用强化学习动态组合多个天气模型，提升预测精度。
An adaptive and evolvable deep reinforcement learning framework for weather prediction
- 通过强化学习动态分配不同模型的融合权重，实现智能集成。
- 在10个气象变量上，误差降低17.2%至78.3%，优于单一模型。
- 可自动淘汰差模型、引入新模型，适合持续更新的天气预测场景。
单一AI天气模型难以在所有变量、气压层和预报时效上表现优异。我们不构建新架构，而是将预报问题重新定义为协同问题。本文提出Feitian Adaptive Ensemble Weather（FTAE-Weather）轻量级框架，通过深度强化学习学习在何时何地信任预训练预报器池中的成员。战术权重代理根据当前大气状态，为不同变量和预报时长分配融合权重；战略演化代理则周期性剔除表现不佳的模型，并吸收新发布的模型。异步预测缓存使训练成本独立于最慢的子模型。仅增加不到0.01%的参数，FTAE-Weather在10个大气变量上相比最优单模型将均方根误差（RMSE）降低17.2%至78.3%，且在72至360小时预报时效内优于传统集合预报基线。该框架将日益增长、碎片化的专业模型库转化为统一预测系统，随领域新架构发布而不断增强，使模型多样性从协调难题变为累积科学优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。