发表机构
The Moonshot Factory, Google LLC; Google LLC; California Institute of Technology; Stanford University（Moonshot工厂、谷歌有限责任公司; 谷歌有限责任公司; 加州理工学院; 斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对AI天气模型降水预报偏差问题，用IMERG降水数据微调图变换器架构，使中期预报评分提升，极端降雨预测表现优于业务模型，验证了融入观测数据可改进降水预报。
AI 中文摘要
人工智能天气预测（AIWP）系统在中期天气预报中已超越最先进的物理模型。当前全球AIWP模型几乎仅用再分析数据集ERA5训练，但它存在已知偏差，尤其在降水方面。本文对图变换器架构进行微调，采用0.25°分辨率的IMERG降水数据。所得模型将中期连续等级概率评分提升最多19%，且在热带风暴和毛毛雨事件上表现出更优技能；在极端降雨预测中，其Brier技能评分在全球范围内比最先进的业务模型高出57%，不过对于最强降水事件，基于物理的业务模型仍更可靠。研究结果表明，将基于观测的降水数据直接融入训练可大幅提升降水预报效果。
英文摘要
Precipitation forecasts shape decision-making across the global economy, particularly in sectors such as agriculture. However, unlike variables such as temperature, precipitation is highly intermittent and localized, making it difficult to forecast. While recent advances in AI weather prediction systems have enabled them to surpass physical models on globally averaged metrics, improvements in mean error rarely translate to actionable forecasts of severe flooding or dry crop fields. Furthermore, most of these models are trained and evaluated against a reanalysis data product, ERA5, which has well-known biases. Here we retrain AIFS, ECMWF's widely-used, open-source operational 0.25° probabilistic graph-transformer weather model, on satellite-based precipitation observations. Our model, Laxmi, improves global probabilistic accuracy by 19% and resolves systematic distributional biases in ERA5. Specifically, Laxmi reduces drizzle overprediction by 33% for amounts less than 3 mm per day. It also mitigates extreme rainfall underprediction, improving the global 95th percentile Brier skill score by 57%. Across a case study of 10 Indian tropical storms, Laxmi delivered the most accurate forecast of 150 mm event-total precipitation in 7 events, compared to 1 for AIFS and 2 for the leading physical model, IFS. Our results demonstrate that incorporating observation-based precipitation data directly into training can substantially improve forecasts.
Comments16 pages, 4 figures. Submitted
