Improving Medium Range Severe Weather Prediction through Transformer Post-processing of AI Weather Forecasts

TL;DR

This paper presents a transformer-based post-processing method for AI weather forecasts that significantly improves medium-range severe weather prediction accuracy and reliability, outperforming traditional neural networks and GFS forecasts.

Contribution

The study introduces a novel transformer-based post-processing approach that models temporal relationships in weather forecasts, enhancing prediction skill over existing methods.

Findings

Transformer post-processing outperforms dense neural networks.

AI forecasts, especially Pangu-Weather, surpass GFS in medium-range prediction.

The method provides interpretable feature attribution analysis.

Abstract

Improving the skill of medium-range (3-8 day) severe weather prediction is crucial for mitigating societal impacts. This study introduces a novel approach leveraging decoder-only transformer networks to post-process AI-based weather forecasts, specifically from the Pangu-Weather model, for improved severe weather guidance. Unlike traditional post-processing methods that use a dense neural network to predict the probability of severe weather using discrete forecast samples, our method treats forecast lead times as sequential ``tokens'', enabling the transformer to learn complex temporal relationships within the evolving atmospheric state. We compare this approach against post-processing of the Global Forecast System (GFS) using both a traditional dense neural network and our transformer, as well as configurations that exclude convective parameters to fairly evaluate the impact of using the Pangu-Weather AI model. Results demonstrate that the transformer-based post-processing significantly enhances forecast skill compared to dense neural networks. Furthermore, AI-driven forecasts, particularly Pangu-Weather initialized from high resolution analysis, exhibit superior performance to GFS in the medium-range, even without explicit convective parameters. Our approach offers improved accuracy, and reliability, which also provides interpretability through feature attribution analysis, advancing medium-range severe weather prediction capabilities.