Improving precipitation forecasts in an AI weather model using observational data

2026-09-02

AI Summary

研究通过使用IMERG降水数据微调图变换架构，改进了AI天气模型中的降水预报，提高了中程预报准确性及极端降雨预测技能。

Abstract

Artificial intelligence weather prediction (AIWP) systems now surpass state-of-the-art physical models for medium-range weather forecasting. Current global AIWP models are trained almost exclusively using one reanalysis dataset, ERA5, but it has known biases, particularly for precipitation. Here we fine-tune a graph-transformer architecture with IMERG precipitation data at 0.25° resolution. The resulting model improves medium-range continuous ranked probability scores by up to 19%, while also demonstrating superior skill for tropical storms and drizzle events. Our model exceeds the Brier skill score of state-of-the-art operational models on extreme rainfall prediction by 57% globally; however, a physics-based operational model remains more reliable for the heaviest precipitation events. Our results demonstrate that incorporating observations-based precipitation data directly into training can substantially improve precipitation forecasts.

Problem

• precipitation forecasts
• artificial intelligence weather prediction
• reanalysis dataset
• bias

Innovation

• graph-transformer
• IMERG
• precipitation forecasting
• medium-range weather forecasting
• Brier skill score