Dataset and code for "A dataset of harmonized global air quality monitoring metadata"

This study addresses the gap in air quality monitoring metadata reporting by building a classifier for air quality station types and area characteristics. It leverages ultra-high-resolution land cover data, complemented by additional demographic and gridded information. We employ advanced machine learning methods, including convolutional neural networks and transformers. Through a custom training approach, we fine-tune pre-trained models on approximately 7000 images and label more than 8000 additional monitors, resulting in a robust model for classifying air quality stations by area characteristics (urban, rural) and source type (background, non-background). The result is the first global harmonized dataset of governmental air quality station metadata for particulate matter, with about 15000 monitors from more than 100 countries. For each air quality station, the dataset provides an identifier, geographical coordinates, the associated country, area characteristics, source type, and classification status. This dataset enables global feasibility studies and regional analyses of conditions leading to exposure. By providing a consistent classification of monitoring stations, it also allows for meaningful comparisons of sectoral exposure contributions across countries, regions, and station types, supporting comparative studies and health impact assessments.