arXiv cs.AI· Qiuyan Sun, Mengxuan Chen, Haoyuan Liang, Guowen Li, Zhen Huang, Jianhao Lin, Juepeng Zheng, Haohuan Fu·· 4 小时前AI 评分38
SeasonRainBench:全球季节性降水预测基准与 Sim2Earth 模型
SeasonRainBench: Global Seasonal Precipitation
AI 导读
研究团队推出 SeasonRainBench,首个覆盖未来 1–5 个月月度降水的全球季节性降水预测基准,含全球 1° 卫星降水数据、7 个业务中心及 52 个气候模型生成的 310,944 个模拟月。
正文 · 原文
Abstract:Accurate seasonal precipitation forecasts help societies prepare for drought, flooding, and crop failure months in advance. While data-driven methods have made rapid progress in weather and subseasonal forecasting, operational seasonal precipitation prediction still relies on numerical ensemble systems. These systems are computationally expensive and exhibit biases and drift that increase with lead time, motivating more efficient data-driven alternatives. Yet this transition faces three linked challenges: comparing data-driven forecasts with operational ones requires (1) a global benchmark that does not exist, scoring them requires (2) metrics that capture operational priorities beyond anomaly correlation (ACC) and RMSE, and training them must (3) rely on a single, short observational record. To address the first two challenges, we introduce \BenchName, the first such benchmark, covering monthly precipitation forecasts 1--5 months ahead. It pairs global $1^\circ$ satellite precipitation with oceanic and atmospheric predictors, includes seven operational centers, and provides 310,944 simulated months from 52 climate models for training. Beyond standard scores, we introduce two operationally motivated metrics for anomaly strength and monthly rain-belt position. To address the third challenge, we develop \MODEL, which learns from simulations what the record lacks and transfers it to Earth through three modules: SimForced aligns the climate background, SimMemory transfers a history encoder pretrained on simulations, and SimAnalog supplements Earth labels with simulated analog outcomes. Extensive experiments show that \MODEL{} improves ACC, CRPS, anomaly strength, and rain-belt position by 12.0\%, 3.6\%, 2.9\%, and 0.3\% over the strongest operational or data-driven model, opening a path from simulated worlds to Earth system prediction.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22281 [cs.AI] |
| (or arXiv:2611.22281v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22281 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mengxuan Chen [view email]
[v1]
Tue, 17 Nov 2026 06:32:48 UTC (3,182 KB)
来源:arXiv cs.AI · arxiv.org