A knowledge discovery framework to predict the N2O emissions in the wastewater sector. (1st July 2020)

• Record Type: Journal Article
• Authors: Vasilaki, V.; Conca, V.; Frison, N.; Eusebi, A.L.; Fatone, F.; Katsou, E.
• Is Part Of: Water research. Volume 178(2020)
• Publication Date: 2020-07-01
• Subjects: Short-cut enhanced nutrients abatement - SCENA -- Long-term dissolved N2O and Energy consumption monitoring, knowledge discovery and data mining; Water -- Pollution -- Research -- Periodicals; 363.7394
• DOI: 10.1016/j.watres.2020.115799
• Languages: English
• ISSNs: 0043-1354

Abstract

Abstract: Data Analytics is being deployed to predict the dissolved nitrous oxide (N2 O) concentration in a full-scale sidestream sequence batch reactor (SBR) treating the anaerobic supernatant. On average, the N2 O emissions are equal to 7.6% of the NH4 –N load and can contribute up to 97% to the operational carbon footprint of the studied nitritation-denitritation and via-nitrite enhanced biological phosphorus removal process (SCENA). The analysis showed that average aerobic dissolved N2 O concentration could significantly vary under similar influent loads, dissolved oxygen (DO), pH and removal efficiencies. A combination of density-based clustering, support vector machine (SVM), and support vector regression (SVR) models were deployed to estimate the dissolved N2 O concentration and behaviour in the different phases of the SBR system. The results of the study reveal that the aerobic dissolved N2 O concentration is correlated with the drop of average aerobic conductivity rate (spearman correlation coefficient equal to 0.7), the DO (spearman correlation coefficient equal to −0.7) and the changes of conductivity between sequential cycles. Additionally, operational conditions resulting in low aerobic N2 O accumulation (<0.6 mg/L) were identified; step-feeding, control of initial NH4 + concentrations and aeration duration can mitigate the N2 O peaks observed in the system. The N2 O emissions during aeration shows correlation with the stripping of accumulated N2 O from the previous anoxic cycle. The analysis shows that N2 O is always consumed after the depletion of NO2 − during denitritation (after the "nitrite knee"). Based on these findings SVM classifiers were constructed to predict whether dissolved N2 O will be consumed during the anoxic and anaerobic phases and SVR models were trained to predict the N2 O concentration at the end of the anaerobic phase and the average dissolved N2 O concentration during aeration. The proposed approach accurately predicts the N2 O emissions as a latent parameter from other low-cost sensors that are traditionally deployed in biological batch processes. Graphical abstract: Image 1 Highlights: S.C.E.N.A N2 O emissions contribute up to 97.3% to the operational carbon footprint. Stripping of accumulated N2 O from the previous anoxic cycle increases emissions. Aerobic dissolved N2 O concentration is correlated with DO and conductivity. Conductivity can be used to control SBR NH4 + concentration and N2 O. N2 O can be estimated as a latent parameter from other low-cost sensors.