Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting
This work solves the challenge of accurate and efficient air quality prediction for global monitoring stations, particularly in data-sparse regions, representing a domain-specific advancement.
The paper tackles the problem of global air quality forecasting by addressing spatial heterogeneity and poor generalization of transductive models to unseen regions, proposing OmniAir, a semantic topology learning framework that achieves state-of-the-art performance against 18 baselines with speeds nearly 10 times faster than existing models.
Global air quality forecasting grapples with extreme spatial heterogeneity and the poor generalization of existing transductive models to unseen regions. To tackle this, we propose OmniAir, a semantic topology learning framework tailored for global station-level prediction. By encoding invariant physical environmental attributes into generalizable station identities and dynamically constructing adaptive sparse topologies, our approach effectively captures long-range non-Euclidean correlations and physical diffusion patterns across unevenly distributed global networks. We further curate WorldAir, a massive dataset covering over 7,800 stations worldwide. Extensive experiments show that OmniAir achieves state-of-the-art performance against 18 baselines, maintaining high efficiency and scalability with speeds nearly 10 times faster than existing models, while effectively bridging the monitoring gap in data-sparse regions.