A Causality-Aware Spatiotemporal Model for Multi-Region and Multi-Pollutant Air Quality Forecasting

2025-09-25

AI Summary

Accurate long-term, multi-pollutant air quality forecasting across geographically distributed regions faces challenges including complex spatiotemporal dependencies, dynamically evolving meteorology–pollution causal mechanisms, and pronounced spatial heterogeneity. Method: This paper proposes a unified deep learning architecture that jointly models cross-site spatial correlations, temporal autocorrelations, and the dynamic causal effects of meteorological variables on multiple pollutants—integrating deep spatiotemporal representation learning with explicit causal inference. Contribution/Results: The model enables fine-grained, interpretable, and collaborative long-term forecasting. Evaluated on multi-scale real-world datasets, it significantly outperforms state-of-the-art methods in prediction accuracy, exhibits strong generalization capability, and maintains stability in long-horizon forecasts. Moreover, it reliably identifies high-risk pollution periods, delivering causally grounded, actionable insights for environmental policy-making and carbon emission reduction strategies.

Technology Category

• Machine Learning: Causal Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Causality

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Air pollution, a pressing global problem, threatens public health, environmental sustainability, and climate stability. Achieving accurate and scalable forecasting across spatially distributed monitoring stations is challenging due to intricate multi-pollutant interactions, evolving meteorological conditions, and region specific spatial heterogeneity. To address this challenge, we propose AirPCM, a novel deep spatiotemporal forecasting model that integrates multi-region, multi-pollutant dynamics with explicit meteorology-pollutant causality modeling. Unlike existing methods limited to single pollutants or localized regions, AirPCM employs a unified architecture to jointly capture cross-station spatial correlations, temporal auto-correlations, and meteorology-pollutant dynamic causality. This empowers fine-grained, interpretable multi-pollutant forecasting across varying geographic and temporal scales, including sudden pollution episodes. Extensive evaluations on multi-scale real-world datasets demonstrate that AirPCM consistently surpasses state-of-the-art baselines in both predictive accuracy and generalization capability. Moreover, the long-term forecasting capability of AirPCM provides actionable insights into future air quality trends and potential high-risk windows, offering timely support for evidence-based environmental governance and carbon mitigation planning.

Problem

• Forecasting multi-pollutant air quality across distributed monitoring stations
• Modeling complex pollutant interactions with meteorological causality effects
• Addressing spatial heterogeneity and temporal dynamics in air pollution

Innovation

• Multi-region multi-pollutant unified deep architecture
• Explicit meteorology-pollutant causality modeling
• Captures spatial correlations and temporal auto-correlations