Enhancing the Interpretability of Spatially Variable N2O Model Predictions with Soft Sensors during Wastewater Treatment

Abstract

Model-based solutions for nitrous oxide (N2O) emissions from wastewater treatment plants (WWTPs) are informed by operational data sets designed to control nutrient levels in liquid waste, coupled with dedicated campaigns for N2O measurements. We analyzed how machine learning (ML) models predict disturbances to WWT operation and spatially variable N2O emissions. A real data set was investigated to validate the modeling framework from N2O emissions predicted by four ML models (R2 = 0.79–0.89). Monitoring campaigns for N2O were simulated with a plant-wide mechanistic model to include additional sensors, site-level N2O data sets, and wastewater disturbances (n = 16). ML models were highly accurate (0.97 ± 0.02, n = 80), but the feature importance depended on the model, the scenario, and the N2O measurement scale (reactor vs. WWTP). We argue that N2O soft sensor model predictions are limited to the measuring location and the methodological uncertainty of the data set, which affect the interpretability of the model. Lastly, the analysis of the mechanistic model structure exposed interactions between autotrophic and heterotrophic pathways over nitric oxide which can overestimate aerobic nitrite production and bias the N2O pathway contributions.