Spatially Directional Dual-Attention GAT for Spatial Fluoride Health Risk Modeling
This addresses the need for better spatial health risk modeling in environmental public health, particularly for fluoride exposure, but is incremental as it builds on existing GNN methods with specific enhancements.
The paper tackled the problem of accurately modeling fluoride-related health risks like dental fluorosis by proposing SDD-GAT, a spatial graph neural network that disentangles geographic and attribute factors; it significantly outperformed traditional and state-of-the-art models on a dataset of over 50,000 samples in Guizhou Province, China, with improved spatial autocorrelation measured by Moran's I.
Environmental exposure to fluoride is a major public health concern, particularly in regions with naturally elevated fluoride concentrations. Accurate modeling of fluoride-related health risks, such as dental fluorosis, requires spatially aware learning frameworks capable of capturing both geographic and semantic heterogeneity. In this work, we propose Spatially Directional Dual-Attention Graph Attention Network (SDD-GAT), a novel spatial graph neural network designed for fine-grained health risk prediction. SDD-GAT introduces a dual-graph architecture that disentangles geographic proximity and attribute similarity, and incorporates a directional attention mechanism that explicitly encodes spatial orientation and distance into the message passing process. To further enhance spatial coherence, we introduce a spatial smoothness regularization term that enforces consistency in predictions across neighboring locations. We evaluate SDD-GAT on a large-scale dataset covering over 50,000 fluoride monitoring samples and fluorosis records across Guizhou Province, China. Results show that SDD-GAT significantly outperforms traditional models and state-of-the-art GNNs in both regression and classification tasks, while also exhibiting improved spatial autocorrelation as measured by Moran's I. Our framework provides a generalizable foundation for spatial health risk modeling and geospatial learning under complex environmental settings.