Machine learning improves predictions of agricultural nitrous oxide emissions from intensively managed cropping systems

The potent greenhouse gas nitrous oxide (N₂O) is accumulating in the atmosphere at unprecedented rates largely due to agricultural intensification, and cultivated soils contribute ~60% of the agricultural flux. Empirical models of N₂O fluxes for intensively managed cropping systems are confounded by highly variable fluxes and limited data; process-based biogeochemical models are rarely able to predict daily to monthly emissions with > 20% accuracy even with site-specific calibration. Here we show the promise for machine learning (ML) to significantly improve field-level flux predictions, especially when coupled with a cropping systems model to simulate unmeasured parameters. We used sub-daily N₂O flux data from six years of automated flux chambers installed in a continuous corn rotation at a site in the upper U.S. Midwest (~3000 sub-daily flux observations), supplemented with weekly to biweekly manual chamber measurements (~1100 daily fluxes), to train an ML model that explained 65-89% of daily flux variance with very few input variables –soil moisture, days after fertilization, soil texture, air temperature, soil carbon, precipitation, and N fertilizer rate. When applied to a long-term test site not used to train the model, the model explained 38% of the variation observed in weekly to biweekly manual chamber measurements from corn, and 51% upon coupling the ML model with a cropping systems model that predicted daily soil N availability. This represents a 2-3 times improvement over conventional process-based models and with substantially fewer input requirements. This coupled approach offers substantial promise for better predictions of agricultural N₂O emissions and thus more precise global models and more effective mitigation management interventions.