Soil Nitrous Oxide Hot Moments: Identification, Characterization, and Prediction Across Agroecosystems

Nitrous oxide (N₂O) emissions from agricultural soils contribute ~4% of total anthropogenic greenhouse gases (GHG) emissions globally. Events known as ‘hot moments’ can occur following environmental changes that favor N₂O production, which contribute disproportionately to annual cumulative emissions. Despite their significance, hot moments have not been statistically well defined, particularly on a global scale. I collected 13,787 soil N₂O flux measurements from 42 publications and evaluated 14 methods of statistical anomaly detection for their ability to identify hot moments within datasets. Two methods achieved highest overall performance by Matthews correlation coefficient (MCC): median absolute deviation (MCC: 0.80) and minimum covariance determinant (MCC: 0.80), the latter which also performed evenly across highly dissimilar datasets and identified more difficult-to-detect contextual hot moments than other top overall performers (39%). I next evaluated a variety of machine learning classification models for their performance in predicting daily hot moments from a limited set of management, environmental, and climate data. The XGBoost model trained using data labels of N₂O flux measurements generated through a context-informed hand labeling process produced the best overall performance (Matthews Correlation Coefficient, MCC: 0.69; Accuracy: 90%), with fewer errors made when flux was < 10 g N ha^-1 d^-1 or >50 g N ha^-1 d^-1. Finally, I investigated the impact of extreme weather events on N₂O emissions across soils ranging widely in climatological histories and textures collected from the Levant region. Soil cores were subjected to varying periods of very high moisture (90% water filled pore space) ranging from a transient flooding to seven days in an incubation experiment. I found that while cumulative emissions were primarily driven by carbon availability, longer periods of flooding significantly increased cumulative N₂O emissions (p< 0.0001) both in soils which experienced impeded gas diffusion by high moisture and those that did not. These findings suggest the possibility of a positive feedback loop as climate change increases the frequency of extreme weather events and flooding, which in turn contribute to greater N₂O emissions.