Beyond binary maps from HCHO∕NO 2 : a deep neural network approach to global daily mapping of net ozone production rates and sensitivities constrained by satellite observations (2005–2023)

Previous studies on net ozone production rates (PO 3 ) and their sensitivities to precursors relied on limited in-situ data, often coarse and uncertain chemical transport models (CTMs), and ozone indicators like the formaldehyde-to-nitrogen dioxide ratio (FNR). However, FNR fails to fully capture PO 3 's complex relationships with pollution, light, and water vapor. To address this, we refine the satellite-based PO 3 product from Souri et al. (2025) with key advancements: (i) a deep neural network to parametrize high-dimensional non-linear ozone chemistry without the need for empirical linearization of atmospheric conditions, (ii) incorporation of water vapor, (iii) improved error characterization, and (iv) the application of a finer CTM to dynamically convert column retrievals into near-surface mixing ratios. Our PO 3 sensitivity maps surpass traditional FNR-based assessments by quantifying sensitivity magnitudes – factoring in photolysis rates and water vapor – with greater spatial information. Our new product provides daily near-clear sky PO 3 and sensitivity maps using bias-corrected OMI (2005–2019, 0.25° × 0.25°) and TROPOMI (2018–2023, 0.1° × 0.1°), with values aligning within 10 %. High PO 3 rates (> 8 ppbv h −1 ) appear in urban and biomass-burning regions under strong photochemical activity, including during a heatwave in the northeastern U.S. Photolysis rates are the dominant factor dictating the seasonality of PO 3 magnitudes and sensitivities. The stability and long-term records of OMI retrievals (2005–2019) enable us to provide the first global maps of PO 3 linear trends showing a surge of > 30 % over China, the Middle East, and India, while a reduction in the eastern U.S., southern Europe, and several regions in Africa.