Interpretable Air Pollution Forecasting by Physics-Guided Spatiotemporal Decoupling
By: Zhiguo Zhang, Xiaoliang Ma, Daniel Schlesinger
Potential Business Impact:
Predicts air pollution accurately and explains why.
Accurate and interpretable air pollution forecasting is crucial for public health, but most models face a trade-off between performance and interpretability. This study proposes a physics-guided, interpretable-by-design spatiotemporal learning framework. The model decomposes the spatiotemporal behavior of air pollutant concentrations into two transparent, additive modules. The first is a physics-guided transport kernel with directed weights conditioned on wind and geography (advection). The second is an explainable attention mechanism that learns local responses and attributes future concentrations to specific historical lags and exogenous drivers. Evaluated on a comprehensive dataset from the Stockholm region, our model consistently outperforms state-of-the-art baselines across multiple forecasting horizons. Our model's integration of high predictive performance and spatiotemporal interpretability provides a more reliable foundation for operational air-quality management in real-world applications.
Similar Papers
Forecasting and Visualizing Air Quality from Sky Images with Vision-Language Models
Machine Learning (CS)
Shows air pollution from sky pictures.
A comparison between geostatistical and machine learning models for spatio-temporal prediction of PM2.5 data
Applications
Makes air pollution maps more accurate.
A Causality-Aware Spatiotemporal Model for Multi-Region and Multi-Pollutant Air Quality Forecasting
Machine Learning (CS)
Predicts air pollution to help us breathe cleaner.