Statistical Postprocessing for Weather Forecasts: Review, Challenges, and Avenues in a Big Data World

Vannitsem, Stéphane; Bremnes, John Bjørnar; Demaeyer, Jonathan; Evans, Gavin R.; Flowerdew, Jonathan; Hemri, Stephan; Lerch, Sebastian; Roberts, Nigel; Theis, Susanne; Atencia, Aitor; Bouallègue, Zied Ben; Bhend, Jonas; Dabernig, Markus; Cruz, Lesley De; Hieta, Leila; Mestre, Olivier; Moret, Lionel; Plenković, Iris Odak; Schmeits, Maurice; Taillardat, Maxime; Bergh, Joris Van den; Schaeybroeck, Bert Van; Whan, Kirien; Ylhäisi, Jussi S.

doi:10.1175/bams-d-19-0308.1

Cited by 167 publications

(147 citation statements)

References 137 publications

Supporting

Mentioning

115

Contrasting

Order By: Relevance

“…DICast has evolved over time to include additional machine-learning methods and has been shown to dramatically improve forecasts across multiple weather-dependent applications including road conditions [16], precision agriculture, wind and solar energy [17][18][19][20], among others. Now, many commercial weather companies and national centres employ AI-based post-processing methods [21].…”

Section: (A) Forecast Improvements With Aimentioning

confidence: 99%

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

Haupt

Chapman

Adams

et al. 2021

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

The most mature aspect of applying artificial intelligence (AI)/machine learning (ML) to problems in the atmospheric sciences is likely post-processing of model output. This article provides some history and current state of the science of post-processing with AI for weather and climate models. Deriving from the discussion at the 2019 Oxford workshop on Machine Learning for Weather and Climate, this paper also presents thoughts on medium-term goals to advance such use of AI, which include assuring that algorithms are trustworthy and interpretable, adherence to FAIR data practices to promote usability, and development of techniques that leverage our physical knowledge of the atmosphere. The coauthors propose several actionable items and have initiated one of those: a repository for datasets from various real weather and climate problems that can be addressed using AI. Five such datasets are presented and permanently archived, together with Jupyter notebooks to process them and assess the results in comparison with a baseline technique. The coauthors invite the readers to test their own algorithms in comparison with the baseline and to archive their results. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

show abstract

Section: (A) Forecast Improvements With Aimentioning

confidence: 99%

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

Haupt

Chapman

Adams

et al. 2021

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

show abstract

“…As discussed by Vannitsem et al . (2020), post‐processing methods such as the BMA and EMOS can be easily implemented, but neural networks or analogues are much more flexible. Therefore, another possibility is to assess the trade‐off between complexity and flexibility.…”

Section: Discussionmentioning

confidence: 99%

“…However, ensemble forecasting is under‐dispersive and not calibrated, especially for meteorological parameters near ground level. To overcome this problem, several statistical methods (Wilks, 2006; Wilks and Hamill, 2007; Williams et al ., 2014; Vannitsem et al ., 2019; Vannitsem et al ., 2020) can be used to post‐process the ensemble forecasting. By using the ensemble post‐processing methods, the biases in both location and dispersion are eliminated by a historical database of ensemble forecast errors, and then a predictive probability density function (PDF) can be estimated.…”

Section: Introductionmentioning

confidence: 99%

Comparison of the BMA and EMOS statistical methods for probabilistic quantitative precipitation forecasting

Javanshiri¹,

Fathi

Mohammadi

2021

Meteorological Applications

View full text Add to dashboard Cite

The main approach to probabilistic weather forecasting has been the use of ensemble forecasting. In ensemble forecasting, the probability information is generally derived by using several numerical model runs, with perturbation of the initial conditions, physical schemes or dynamic core of the numerical weather prediction (NWP) models. However, ensemble forecasting usually tends to be under‐dispersive. Statistical post‐processing has, therefore, become an essential component of any ensemble prediction system aiming to improve the quality of numerical weather forecasts as they seek to generate calibrated and sharp predictive distributions of future weather quantities. Different versions of the ensemble model output statistics (EMOS) and the Bayesian model averaging (BMA) post‐processing methods are used in the present paper to calibrate 24, 48 and 72 hr forecasts of 24 hr accumulative precipitation. The ensemble employs the weather and research forecasting (WRF) model with eight different configurations which were run over Iran for six months (September 2015–February 2016). The results reveal that the BMA and EMOS‐censored, shifted gamma (CSG) techniques are substantially successful at improving the raw WRF ensemble forecasts; however, each approach improves different aspects of the forecast quality. The BMA method is more accurate, skilful and reliable than the EMOS‐CSG method, but has poorer discrimination. Moreover, it has better resolution in predicting the probability of high‐precipitation events than the EMOS‐CSG method.

show abstract

“…First called ensemble‐MOS (EMOS), statistical post‐processing of ensemble forecasts has been a primary focus of the meteorological community for the past two decades (Gneiting and Raftery, 2005; Vannitsem and Hagedorn, 2011; Vannitsem et al ., 2018, 2020). The goal of the EMOS, and probabilistic forecasting in general, is to create sharp probabilistic forecasts, while retaining reliability (calibration) (Wilks, 2018).…”

Section: Introductionmentioning

confidence: 99%

A comparison of statistical and dynamical downscaling methods for short‐term weather forecasts in the US Northeast

Alessi

DeGaetano

2021

Meteorological Applications

View full text Add to dashboard Cite

The Weather Research and Forecasting model (WRF) was used to produce both 9 and 3 km resolution ensemble forecasts from the deterministic Global Forecast System (GFS) model for microclimatic, agricultural regions in New York State. The forecasts were then statistically post‐processed to generate probabilistic forecasts for surface temperature (T), specific humidity (q), incoming solar radiation (SR) and precipitation (P). T was post‐processed with non‐homogeneous Gaussian regression (NGR), q and SR with truncated NGR, and P with extended logistic regression. A comparison of forecast skill was conducted between these post‐processed forecasts, the raw WRF output, the GFS forecasts and forecasts from the National Weather Service's deterministic National Digital Forecast Database (NDFD). Overall, significant improvement was observed in post‐processed WRF forecasts over all other methods for all locations and variables. Furthermore, raw WRF ensembles were found to outperform deterministic NDFD, so that if observational data are unavailable for post‐processing, dynamically downscaled WRF should be selected over deterministic, human‐altered NDFD forecasts. Finally, the 9 km post‐processed WRF had the same forecast skill as the 3 km post‐processed WRF, except for precipitation, rendering the 3 km WRF unnecessary if observational data are available, saving computational cost.

show abstract

Statistical Postprocessing for Weather Forecasts: Review, Challenges, and Avenues in a Big Data World

Abstract: CapsuleState-of-the-Art statistical postprocessing techniques for ensemble forecasts are reviewed, together with the challenges posed by a demand for timely, high-resolution and reliable probabilistic information. Possible research avenues are also discussed.

Cited by 167 publications

References 137 publications

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop

Comparison of the BMA and EMOS statistical methods for probabilistic quantitative precipitation forecasting

A comparison of statistical and dynamical downscaling methods for short‐term weather forecasts in the US Northeast

Contact Info

Product

Resources

About