Tree-structured parzen estimator optimized-automated machine learning assisted by meta-analysis for predicting biochar-driven N2O mitigation effect in constructed wetlands

Abstract

Biochar is a carbon-neutral tool for combating climate change. Artificial intelligence applications to estimate the biochar mitigation effect on greenhouse gases (GHGs) can assist scientists in making more informed solutions. However, there is also evidence indicating that biochar promotes, rather than reduces, N₂O emissions. Thus, the effect of biochar on N₂O remains uncertain in constructed wetlands (CWs), and there is not a characterization metric for this effect, which increases the difficulty and inaccuracy of biochar-driven alleviation effect projections. Here, we provide new insight by utilizing machine learning-based, tree-structured Parzen Estimator (TPE) optimization assisted by a meta-analysis to estimate the potency of biochar-driven N₂O mitigation. We first synthesized datasets that contained 80 studies on global biochar-amended CWs. The mitigation effect size was then calculated and further introduced as a new metric. TPE optimization was then applied to automatically tune the hyperparameters of the built extreme gradient boosting (XGBoost) and random forest (RF), and the optimum TPE-XGBoost obtained adequately achieved a satisfactory prediction accuracy for N₂O flux (R² = 91.90%, RPD = 3.57) and the effect size (R² = 92.61%, RPD = 3.59). Results indicated that a high influent chemical oxygen demand/total nitrogen (COD/TN) ratio and the COD removal efficiency interpreted by the Shapley value significantly enhanced the effect size contribution. COD/TN ratio made the most and the second greatest positive contributions among 22 input variables to N₂O flux and to the effect size that were up to 18% and 14%, respectively. By combining with a structural equation model analysis, NH₄⁺-N removal rate had significant negative direct effects on the N₂O flux. This study implied that the application of granulated biochar derived from C-rich feedstocks would maximize the net climate benefit of N₂O mitigation driven by biochar for future biochar-based CWs.

Keywords: Automated machine learning; Biochar; Hyperparameter tuning; Nitrous oxide; TPE optimization.