Geo-STO3Net: A Deep Neural Network Integrating Geographical Spatiotemporal Information for Surface Ozone Estimation

The escalating surface ozone (O3) pollution in urban areas throughout China has raised significant concerns due to its detrimental impacts on public health, local environment, and agriculture. Despite numerous efforts in surface O3 estimation, intricate geographical spatiotemporal interactions of the potential predictors have been largely overlooked. This limitation has significantly constrained the O3 estimation accuracy. To address this issue, we proposed a novel deep neural network (DNN), named Geo-STO3Net, to effectively integrate adjacent geographical spatiotemporal information from meteorological data and satellite observations into surface O3 estimation. The Geo-STO3Net model used a spatial encoder based on the residual network, a temporal encoder based on the Transformer, and a feature decoder based on the DNN to comprehensively capture the intricate geographical spatiotemporal dependencies among the predictors. Our model achieved a cross-validation (CV) R2 value of 0.95, outperforming popular models. The Geo-STO3Net model demonstrated robust spatial and temporal transferability, as evidenced by R2 values of 0.94 and 0.82 in external spatial and temporal validation on monthly scales, respectively. The Geo-STO3Net model's proficiency in handling geographical spatiotemporal information led to substantial performance improvements compared to models lacking this feature, with improved CV R2 values ranging from 0.01 to 0.18. Our findings also highlighted the severe O3 pollution over the Yangtze River Delta (YRD) region in 2022, with average surface O3 concentrations reaching 103.14μg/m3. These evidences indicate that our proposed Geo-STO3Net model can accurately estimate surface O3 concentrations and provide valuable insights into the development of effective control policies.