建模气象与污染的动态关系，提升空气质量预测精度
Air Quality Prediction with A Meteorology-Guided Modality-Decoupled Spatio-Temporal Network
- 将空气质量和气象数据作为独立模态分别建模，融合多层气象数据
- 在国家级数据集上使48小时预测误差降低17.54%
- 适合关注环境建模与多源数据融合的研究者
空气质量预测对公共健康和环境保护至关重要。准确预测需处理时间模式、污染物关联、站点空间依赖及气象因素对污染物扩散与化学反应的影响。现有方法低估气象作用，忽视多层气象数据利用，难以建模二者动态关系。为此，提出MDSTNet，一种编码器-解码器框架，将空气质量与气象条件作为独立模态，融合多压力层气象数据与天气预报，捕捉大气-污染依赖关系。同时构建中国首个全国性数据集ChinaAirNet，整合空气质量记录与多压力层气象观测。在ChinaAirNet上的实验表明，MDSTNet相比当前最优模型，48小时预测误差降低17.54%。代码与数据集将开源。
原文摘要 · Abstract (English)
Air quality prediction plays a crucial role in public health and environmental protection. Accurate air quality prediction is a complex multivariate spatiotemporal problem, that involves interactions across temporal patterns, pollutant correlations, spatial station dependencies, and particularly meteorological influences that govern pollutant dispersion and chemical transformations. Existing works underestimate the critical role of atmospheric conditions in air quality prediction and neglect comprehensive meteorological data utilization, thereby impairing the modeling of dynamic interdependencies between air quality and meteorological data. To overcome this, we propose MDSTNet, an encoder-decoder framework that explicitly models air quality observations and atmospheric conditions as distinct modalities, integrating multi-pressure-level meteorological data and weather forecasts to capture atmosphere-pollution dependencies for prediction. Meantime, we construct ChinaAirNet, the first nationwide dataset combining air quality records with multi-pressure-level meteorological observations. Experimental results on ChinaAirNet demonstrate MDSTNet's superiority, substantially reducing 48-hour prediction errors by 17.54\% compared to the state-of-the-art model. The source code and dataset will be available on github.
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。