Improving predictions of convective storm wind gusts through statistical post-processing of neural weather models

TL;DR

This paper shows how using advanced weather models and statistical methods can improve predictions of strong wind gusts from thunderstorms, helping with early warnings.

Contribution

The novel approach uses a convolutional neural network to post-process neural weather model outputs, improving wind gust forecasts.

Findings

A convolutional neural network outperforms direct forecasting for wind gust predictions.

Statistical robustness is achieved using generalized extreme-value distributions in five Swiss regions.

Neural weather models add value for forecasting extreme winds up to three days ahead.

Abstract

Issuing timely severe weather warnings helps mitigate potentially disastrous consequences. Recent advancements in Neural Weather Models (NWMs) offer a computationally inexpensive and fast approach for forecasting atmospheric environments on a 0.25° global grid. For thunderstorms, these environments can be empirically post-processed to predict wind gust distributions at specific locations. With the Pangu-Weather NWM, we apply a hierarchy of statistical and deep learning post-processing methods to forecast hourly wind gusts up to three days ahead. To ensure statistical robustness, we constrain our probabilistic forecasts using generalised extreme-value distributions across five regions in Switzerland. Using a convolutional neural network to post-process the predicted atmospheric environment’s spatial patterns yields the best results, outperforming direct forecasting approaches across lead times and wind gust speeds. Our results confirm the added value of NWMs for extreme wind forecasting, especially for designing more responsive early-warning systems.

Figures