Machine learning for modeling N2O emissions from wastewater treatment plants: Aligning model performance, complexity, and interpretability

•A novel definition of the best machine model for N2O soft sensors was established.•Multivariate outlier detection considered special characteristics of wastewater.•Feature reduction balanced data acquisition, computation time, and model accuracy.•Boosted decision trees showed better overall performance than deep neural network.•Interpretable ML is a step towards guided decisions for N2O emissions mitigation.