Machine learning exhibited excellent advantages in the performance simulation and prediction of free water surface constructed wetlands

Optimizing the design and operation parameters of free water surface constructed wetlands (FWS CWs) in runoff regulation and wastewater treatment is necessary to improve the comprehensive performance. In this study, nine machine learning (ML) algorithms were successfully developed to optimize the pa...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of environmental management Ročník 309; s. 114694
Hlavní autoři: Guo, Changqiang, Cui, Yuanlai
Médium: Journal Article
Jazyk:angličtina
Vydáno: England Elsevier Ltd 01.05.2022
Témata:
Algorithm comparison
Computer Simulation
data collection
Feature importance
Interpretability
Machine Learning
prediction
runoff
Scenario prediction
surface area
Waste Disposal, Fluid - methods
Waste Water
wastewater treatment
Water
Water Purification - methods
Wetland performance
Wetlands
Feature importance
Algorithm comparison
Wetland performance
Interpretability
Scenario prediction
ISSN:0301-4797, 1095-8630, 1095-8630
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Optimizing the design and operation parameters of free water surface constructed wetlands (FWS CWs) in runoff regulation and wastewater treatment is necessary to improve the comprehensive performance. In this study, nine machine learning (ML) algorithms were successfully developed to optimize the parameter combinations for FWS CWs. The scale effect of surface area on wetland performance was determined based on consistently smaller predictions (−6.2% to −28.9%) of the nine well-established ML algorithms. The models most suitable for FWS CW performance simulation and prediction were random forest and extra trees algorithms because of their high R2 values (0.818 in both) with the training set and low mean absolute relative errors (4.7% and 3.8%, respectively) with the test set. Results from feature analysis of the six tree-based algorithms emphasized the importance of water depth and layout of inlet and outlet, and revealed the negligible effect of the aspect ratio. Feature importance and partial dependence analysis enhanced the interpretability of the tree-based algorithms. The proposed ML algorithms enabled the implementation of an extended scenario at a low cost in real time. Therefore, ML algorithms are suitable for expressing the complex and uncertain effects of the design and operation parameters on the performance of FWS CWs. Acquiring datasets consisting of more extensive, uniform, and unbiased parameter combinations is crucial for developing more robust and practical ML algorithms for the optimal design of FWS CWs. [Display omitted] •Machine learning algorithms were applied to optimize constructed wetlands.•A scale effect of surface area was observed based on consistent underestimation.•Random forest and extra trees were preferred models for predicting performance.•Machine learning was advantageous for scenario prediction and factor importance.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0301-4797
1095-8630
1095-8630
DOI:10.1016/j.jenvman.2022.114694