Machine Learning Predicts Biochar Aging Effects on Nitrous Oxide Emissions from Agricultural Soils

Abstract

Biochar effects on agricultural soils change over time as biochar ages. To better understand the long-term impacts of biochar application on climate change mitigation, the effect of biochar aging on nitrous oxide (N₂O) emissions has been widely investigated in field experiments. However, the underlying relationship of N₂O emissions with biochar properties, fertilization practices, soil properties, and weather conditions is poorly understood. We collected data from 30 peer-reviewed publications with 279 observations and used machine learning (ML) to model and explore critical factors affecting daily N₂O fluxes. We established and compared models constructed using neural networks (NN), support vector regression (SVR), random forest (RF), and extreme gradient boosting (XGB). We found that the gradient boosting regression (GBR) model was the optimal algorithm for predicting daily N₂O fluxes (R² > 0.90). The importance of factors driving daily N₂O fluxes is as follows: fertilization practices (44%) > weather conditions (30%) > soil properties (21%) > biochar properties (5%). In addition, the aging time of biochar, potassium application rate, soil clay fraction, and mean air temperature were critical factors affecting the daily N₂O fluxes. When biochar is initially applied, it can reduce N₂O emissions; however, it has no long-term effects in reducing N₂O emissions. The accurate prediction and insights from the ML model benefit the assessment of the long-term effects of biochar aging on N₂O emissions from agricultural soils.