Improving Prediction of Nutrient Recovery via Struvite Precipitation from Organic Waste Digestate DOI

Haidar Aldaach,

Mohammed Tamim Zaki, Kevin D. Orner

et al.

Environmental Engineering Science, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 15, 2024

Increased organic waste generation in the residential, industrial, and agricultural sectors results massive amounts of that are landfilled incinerated, thereby contributing to environmental pollution. Opportunities exist recover valuable resources from potentially leverage economic benefits. One common strategy for managing is anaerobic digestion (AD). The liquid effluent AD, called digestate, a concentrated source phosphorus nitrogen. These nutrients can be recovered via struvite precipitation. overall study goal was quantify effectiveness five statistical machine learning (ML) models predicting percentage digestate derived different streams Nine combinations parameters were developed effects multiple on nutrient recovery efficiency. linear regression (MLR), polynomial (PLR), K-nearest neighbors (KNN), random forest (RF), eXtreme Gradient Boosting (XGBoost). RF XGBoost had best performance efficiency among models. Both coefficient (R2) phosphate ammonium recoveries above 0.90 root mean square error 2–7.67. comparison indicated PO43− NH4+ (%) most influenced by following input variables: pH, Mg:P N:P molar ratios, mixing speed, reaction temperature, hydraulic retention time, concentrations sodium, potassium, calcium, magnesium, ammonium, phosphate. We concluded ML provide useful predictions As result, operation resource systems optimized using

Language: Английский

Enhanced nitrogen prediction and mechanistic process analysis in high-salinity wastewater treatment using interpretable machine learning approach DOI
Qing Wei,

Zuxin Xu,

Hailong Yin

et al.

Bioresource Technology, Journal Year: 2025, Volume and Issue: unknown, P. 132393 - 132393

Published: March 1, 2025

Language: Английский

Citations

0
Leveraging ionic information for machine learning-enhanced source identification in integrated wastewater treatment plant DOI

Yaorong Shu,

Fanming Kong,

Xia Li

et al.

Journal of Water Process Engineering, Journal Year: 2025, Volume and Issue: 74, P. 107784 - 107784

Published: April 23, 2025

Language: Английский

Citations

0
Machine Learning Methods for the Prediction of Wastewater Treatment Efficiency and Anomaly Classification with Lack of Historical Data DOI Creative Commons
Igor Gulshin, Olga Kuzina

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(22), P. 10689 - 10689

Published: Nov. 19, 2024

This study examines an algorithm for collecting and analyzing data from wastewater treatment facilities, aimed at addressing regression tasks predicting the quality of treated classification preventing emergency situations, specifically filamentous bulking activated sludge. The feasibility using obtained under laboratory conditions simulating technological process as a training dataset is explored. A small collected actual plants considered test dataset. For both tasks, best results were achieved gradient-boosting models CatBoost family, yielding metrics SMAPE = 9.1 ROC-AUC 1.0. set most important predictors modeling was selected each target features.

Language: Английский

Citations

3
Industrial activated sludge model identification using hyperparameter-tuned metaheuristics DOI
Akhil T. Nair,

M. Arivazhagan

Swarm and Evolutionary Computation, Journal Year: 2024, Volume and Issue: 91, P. 101733 - 101733

Published: Sept. 20, 2024

Language: Английский

Citations

0
Improving Prediction of Nutrient Recovery via Struvite Precipitation from Organic Waste Digestate DOI

Haidar Aldaach,

Mohammed Tamim Zaki, Kevin D. Orner

et al.

Environmental Engineering Science, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 15, 2024

Increased organic waste generation in the residential, industrial, and agricultural sectors results massive amounts of that are landfilled incinerated, thereby contributing to environmental pollution. Opportunities exist recover valuable resources from potentially leverage economic benefits. One common strategy for managing is anaerobic digestion (AD). The liquid effluent AD, called digestate, a concentrated source phosphorus nitrogen. These nutrients can be recovered via struvite precipitation. overall study goal was quantify effectiveness five statistical machine learning (ML) models predicting percentage digestate derived different streams Nine combinations parameters were developed effects multiple on nutrient recovery efficiency. linear regression (MLR), polynomial (PLR), K-nearest neighbors (KNN), random forest (RF), eXtreme Gradient Boosting (XGBoost). RF XGBoost had best performance efficiency among models. Both coefficient (R2) phosphate ammonium recoveries above 0.90 root mean square error 2–7.67. comparison indicated PO43− NH4+ (%) most influenced by following input variables: pH, Mg:P N:P molar ratios, mixing speed, reaction temperature, hydraulic retention time, concentrations sodium, potassium, calcium, magnesium, ammonium, phosphate. We concluded ML provide useful predictions As result, operation resource systems optimized using

Language: Английский

Citations

0