A hybrid model driven by remotely-sensed data for simulating the impact of high spatiotemporal variations in fertilization and atmospheric N2O on N2O emissions in paddy fields

• Machine learning algorithms predicted dissolved N 2 O concentration in paddy fields. • Fertilization date and amount were derived from remote sensing at high resolution. • Water-air gas exchange model considers the dynamic atmospheric N 2 O concentration. • Coupling the effect of fertilization and atmospheric N 2 O dynamics on N 2 O emissions. • A novel hybrid model predicts daily field-scale N 2 O emissions in paddy fields. Paddy fields with excessive fertilizer application are potential N 2 O emission hotspots, which profoundly affect the greenhouse effect. Unlike prior regional models assuming uniform fertilization and static atmospheric N 2 O concentration, this study focuses on simulating the effects of fertilization heterogeneity and dynamic atmospheric N 2 O concentration on daily field-scale N 2 O emissions. Accordingly, this study presents a hybrid model (NAU-RS P -N 2 O) that combines multi-source remotely-sensed data, ML algorithms, and the water-air gas exchange model to predict daily field-scale N 2 O emissions in paddies. Firstly, we built Bayesian-optimized ML models using critical water quality parameters to predict dissolved N 2 O and incorporated SHAP analysis for interpretability. Secondly, the remotely-sensed data (fertilization information, LST) were used to drive models of water quality parameters, capturing their complex spatiotemporal changes. Finally, the water-air interface gas model considering the dynamic atmospheric N 2 O concentration simulated daily field-scale N 2 O emissions in paddy fields. The model demonstrated an average R 2 of 0.72, with MAE of 1.56 mg·m -2 ·d -1 and RMSE of 1.65 mg·m -2 ·d -1 . The NAU-RS P -N 2 O model effectively simulated daily field-scale N 2 O emissions and spatiotemporal patterns, highlighting the critical role of nitrogen management and atmospheric N 2 O levels in controlling emissions. Our findings present a novel approach for the large-scale prediction of N 2 O emissions from paddy fields, applicable across diverse rice-growing regions in China.