Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Vertical flow constructed wetlands using expanded clay and biochar for wastewater remediation: A comparative study and prediction of effluents using machine learning
Ist Teil von
Journal of hazardous materials, 2021-07, Vol.413, p.125426, Article 125426
Ort / Verlag
Netherlands: Elsevier B.V
Erscheinungsjahr
2021
Quelle
Alma/SFX Local Collection
Beschreibungen/Notizen
This study evaluated and compared the performance of two vertical flow constructed wetlands (VF) using expanded clay (VF1) and biochar (VF2), of which both are low-cost, eco-friendly, and exhibit potentially high adsorption as compared to conventional filter layers. Both VFs achieved relatively high removal for organic matters (i.e. Biological oxygen demand during 5 days, BOD5) and nitrogen, accounting for 9.5 – 10.5 g.BOD5.m−2.d−1 and 3.5 – 3.6 g.NH4-N.m−2.d−1, respectively. The different filter materials did not exert any significant discrepancy to effluent quality in terms of suspended solids, organic matters and NO3-N (P > 0.05), but they did influence NH4-N effluent as evidenced by the removal rate of that by VF1 and VF2 being of 82.4 ± 5.7 and 84.6 ± 6.4%, respectively (P < 0.05). The results obtained from the designed systems were further subject to machine learning to clarify the effecting factors and predict the effluents. The optimal algorithms were random forest, generalized linear model, and support vector machine. The values of the coefficient of determination (R2) and the root mean square error (RMSE) of whole fitting data achieved 74.0% and 5.0 mg.L−1, 80.0% and 0.3 mg.L−1, 90.1% and 2.9 mg.L−1, and 48.5% and 0.5 mg.L−1 for BOD5_VF1, NH4-N_VF1, BOD5_VF2, and NH4-N_VF2, respectively
[Display omitted]
•Vertical flow packed biochar exposed the promising potential for absorbing nitrogen.•Different filters do not significantly influence effluents, except for NH4-N.•Random forest, Generalized linear model, and Support vector machines selected.•Low difference between RMSE and the range of experimental effluents (BOD5 and NH4-N).