Spatial Resolved Surface Ozone with Urban and Rural Differentiation during 1990-2019: A Space-Time Bayesian Neural Network Downscaler

Long-term exposure to ambient ozone (O3) canlead to a series of chronic diseases and associated prematuredeaths, and thus population-level environmental health studieshanker after the high-resolution surface O3concentration database.In response to this demand, we innovatively construct a space-time Bayesian neural network parametric regressor to fuse TOARhistorical observations, CMIP6 multimodel simulation ensemble,population distributions, land cover properties, and emissioninventories altogether and downscale to 10 kmx10 km spatialresolution with high methodological reliability (R2= 0.89-0.97,RMSE = 1.97-3.42 ppbV), fair prediction accuracy (R2= 0.69-0.77, RMSE = 5.63-7.97 ppbV), and commendable spatiotempo-ral extrapolation capabilities (R2= 0.62-0.76, RMSE = 5.38-11.7 ppbV). Based on our predictions in 8-h maximum daily averagemetric, the rural-site surface O3are 15.1 +/- 7.4 ppbV higher than urban globally averaged across 30 historical years during 1990-2019,with developing countries being of the most evident differences. The globe-wide urban surface O3are climbing by 1.9 +/- 2.3 ppbV perdecade, except for the decreasing trends in eastern United States. On the other hand, the global rural surface O3tend to be relativelystable, except for the rising tendencies in China and India. Using CMIP6 model simulations directly without urban-ruraldifferentiation will lead to underestimations of population O3exposure by 2.0 +/- 0.8 ppbV averaged over each historical year. Ouroriginal Bayesian neural network framework contributes to the deep-learning-driven environmental studies methodologically byproviding a brand-new feasible way to realize data fusion and downscaling, which maintains high interpretability by conforming tothe principles of spatial statistics without compromising the prediction accuracy. Moreover, the 30-year highly spatial resolvedmonthly surface O3database with multiple metricsfills in the literature gap for long-term surface O3exposure tracing.