Interpolation of missing ozone data using graph machine learning and parameter analysis through eXplainable artificial intelligence comparison

Ozone (O₃), a short-lived climate pollutant, continues to increase despite policies aimed at suppressing its precursors in South Korea. The government operates approximately 500 observatories to monitor O₃ and trace gases. Researchers use these data to address the ongoing issue of increasing O₃ levels. However, challenges in data retrieval from observatories may introduce biases in O₃ studies. In this study, we developed a graph-based machine learning model to simulate missing O₃ concentrations for mitigate bias. The model incorporates spatiotemporal distribution characteristics using a merged observation dataset from South Korea in 2021. Regardless of region or length of missing data, the model effectively simulates O₃ variations with R² of up to 0.9 and RMSE of 3.6. To determine the influence of input parameters on O₃ interpolation, we used eXplainable AI methods. The results indicated that NO₂ is the most important factor in cities, while photochemical indicators are more influential in provinces.