VA-MoE：面向增量天气预报的变量自适应专家混合模型
VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting
AI总结：
本文提出变量自适应专家混合模型VAMoE，通过变量自适应门控机制动态组合专家，在ERA5数据集上以约25%参数和50%训练数据实现与SoTA模型相当的短期和长期天气预报精度。
摘要：
本文提出了变量自适应专家混合模型（VAMoE），这是一种用于增量天气预报的新型框架，能够动态适应实时数据中不断演变的时空模式。传统天气预报模型往往面临高昂的计算开销，并且需要在新观测数据到达时持续更新预报。VAMoE通过利用混合专家架构来应对这些挑战，其中每个专家专门负责捕捉大气变量（温度、湿度、风速）的不同子模式。此外，所提出的方法采用变量自适应门控机制，根据输入上下文动态选择并组合相关专家，从而实现高效的知识蒸馏和参数共享。该设计显著降低了计算开销，同时保持了较高的预报精度。在真实世界ERA5数据集上的实验表明，VAMoE在短期（1天）和长期（5天）预报任务中均取得了与最先进（SoTA）模型相当的性能，而可训练参数仅约为后者的25%，初始训练数据仅需约50%。
英文摘要：
This paper presents Variables Adaptive Mixture of Experts (VAMoE), a novel framework for incremental weather forecasting that dynamically adapts to evolving spatiotemporal patterns in real time data. Traditional weather prediction models often struggle with exorbitant computational expenditure and the need to continuously update forecasts as new observations arrive. VAMoE addresses these challenges by leveraging a hybrid architecture of experts, where each expert specializes in capturing distinct subpatterns of atmospheric variables (temperature, humidity, wind speed). Moreover, the proposed method employs a variable adaptive gating mechanism to dynamically select and combine relevant experts based on the input context, enabling efficient knowledge distillation and parameter sharing. This design significantly reduces computational overhead while maintaining high forecast accuracy. Experiments on real world ERA5 dataset demonstrate that VAMoE performs comparable against SoTA models in both short term (1 days) and long term (5 days) forecasting tasks, with only about 25% of trainable parameters and 50% of the initial training data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
