# Improving probabilistic forecasts of extreme wind speeds by training statistical post-processing models with weighted scoring rules

arXiv: https://arxiv.org/abs/2407.15900 · HTML: https://mlsanity.com/paper/2407.15900/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 72 references that are in the map.
- First posted on arXiv 22 Jul 2024.

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural networks for post-processing ensemble weather forecasts](https://mlsanity.com/paper/1805.09091/) (2018)
- [Regression Diagnostics meets Forecast Evaluation: Conditional Calibration, Reliability Diagrams, and Coefficient of Determination](https://mlsanity.com/paper/2108.03210/) (2021)
- [The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression](https://mlsanity.com/paper/2202.09101/) (2022)
- [Generative machine learning methods for multivariate ensemble post-processing](https://mlsanity.com/paper/2211.01345/) (2022)
- [CRPS Learning](https://mlsanity.com/paper/2102.00968/) (2021)
- [Forecaster's Dilemma: Extreme Events and Forecast Evaluation](https://mlsanity.com/paper/1512.09244/) (2015)
- [Gradient boosting for extreme quantile regression](https://mlsanity.com/paper/2103.00808/) (2021)
- [Evaluating forecasts for high-impact events using transformed kernel scores](https://mlsanity.com/paper/2202.12732/) (2022)
- [Log-normal distribution based EMOS models for probabilistic wind speed forecasting](https://mlsanity.com/paper/1407.3252/) (2014)
- [Combining predictive distributions for statistical post-processing of ensemble forecasts](https://mlsanity.com/paper/1607.08096/) (2016)
- [Evaluating probabilistic forecasts of extremes using continuous ranked probability score distributions](https://mlsanity.com/paper/1905.04022/) (2019)
- [Tail calibration of probabilistic forecasts](https://mlsanity.com/paper/2407.03167/) (2024)
- [Assessing the calibration of high-dimensional ensemble forecasts using rank histograms](https://mlsanity.com/paper/1310.0236/) (2013)
- [Censored and shifted gamma distribution based EMOS model for probabilistic quantitative precipitation forecasting](https://mlsanity.com/paper/1512.04068/) (2015)
- [Forest-based methods and ensemble model output statistics for rainfall ensemble forecasting](https://mlsanity.com/paper/1711.10937/) (2017)
- [Improving precipitation forecasts using extreme quantile regression](https://mlsanity.com/paper/1806.05429/) (2018)
- [Statistical Post-Processing of Forecasts for Extremes Using Bivariate Brown-Resnick Processes with an Application to Wind Gusts](https://mlsanity.com/paper/1312.4584/) (2013)
- [CRPS M-estimation for max-stable models](https://mlsanity.com/paper/1307.7209/) (2013)

## Built on by (most cited first, 2 of 2)

- [Enforcing tail calibration when training probabilistic forecast models](https://mlsanity.com/paper/2506.13687/) (2025)
- [DeepL'evy: Learning Heavy-Tailed Uncertainty in Highly Volatile Time Series](https://mlsanity.com/paper/2605.10364/) (2026)

## Abstract (arXiv)

Accurate forecasts of extreme wind speeds are of high importance for many applications. Such forecasts are usually generated by ensembles of numerical weather prediction (NWP) models, which however can be biased and have errors in dispersion, thus necessitating the application of statistical post-processing techniques. In this work we aim to improve statistical post-processing models for probabilistic predictions of extreme wind speeds. We do this by adjusting the training procedure used to fit ensemble model output statistics (EMOS) models - a commonly applied post-processing technique - and propose estimating parameters using the so-called threshold-weighted continuous ranked probability score (twCRPS), a proper scoring rule that places special emphasis on predictions over a threshold. We show that training using the twCRPS leads to improved extreme event performance of post-processing models for a variety of thresholds. We find a distribution body-tail trade-off where improved performance for probabilistic predictions of extreme events comes with worse performance for predictions of the distribution body. However, we introduce strategies to mitigate this trade-off based on weighted training and linear pooling. Finally, we consider some synthetic experiments to explain the training impact of the twCRPS and derive closed-form expressions of the twCRPS for a number of distributions, giving the first such collection in the literature. The results will enable researchers and practitioners alike to improve the performance of probabilistic forecasting models for extremes and other events of interest.