发表机构
Collaborative Innovation Center for Western Ecological Safety; Lanzhou University（西部生态安全协同创新中心; 兰州大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出FTAE-Weather框架，通过深度强化学习协调预训练气象模型，以极低额外参数实现预报误差显著降低，优于传统集合基线，将模型多样性转化为科学优势。
AI 中文摘要
目前没有任何单一AI气象模型能在所有变量、气压层和预报时效上表现出色，因此我们将预报问题重新定义为协调问题，而非构建新架构。本文提出Feitian自适应集合气象框架（FTAE-Weather），这是一个轻量级框架，通过深度强化学习学习何时、何地信任预训练预报器开放池中的每个成员。战术权重智能体（Weight-Agent）读取当前大气状态，分配针对变量和时效的融合权重；战略演化智能体（Evolve-Agent）定期修剪表现不佳的模型并吸收新发布的模型。异步预测缓存机制使训练成本与最慢的组成模型无关。FTAE-Weather仅增加不到0.01%的额外参数，在10个大气变量上比最优单一模型降低17.2%至78.3%的均方根误差（RMSE），在72至360小时的预报时效上优于传统集合基线。该框架将不断增长、分散的专业模型集合转化为单一预报系统，随着AI气象预报领域发布新架构而不断强化，将模型多样性从协调挑战转化为可累积的科学优势。
英文摘要
No single AI weather model excels at all variables, pressure levels, and lead times. Rather than building yet another architecture, we reframe the forecasting problem as one of coordination. Here we present Feitian Adaptive Ensemble Weather (FTAE-Weather), a lightweight framework that learns, through deep reinforcement learning, when and where to trust each member of an open pool of pretrained forecasters. A tactical Weight-Agent reads the current atmospheric state and assigns variable- and horizon-specific fusion weights, while a strategic Evolve-Agent periodically prunes underperforming models and absorbs newly released ones. Asynchronous prediction caching keeps training cost independent of the slowest constituent model. Adding fewer than 0.01 percent extra parameters, FTAE-Weather reduces RMSE by from 17.2 percent to 78.3 percent over the best individual model in 10 atmospheric variables and outperforms conventional ensemble baselines across lead times from 72 to 360 hours. The framework thus converts a growing, fragmented inventory of specialist models into a single prediction system that strengthens as the field of AI weather forecasting releases new architectures-turning model diversity from a coordination challenge into a compounding scientific advantage.
