Forecasting O and NO concentrations with spatiotemporally continuous coverage in southeastern China using a Machine learning approach.

Ozone (O) is a significant contributor to air pollution and the main constituent ofphotochemical smog that plagues China. Nitrogen dioxide (NO) is a significant air pollutant and a critical trace gas in the Earth's atmosphere. The presence of O and NO has detrimental effects on human health, the ecosystem, and agricultural production. Forecasting accurate ambient O and NO concentrations with full spatiotemporal coverage is pivotal for decision-makers to develop effective mitigation strategies and prevent harmful public exposure. Existing methods, including chemical transport models (CTMs) and time series at air monitoring sites, forecast O and NO concentrations either with nontrivial uncertainty or without spatiotemporally continuous coverage. In this research, we adopted a forecasting model that integrates the random forest algorithm with NASA's Goddard Earth Observing System "Composing Forecasting" (GEOS-CF) product. This approach offers spatiotemporally continuous forecasts of O and NO concentrations across southeastern China for up to five days in advance. Both overall validation and spatial cross-validation revealed that our forecast framework significantly surpassed the initial GEOS-CF model for all validation metrics, substantially reducing the errors in the GEOS-CF forecast data. Our model could provide accurate near-real-time O and NO forecasts with continuous spatiotemporal coverage.