发表机构
University of Oxford; AfriClimate AI; ECMWF; University of Witwatersrand（牛津大学; 非洲气候人工智能组织; 欧洲中期天气预报中心; 金山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究比较了AI模型与物理NWP模型在非洲的降雨预报技能，发现AI模型在湿润地区优于IFS，中位改进约5%，且GraphCast与FGN技能相当，展示了校准AI预报的潜力。
AI 中文摘要
基于人工智能（AI）的天气预报正在以极低的计算成本接近物理数值天气预报（NWP）系统的技能水平。这对非洲尤其具有前景，因为该地区的极端降雨正在加剧，且许多预报中心缺乏在延长预报时效下运行物理模型的基础设施。我们针对非洲降雨预测，提出了GraphCast、GenCast和功能生成网络（FGN）与物理NWP模型IFS的校准比较。确定性预报和概率预报均使用等渗分布回归进行后处理，并使用连续排序概率评分（CRPS）与IMERG、RFEv2和CHIRPS数据在不同季节、干湿状态、海拔区域和预报时效下进行评估。所有模型在大多数季节和延长预报时效下均保持超越气候态的技能。AI模型在湿润地区普遍优于IFS，而IFS在干燥的高海拔地区表现更好，其更精细的分辨率能更好地表征地形对降雨的控制作用。跨观测数据集和季节，AI模型相对于IFS的中位改进约为5%。GraphCast实现了与基于集合的FGN相当的校准技能，尽管FGN在更长预报时效下提供了更显著的技能优势。这些结果突显了校准AI天气预报在非洲提供可获取且计算高效的降雨预报的潜力，同时展示了空间分辨率、集合设计和区域特征的持续重要性。
英文摘要
Artificial intelligence (AI)-based weather prediction is approaching the skill of physical numerical weather prediction (NWP) systems at a fraction of the computational cost. This is particularly promising for Africa, where rainfall extremes are intensifying and many forecasting centres lack the infrastructure to run physical models at extended lead times. We present a calibrated comparison of GraphCast, GenCast and the Functional Generative Network (FGN) against the physical NWP model IFS for rainfall prediction across Africa. Deterministic and probabilistic forecasts are postprocessed using Isotonic Distributional Regression and evaluated with the Continuous Ranked Probability Score against IMERG, RFEv2 and CHIRPS across seasons, wet and dry regimes, elevation zones and lead times. All models retain skill beyond climatology across most seasons and at extended lead times. AI models generally outperform IFS in wet regions, whereas IFS performs better in dry, high-elevation areas, where its finer resolution better represents orographic controls on rainfall. Across observational datasets and seasons, AI models achieve a median improvement of approximately 5% over IFS. GraphCast achieves calibrated skill comparable to the ensemble-based FGN, although FGN provides greater significant skill at longer lead times. These results highlight the potential of calibrated AI weather prediction to provide accessible and computationally efficient rainfall forecasts across Africa, while demonstrating the continuing importance of spatial resolution, ensemble design and regional characteristics.
Comments19 pages, 11 figures (excluding supplementary and references)
