Surface ozone (O₃) is well-known for posing great threats to both human health and agriculture worldwide. However, a multidecadal assessment of the impacts of O₃ on public health and agriculture in China is lacking without sufficient O₃ observations. We used a hybrid approach combining a chemical transport model and machine learning to provide a robust dataset of O₃ concentrations over the past 4 decades in China, thereby filling the gap in the long-term O₃ trend and impact assessment in China.