A novel near real-time approach to forecast high resolution NO concentrations in southeastern China by incorporating multi-source satellite data.

Nitrogen dioxide, designated as NO, is a critical yet harmful trace gas in Earth's atmospheric composition. NO poses significant threats to human health, ecosystems, and agricultural productivity. Accurate NO forecasts at high spatial resolution enable authorities to safeguard public health through targeted mitigation efforts. Conventional NO forecasting approaches, such as time series analysis and chemical transport models (CTMs), often suffer from significant uncertainty or lack fine spatial details. This study presents a novel NO forecast model that combines Random Forest techniques with multi-source satellite data and NASA's Goddard Earth Observing System "Composing Forecasting" (GEOS-CF) product to provide spatially continuous, five-day forecasts of NO concentrations at 1 km resolution across southeastern China. The superior capabilities of our forecast framework were confirmed through multiple validation methods, consistently surpassing the performance of the original GEOS-CF model. Notably, the new framework achieved substantial error reductions and resolution enhancements in GEOS-CF forecasts, outperforming the initial product across all validation metrics. The developed model facilitates the generation of NO forecasts characterized by near-real-time delivery, great precision, and high spatial resolution.