Improving Local Air Quality Predictions Using Transfer Learning on Satellite Data and Graph Neural Networks
This work addresses air quality monitoring for urban areas with sparse data, offering incremental improvements in prediction accuracy for health and climate applications.
The paper tackled the problem of predicting nitrogen dioxide concentrations at unmonitored urban locations by proposing a method using transfer learning with satellite data and Graph Neural Networks, achieving an 8.6% reduction in NRMSE and a 32.6% reduction in Gradient RMSE compared to a baseline.
Air pollution is a significant global health risk, contributing to millions of premature deaths annually. Nitrogen dioxide (NO2), a harmful pollutant, disproportionately affects urban areas where monitoring networks are often sparse. We propose a novel method for predicting NO2 concentrations at unmonitored locations using transfer learning with satellite and meteorological data. Leveraging the GraphSAGE framework, our approach integrates autoregression and transfer learning to enhance predictive accuracy in data-scarce regions like Bristol. Pre-trained on data from London, UK, our model achieves a 8.6% reduction in Normalised Root Mean Squared Error (NRMSE) and a 32.6% reduction in Gradient RMSE compared to a baseline model. This work demonstrates the potential of virtual sensors for cost-effective air quality monitoring, contributing to actionable insights for climate and health interventions.