecasts for calendar years 2017–2018 initialized at 0000 UTC with a forecast horizon of 120 h and temporal resolution of 6 h for 42 SYNOP stations in Germany and France (Figure 1b).…”

Section: Datamentioning

confidence: 99%

Statistical post‐processing of visibility ensemble forecasts

Baran,

Lakatos

2023

Meteorological Applications

View full text Add to dashboard Cite

To be able to produce accurate and reliable predictions of visibility has crucial importance in aviation meteorology, as well as in water‐ and road transportation. Nowadays, several meteorological services provide ensemble forecasts of visibility; however, the skill and reliability of visibility predictions are far reduced compared with other variables, such as temperature or wind speed. Hence, some form of calibration is strongly advised, which usually means estimation of the predictive distribution of the weather quantity at hand either by parametric or nonparametric approaches, including machine learning‐based techniques. As visibility observations—according to the suggestion of the World Meteorological Organization—are usually reported in discrete values, the predictive distribution for this particular variable is a discrete probability law, hence calibration can be reduced to a classification problem. Based on visibility ensemble forecasts of the European Centre for Medium‐Range Weather Forecasts covering two slightly overlapping domains in Central and Western Europe and two different time periods, we investigate the predictive performance of locally, semi‐locally and regionally trained proportional odds logistic regression (POLR) and multilayer perceptron (MLP) neural network classifiers. We show that while climatological forecasts outperform the raw ensemble by a wide margin, post‐processing results in further substantial improvement in forecast skill, and in general, POLR models are superior to their MLP counterparts.

show abstract

“…For the implementation details of this initial network, see Sections 4.1.1 and 4.2.1. Note that a similar pooling of lead times is used in the Atmosphere NETwork approach described, for example, in Demaeyer et al (2023).…”

Section: Mlp-s Modelmentioning

confidence: 99%

A two‐step machine‐learning approach to statistical post‐processing of weather forecasts for power generation

Baran,

Baran

2023

Quart J Royal Meteoro Soc

View full text Add to dashboard Cite

By the end of 2021, the renewable energy share of the global electricity capacity reached 38.3% and the new installations were dominated by wind and solar energy, showing global increases of 12.7% and 18.5% respectively. However, both wind and photovoltaic energy sources are highly volatile, making planning difficult for grid operators; thuss, accurate forecasts of the corresponding weather variables are essential for reliable electricity predictions. The most advanced approach in weather prediction is the ensemble method, which opens the door for probabilistic forecasting. However, ensemble forecasts are often underdispersive and subject to systematic bias. Hence, they require some form of statistical post‐processing, where parametric models provide full predictive distributions of the weather variables at hand. We propose a general two‐step machine‐learning‐based approach to calibrating ensemble weather forecasts, where, in the first step, improved point forecasts are generated, which then together with various ensemble statistics serve as input features of the neural network estimating the parameters of the predictive distribution. In two case studies based on 100 m wind speed and global horizontal irradiance forecasts of the operational ensemble prediction system of the Hungarian Meteorological Service, the predictive performance of this novel method is compared with the forecast skill of the raw ensemble and the state‐of‐the‐art parametric approaches. Both case studies confirm that, at least up to 48 hr, statistical post‐processing substantially improves the predictive performance of the raw ensemble for all forecast horizons considered. The variants of the proposed two‐step method investigated outperform in skill their competitors, and the suggested new approach is well applicable for different weather quantities and for a fair range of predictive distributions.

show abstract

The EUPPBench postprocessing benchmark dataset v1.0

Cited by 8 publications

References 45 publications

Lead‐time‐continuous statistical postprocessing of ensemble weather forecasts

Lead‐time‐continuous statistical postprocessing of ensemble weather forecasts

Statistical post‐processing of visibility ensemble forecasts

A two‐step machine‐learning approach to statistical post‐processing of weather forecasts for power generation

Contact Info

Product

Resources

About