Deep learning based data-driven model for detecting time-delay water quality indicators of wastewater treatment plant influent

Chemical Engineering Journal, Год журнала: 2023, Номер 467, С. 143483 - 143483

Опубликована: Май 15, 2023

Язык: Английский

---

Predicting quality parameters of wastewater treatment plants using artificial intelligence techniques

Journal of Cleaner Production, Год журнала: 2023, Номер 405, С. 137019 - 137019

Опубликована: Март 31, 2023

Estimating wastewater treatment plants' (WWTPs) influent parameters such as 5-day biological oxygen demand (BOD5) and chemical (COD) is vital for optimizing electricity energy consumption. Against this backdrop, the existing body of knowledge bereft a study employing Artificial Intelligence-based techniques prediction BOD5 COD. Thus, in study, Gene expression programming (GEP), multilayer perception neural networks, multi-linear regression, k-nearest neighbors, gradient boosting, regression trees -based models were trained predicting COD, using monthly data collected from inflow 7 WWTPs over three-year period Hong Kong. Based on different statistical parameters, GEP provides more accurate estimations, with R2 values 0.784 0.861 COD respectively. Furthermore, results sensitivity analysis undertaken by monte Carlo simulation revealed that both mostly affected concentrations total suspended solids, 10% increase value TSS resulted 7.94% 7.92% It seen modeling complied fundamental chemistry quality can be further applied other sewage sources industrial leachate. The promising obtained pave way forecasting operational during sludge processing, leading to an extensive savings processes.

Язык: Английский

---

A novel deep learning ensemble model based on two-stage feature selection and intelligent optimization for water quality prediction

Environmental Research, Год журнала: 2023, Номер 224, С. 115560 - 115560

Опубликована: Фев. 25, 2023

Язык: Английский

---

Water quality prediction of copper-molybdenum mining-beneficiation wastewater based on the PSO-SVR model

Frontiers of Environmental Science & Engineering, Год журнала: 2023, Номер 17(8)

Опубликована: Март 13, 2023

Язык: Английский

---

Enhanced Insights into Effluent Prediction in Wastewater Treatment Plants: Comprehensive Deep Learning Model Explanation Based on SHAP

ACS ES&T Water, Год журнала: 2024, Номер 4(4), С. 1904 - 1915

Опубликована: Апрель 2, 2024

Models are increasingly being utilized to improve the understanding and operation of wastewater treatment plants (WWTPs) in face escalating water resource challenges. Abundant operational data provide extensive opportunities for development machine learning (ML) deep (DL) models. However, coupling time lag among features exacerbate black-box nature such models, hindering their application WWTPs. In this study, we construct a DL model using long short-term memory (LSTM) algorithm capable accurately predicting effluent quality full-scale WWTP with finely tuned hyperparameters rationally chosen input features. Comprehensive explanation based on Shapley additive explanations (SHAP) is implemented clarify contributions multivariate series (MTS) inputs predicted results terms feature dimensions. The LSTM models exhibit excellent accuracy (R2 0.96, 0.95, 0.76 MAPE 5.49, 7.17, 13.37%, respectively) chemical oxygen demand (COD), total phosphorus (TP), nitrogen (TN) better than other baseline ML SHAP quantify what most important when they exert influence how impact results. analysis from temporal dimension further explains characteristics process justifies introduction MTS. Compared correlation without engineering, selection method by significantly enhances predictive accuracy. combinations adjusted values, strong interactions significant output identified. This novel attempt both explainability MTS prediction work shows potential applying WWTPs performance.

Язык: Английский

---

Enhancing wastewater treatment through artificial intelligence: A comprehensive study on nutrient removal and effluent quality prediction

Journal of Water Process Engineering, Год журнала: 2024, Номер 61, С. 105212 - 105212

Опубликована: Апрель 11, 2024

Язык: Английский

---

Prediction of the effluent chemical oxygen demand and volatile fatty acids for anaerobic treatment based on different feature selections machine-learning methods from lab-scale to pilot-scale

Journal of Cleaner Production, Год журнала: 2024, Номер 437, С. 140679 - 140679

Опубликована: Янв. 1, 2024

Язык: Английский

---

A full-view management method based on artificial neural networks for energy and material-savings in wastewater treatment plants

Environmental Research, Год журнала: 2022, Номер 211, С. 113054 - 113054

Опубликована: Март 9, 2022

Язык: Английский

---

Prediction and Evaluation of Indirect Carbon Emission from Electrical Consumption in Multiple Full-Scale Wastewater Treatment Plants via Automated Machine Learning-Based Analysis

ACS ES&T Engineering, Год журнала: 2022, Номер 3(3), С. 360 - 372

Опубликована: Дек. 15, 2022

The indirect carbon emission from electrical consumption of wastewater treatment plants (WWTPs) accounts for large proportions their total emissions, which deserves intensive attention. This work proposed an automated machine learning (AutoML)-based analysis (ACIA) approach and predicted the specific (SEe; kg CO2/m3) successfully in nine full-scale WWTPs (W1–W9) with different configurations based on historical operational data. stacked ensemble models generated by AutoML accurately SEe (mean absolute error = 0.02232–0.02352, R2 0.65107–0.67509). Then, variable importance Shapley additive explanations (SHAP) summary plots qualitatively revealed that influent volume types secondary tertiary processes were most important variables associated prediction. interpretation results partial dependence individual conditional expectation further verified quantitative relationships between input SEe. Also, low energy efficiency high was distinguished. Compared traditional prediction methods, ACIA method could evaluate predict scales easily available reveal qualitative inside datasets simultaneously, is a powerful tool to benefit "carbon neutrality" WWTPs.

Язык: Английский

---

Coupling process-based modeling with machine learning for long-term simulation of wastewater treatment plant operations

Journal of Environmental Management, Год журнала: 2023, Номер 341, С. 118116 - 118116

Опубликована: Май 10, 2023

Язык: Английский

---