Ozone Pollution in China Affected by Climate Change in a Carbon Neutral Future as Predicted by a Process-Based Interpretable Machine Learning Method

Abstract

Ozone (O₃) pollution is a severe air quality issue in China, posing a threat to human health and ecosystems. The climate change will affect O₃ levels by directly changing physical and chemical processes of O₃ and indirectly changing natural emissions of O₃ precursors. In this study, near-surface O₃ concentrations in China in 2030 and 2060 are predicted using the process-based interpretable Extreme Gradient Boosting (XGBoost) model integrated with multi-source data. The results show that the climate-driven O₃ levels over eastern China are projected to decrease by more than 0.4 ppb in 2060 under the carbon neutral scenario (SSP1-1.9) compared with the high emission scenario (SSP5-8.5). Among this reduction, 80% is attributed to the changes in physical and chemical processes of O₃ related to a cooler climate, while the remaining 20% is attributed to the reduced biogenic isoprene emissions.