New approach for predicting nitrification and its fraction of N2O emissions in global terrestrial ecosystems

Abstract

Nitrification is a major pathway of N₂O production in aerobic soils. Measurements and model simulations of nitrification and associated N₂O emission are challenging. Here we innovatively integrated data mining and machine learning to predict nitrification rate (\({R_{{\text{nit}}}}\)) and the fraction of nitrification as N₂O emissions (\({f_{{{\text{N}}_{\text{2}}}{{\text{O}}_{{\text{Nit}}}}}}\)). Using our global database on \({R_{{\text{nit}}}}\) and \({f_{{{\text{N}}_{\text{2}}}{{\text{O}}_{{\text{Nit}}}}}}\), we found that the machine-learning based stochastic gradient boosting (SGB) model outperformed three widely used process-based models in estimating \({R_{{\text{nit}}}}\) and N₂O emission from nitrification. We then applied the SGB technique for global prediction. The potential \({R_{{\text{nit}}}}\) was driven by long-term mean annual temperature, soil C/N ratio and soil pH, whereas \({f_{{{\text{N}}_{\text{2}}}{{\text{O}}_{{\text{Nit}}}}}}\) by mean annual precipitation, soil clay content, soil pH, soil total N. The global \({f_{{{\text{N}}_{\text{2}}}{{\text{O}}_{{\text{Nit}}}}}}\) varied by over 200 times (0.006%–1.2%), which challenges the common practice of using a constant value in process-based models. This study provides insights into advancing process-based models for projecting N dynamics and greenhouse gas emissions using a machine learning approach.