Abstract
Global ambient air pollution, a transboundary challenge, is typically addressed through interventions relying on data from spatially sparse and heterogeneously placed monitoring stations. These stations often encounter temporal data gaps due to issues such as power outages. In response, we have developed a scalable, data-driven, supervised machine learning framework. The models produced by the framework are designed to impute missing temporal and spatial measurements, thereby generating a comprehensive dataset for air pollutants including NO(2), O(3), PM(10), PM(2).(5) and SO(2). In this work, we produce models providing concentration estimations at 261 377 locations across the globe. The dataset, with a fine granularity of 0.25° spatial resolution at hourly time intervals and accompanied by prediction intervals for each estimate, caters to a wide range of stakeholders relying on outdoor air pollution data for downstream assessments. This enables more detailed studies. Additionally, the model's performance across various geographical locations is examined, providing insights and recommendations for strategic placement of future monitoring stations to further enhance the model's accuracy.