Accurately mapping ground-level ozone concentrations at high spatiotemporal resolution (daily, 1 km) is essential for evaluating human exposure and conducting public health assessments. This requires identifying and understanding a proxy that is well-correlated with ground-level ozone variation and available with spatiotemporal high-resolution data. This study introduces a high-resolution ozone modeling method utilizing the XGBoost algorithm with satellite-derived land surface temperature (LST) as the primary predictor. Focusing on China in 2019, our model achieved a cross-validation R2 of 0.91 and a root-mean-square error (RMSE) of 13.51 μg/m3. We provide detailed maps highlighting ground-level ozone concentrations in urban areas, uncovering spatial variations previously unresolved, along with time series aligning with established understandings of ozone dynamics. Our local interpretation of the machine learning model underscores the significant contribution of LST to spatiotemporal ozone variations, surpassing other meteorological, pollutant, and geographical predictors in its influence. Validation results indicate that model performance decreases as spatial resolution becomes coarser, with R2 decreasing from 0.91 for the 1 km model to 0.85 for the 25 km model. The methodology and data sets generated by this study offer new insights into ground-level ozone variability and mapping and can significantly aid in exposure assessment and epidemiological research related to this critical environmental challenge.

The Lower Mekong Delta region (LMD) accounts for 90% of Vietnam\'s rice exports; however, the air quality in the LMD is remarkably reduced by ground-level ozone (O3) pollution. This study aimed to quantify the relative yield and economic value losses in rice-growing crop seasons affected by ground-level O3 concentrations across the LMD. The results of this study can serve as a basis for extensive assessments for the following years and support environmental managers to propose control measures of O3 precursor emissions (NOx and VOCs) from man-made sectors, as well as build protective solutions for rice farming in LMD. Two ground-level O3 exposure metrics of M7 and AOT40 reflecting ground-level O3 pollution impacts, combined with the model of exposure-relative yield relationship (or surface O3-crop models), were used to assess losses of crop production (CPL) and economic cost losses (ECL) caused by rice crop yield reductions. For the M7 metric of ground-level O3 exposure, the average value was 14.746 ppbV, with levels ranging from 13.959 ppbV to 15.502 ppbV, and the affected area was spread across 1309.39 thousand hectares. The AOT40 exposure metric reached an average value of 11.490 ppbV, with a range of 0.000-31.665 ppbV. The highest exposure level was 17.503-31.653 ppbV, covering an area of 747.01 thousand hectares. The total CPL of the three rice crops over the LMD was 9593.52 tonnes (accounting for 0.039% of the total value of rice production in the region), with a total corresponding EPL of 62.405 billion VND (equivalent to 2761.01 thousand USD). The results are considered a baseline study to serve as a basis for extensive assessments for the following years and support for the environmental managers to propose control measures of O3 precursor emissions (NOx and VOCs) from man-made sectors as well as build protective solutions in rice farming in LMD shortly.