Graph Neural Networks for Enhancing Ensemble Forecasts of Extreme Rainfall
This work addresses the need for more reliable extreme precipitation forecasts to mitigate risks for infrastructure, agriculture, and public safety, representing an incremental advancement in post-processing techniques.
The paper tackles the problem of improving ensemble forecasts for extreme rainfall by developing a graph neural network framework that models spatial dependencies and tail behavior, resulting in enhanced forecast accuracy for extreme events.
Climate change is increasing the occurrence of extreme precipitation events, threatening infrastructure, agriculture, and public safety. Ensemble prediction systems provide probabilistic forecasts but exhibit biases and difficulties in capturing extreme weather. While post-processing techniques aim to enhance forecast accuracy, they rarely focus on precipitation, which exhibits complex spatial dependencies and tail behavior. Our novel framework leverages graph neural networks to post-process ensemble forecasts, specifically modeling the extremes of the underlying distribution. This allows to capture spatial dependencies and improves forecast accuracy for extreme events, thus leading to more reliable forecasts and mitigating risks of extreme precipitation and flooding.