Opportunistic Air Quality Monitoring and Forecasting with Expandable Graph Neural Networks
This work addresses the need for flexible and personalized air quality monitoring solutions for smaller institutes or companies with limited budgets, representing an incremental improvement in adapting existing models to evolving spatial scenarios.
The paper tackles the problem of air quality forecasting in areas lacking fixed monitoring infrastructure by proposing an expandable graph attention network (EGAT) model that integrates data from both existing and new sensors with varying spatial structures, validated on real data from PurpleAir.
Air Quality Monitoring and Forecasting has been a popular research topic in recent years. Recently, data-driven approaches for air quality forecasting have garnered significant attention, owing to the availability of well-established data collection facilities in urban areas. Fixed infrastructures, typically deployed by national institutes or tech giants, often fall short in meeting the requirements of diverse personalized scenarios, e.g., forecasting in areas without any existing infrastructure. Consequently, smaller institutes or companies with limited budgets are compelled to seek tailored solutions by introducing more flexible infrastructures for data collection. In this paper, we propose an expandable graph attention network (EGAT) model, which digests data collected from existing and newly-added infrastructures, with different spatial structures. Additionally, our proposal can be embedded into any air quality forecasting models, to apply to the scenarios with evolving spatial structures. The proposal is validated over real air quality data from PurpleAir.