PMID- 35921006
OWN - NLM
STAT- MEDLINE
DCOM- 20230106
LR  - 20230111
IS  - 1614-7499 (Electronic)
IS  - 0944-1344 (Linking)
VI  - 30
IP  - 1
DP  - 2023 Jan
TI  - A new hybrid ensemble approach for the prediction of effluent total nitrogen from 
      a full-scale wastewater treatment plant using a combined trickling 
      filter-activated sludge system.
PG  - 1622-1639
LID - 10.1007/s11356-022-21864-w [doi]
AB  - In this study, different K-nearest neighbors (KNN), support vector regression 
      (SVR), decision tree (DT), and random forest (RF) algorithms integrated with the 
      Bayesian optimization algorithm (BOP) have been applied as novel hybrid 
      modeling/optimization tools to predict the total nitrogen in treated wastewater 
      of Southern Tehran Wastewater Treatment Plant (STWWTP). In order to enhance the 
      outcomes of hybrid models, the chosen sub-models (the best and least correlated 
      hybrid models) were used to generate voting average and stacked regression 
      ensemble models. Throughout the preprocessing step, two alternative scenarios 
      were used to handle missing values from the samples, including elimination versus 
      estimation via linear interpolation. The results of this research demonstrated 
      that ensemble models were better than individual hybrid models, although not all 
      ensemble models were superior to single models. The results also revealed that 
      the stacking regression ensemble model using KNN-BOP and SVR-BOP as sub-models 
      was the most superior model among the developed models, with the coefficient of 
      determination (R(2)) = 0.640, root mean squared error (RMSE) = 2.378, and mean 
      absolute error (MAE) = 1.838 on the test data. The best hybrid ensemble model 
      that can accurately predict the concentration of total nitrogen (TN) in the 
      effluent can give people a heads-up about water pollution caused by 
      eutrophication before it gets bad.
CI  - (c) 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, 
      part of Springer Nature.
FAU - Sadri Moghaddam, Shabnam
AU  - Sadri Moghaddam S
AUID- ORCID: 0000-0003-1943-1604
AD  - Faculty of Civil Engineering, K. N. Toosi University of Technology, Tehran, Iran. 
      sadrimoghaddam@kntu.ac.ir.
FAU - Mesghali, Hassan
AU  - Mesghali H
AD  - Faculty of Civil Engineering, K. N. Toosi University of Technology, Tehran, Iran.
LA  - eng
PT  - Journal Article
DEP - 20220803
PL  - Germany
TA  - Environ Sci Pollut Res Int
JT  - Environmental science and pollution research international
JID - 9441769
RN  - 0 (Sewage)
RN  - N762921K75 (Nitrogen)
SB  - IM
MH  - Humans
MH  - *Sewage
MH  - Nitrogen
MH  - Bayes Theorem
MH  - Iran
MH  - *Water Purification/methods
OTO - NOTNLM
OT  - Ensemble method
OT  - Full-scale domestic wastewater treatment plant
OT  - Hybrid model
OT  - Machine learning
OT  - Total nitrogen removal
OT  - Trickling filter-activated sludge combined system
EDAT- 2022/08/04 06:00
MHDA- 2023/01/07 06:00
CRDT- 2022/08/03 11:21
PHST- 2022/04/13 00:00 [received]
PHST- 2022/07/01 00:00 [accepted]
PHST- 2022/08/04 06:00 [pubmed]
PHST- 2023/01/07 06:00 [medline]
PHST- 2022/08/03 11:21 [entrez]
AID - 10.1007/s11356-022-21864-w [pii]
AID - 10.1007/s11356-022-21864-w [doi]
PST - ppublish
SO  - Environ Sci Pollut Res Int. 2023 Jan;30(1):1622-1639. doi: 
      10.1007/s11356-022-21864-w. Epub 2022 Aug 3.