AirFlow：面向空气质量预测的上下文保留与多速率状态建模
AirFlow: Context Preserving and Multi-Rate State Modeling for Air Quality Forecasting
浏览论文内容
中文总结 AI 辅助
AirFlow是一种基于站点多元观测的双流空气质量预测框架，通过统计引导归一化路由和分层双流状态模型，在36项指标中获34项最优，参数与计算开销低，性能优于现有方法。
中文摘要 AI 辅助
精准的空气质量预测对公共卫生和城市环境管理至关重要，但仍面临挑战，因为污染物通道具有不同的周期性和分布漂移，其浓度轨迹同时包含多尺度依赖关系和快速变化。近期方法已改进了空间依赖学习和气象协变量建模，但污染物通道仍通过相同的归一化规则和时间骨干网络传递，使用共享的潜在表示处理不同速率下通道特定的分布和变化。为解决这一局限，我们提出AirFlow，一种污染物感知的双流框架，该框架基于站点多元观测值运行，无需额外的图传播或预定义的信号分解。具体而言，AirFlow设计了两个新模块：（1）统计引导的归一化路由机制，根据每种污染物的24小时自相关和分布漂移为其选择归一化路径；（2）分层双流状态模型，将多尺度状态空间传播与可学习响应系数相结合，其中门控双向交叉注意力交换信息并自适应融合所得表示。对多个城市真实数据的实验表明，AirFlow在36项指标对比中取得34项最优性能，与最先进基线相比，均方根误差降低幅度达11.11%；AirFlow仅需0.0483M参数和0.0215G FLOPs，以低计算开销实现了高预测精度。
英文摘要
Accurate air quality forecasting is essential for public health and urban environmental management, but remains challenging because pollutant channels differ in periodicity and distribution drift, while their concentration trajectories contain both multi-scale dependencies and rapid changes. Recent methods have improved spatial dependency learning and meteorological covariate modeling. However, pollutant channels are still passed through the same normalization rule and temporal backbone, using a shared latent representation for channel-specific distributions and changes at different rates. To address this limitation, we propose AirFlow, a pollutant-aware dual-stream framework that operates on station multivariate observations without additional graph propagation or predefined signal decomposition. Specifically, AirFlow designs two novel blocks: (1) a statistic-guided normalization routing mechanism that selects a normalization path for each pollutant according to its 24-hour autocorrelation and distribution drift; and (2) a hierarchical dual-stream state model that combines multi-scale state space propagation with learnable response coefficients, where gated bidirectional cross-attention exchanges information and adaptively fuses the resulting representations. Experiments on real-world data from multiple cities show that AirFlow achieves the best performance in 34 of 36 metrics comparisons, with reductions of up to 11.11% root mean square error over the state-of-the-art baseline. AirFlow also requires only 0.0483M parameters and 0.0215G FLOPs, achieving high forecasting accuracy with low computational overhead.
发表机构
- School of Software Technology, Zhejiang University（浙江大学软件学院）
机构由 AI 辅助整理，请以论文原文为准。
