用带延迟的神经微分方程预测空气质量，更准更合理。
AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting
- 引入记忆注意力模块，动态捕捉多因素延迟效应。
- 基于物理方程建模扩散与延迟传输，提升预测准确性。
- 在三个真实数据集上优于现有方法，适合环境健康研究者。
精准的空气质量预测对公共健康和环境可持续性至关重要，但受污染物复杂动态影响仍具挑战。现有深度学习方法常将污染过程视为瞬时变化，忽略污染物传播中的固有延迟。为此，我们提出AirDDE，首个在此任务中结合延迟建模的神经微分方程框架，将延迟机制融入连续时间污染物演化过程，并具备物理指导性。具体包含两个新组件：(1) 增强记忆的注意力模块，可自适应检索全局与局部历史特征，捕捉多因素调控下的延迟效应；(2) 物理引导的延迟演化函数，基于扩散-输运方程，建模扩散、延迟输送及源/汇项，能以物理合理性捕捉延迟感知的污染累积模式。在三个真实世界数据集上的实验表明，AirDDE在平均MAE上比最优基线降低8.79%，达到当前最优性能。代码已公开于https://github.com/w2obin/airdde-aaai。
原文摘要 · Abstract (English)
Accurate air quality forecasting is essential for public health and environmental sustainability, but remains challenging due to the complex pollutant dynamics. Existing deep learning methods often model pollutant dynamics as an instantaneous process, overlooking the intrinsic delays in pollutant propagation. Thus, we propose AirDDE, the first neural delay differential equation framework in this task that integrates delay modeling into a continuous-time pollutant evolution under physical guidance. Specifically, two novel components are introduced: (1) a memory-augmented attention module that retrieves globally and locally historical features, which can adaptively capture delay effects modulated by multifactor data; and (2) a physics-guided delay evolving function, grounded in the diffusion-advection equation, that models diffusion, delayed advection, and source/sink terms, which can capture delay-aware pollutant accumulation patterns with physical plausibility. Extensive experiments on three real-world datasets demonstrate that AirDDE achieves the state-of-the-art forecasting performance with an average MAE reduction of 8.79\% over the best baselines. The code is available at https://github.com/w2obin/airdde-aaai.
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。