Machine learning improves predictions of agricultural nitrous oxide (N<sub>2</sub>O) emissions from intensively managed cropping systems
Debasish Saha, Bruno Basso, G. Philip Robertson
Abstract
The potent greenhouse gas nitrous oxide (N _2 O) 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 N _2 O fluxes for intensively managed cropping systems are confounded by highly variable fluxes and limited geographic coverage; 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 soil parameters. We used sub-daily N _2 O flux data from six years of automated flux chambers installed in a continuous corn rotation at a site in the upper US 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 nitrogen (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 two to three times improvement over conventional process-based models and with substantially fewer input requirements. This coupled approach offers promise for better predictions of agricultural N _2 O emissions and thus more precise global models and more effective agricultural mitigation interventions.