Elucidating nitrogen removal performance and response mechanisms of anammox under heavy metal stress using big data analysis and machine learning.

[Display omitted] • Cr6+ caused a greater reduction in NRR than other five heavy metals. • The inhibitory effect of heavy metals was verified by Spearman and RDA analysis. • Compared with SVR model, XGBoost model has the best performance with R2 of 0.999. • The effects of multiple heavy metal coexistence on NRR were analyzed by SHAP method. In this study, machine learning algorithms and big data analysis were used to decipher the nitrogen removal rate (NRR) and response mechanisms of anammox process under heavy metal stresses. Spearman algorithm and Statistical analysis revealed that Cr6+ had the strongest inhibitory effect on NRR compared to other heavy metals. The established machine learning model (extreme gradient boost) accurately predicted NRR with an accuracy>99%, and the prediction error for new data points was mostly less than 20%. Additionally, the findings of feature analysis demonstrated that Cu2+ and Fe3+ had the strongest effect on the anammox process, respectively. According to the new insights from this study, Cr6+ and Cu2+ should be removed preferentially in anammox processes under heavy metal stress. This study revealed the feasible application of machine learning and big data analysis for NRR prediction of anammox process under heavy metal stress. [ABSTRACT FROM AUTHOR]