Explainable spatiotemporal Graph Neural Networks: Multi-City PM2.5 forecasting in Bangladesh with geographic graph topology validation

Abstract

Accurate forecasting of fine particulate matter (PM 2.5 ) is critical for mitigating severe health risks in South Asia, yet it remains challenging in data-scarce regions like Bangladesh. While spatiotemporal graph neural networks (GNNs) offer a promising solution by capturing atmospheric transport, their effectiveness and the physical validity of their assumed spatial graphs have rarely been rigorously tested in such constrained settings. This study addresses this gap by evaluating a graph diffusion gated recurrent unit (GD-GRU) model using four years of daily, multi-source environmental data across a 12-city network. For forecasts up to three days ahead, the GD-GRU achieves an overall mean absolute error of 8.853 µg/m 3 and an R 2 of 0.666, significantly outperforming non-graph baselines under FDR-corrected Diebold–Mariano testing (p < 0.001). Furthermore, the model significantly outperforms DCRNN when pooled across all forecast horizons (p < 0.001), while remaining closely matched at individual lead times. Crucially, empirical validation of the model’s underlying spatial assumptions demonstrates that occlusion-based spatial influence closely tracks the fixed geographic adjacency (r = 0.928, p < 0.001), and this simple distance-based graph outperforms unconstrained adaptive, wind-informed, and hybrid alternatives. Finally, a multi-method explainability framework shows strong rank convergence (Spearman ρ = 0.590 to 0.783), identifying the Green Leaf Index, wind speed, atmospheric pressure, and seasonal encoding as the dominant predictors of PM 2.5 . These findings confirm that carefully validated, interpretable static graph models can deliver robust air quality forecasts without requiring dense sensor networks, offering a practical template for environmental monitoring in data-limited regions.