Prediction of wastewater treatment plant performance through machine learning techniques

Desalination and Water Treatment, Год журнала: 2024, Номер 319, С. 100524 - 100524

Опубликована: Июнь 11, 2024

This study investigates the use of developed machine learning techniques for modeling performance AlHayer, Saudi Arabia, wastewater treatment plant (ALWTP). Three physio-chemical characteristics were measured and predicted, including chemical oxygen demand (COD), biological (BOD), suspended solids (SS), at ALWTP. The pre-evaluation collected data revealed effective capabilities ALWTP removal solids, organic, nutrient pollutants. To estimate ALWATP, four evaluated compared. Logistic regression (LR), random forest (RF), gradient boosting (GB), support vector (SVR) designed. evaluation proposed models showed RF outperformed other estimating COD SS with accuracy 91 % 95 in terms coefficient determination (R2); however, GB was found best, 92 %, detecting BOD ALWATP. indicates ensemble models, GB, can be considered a superiority soft solution plant.

Язык: Английский

---

Construction of Bi2MoO6–SOVs/ZnCdS S–scheme heterojunction with the synergistic effect of internal electric field and oxygen vacancies for photocatalytic degradation of levofloxacin

Separation and Purification Technology, Год журнала: 2024, Номер 358, С. 130350 - 130350

Опубликована: Ноя. 1, 2024

Язык: Английский

---

Strong, tough, conductive and transparent nanocellulose hydrogel based on Ca2+-induced cross-linked double-networks and its adsorption of methylene blue dye

International Journal of Biological Macromolecules, Год журнала: 2024, Номер 274, С. 133417 - 133417

Опубликована: Июнь 29, 2024

Язык: Английский

---

The Magnetic Catalyst CoFe₂O₄/CoFe@BC Derived from Loofah Exhibits High Efficiency in Degrading Levofloxacin

ChemistrySelect, Год журнала: 2025, Номер 10(6)

Опубликована: Фев. 1, 2025

Abstract To mitigate pollution caused by levofloxacin (LVF) in aquatic environments, a magnetic catalyst, CoFe 2 O 4 /CoFe@BC (CF@BC), was synthesized using loofah‐derived biochar (BC) as support, through coprecipitation followed calcination at high temperatures. CF@BC utilized for the degradation of LVF aqueous solutions containing peroxymonosulfate (PMS), requiring no additional energy input. demonstrates exceptional catalytic performance, even under acidic conditions, achieving rate 98% within min. Compared to pure nanoparticles (CF), exhibits smaller particle sizes and improved dispersion properties, enhancing exposure reactive sites. The degradability CF@BC/PMS system is nearly three times greater than that CF/PMS identical conditions. Furthermore, demonstrated effective across wide initial pH range (3 9) maintained efficiency after cycles. Both Co(II)/Co(III) Fe(III)/Fe(II) are involved activation process PMS, with SO₄ •− 1 O₂ being predominant species contributing degradation. Additionally, two pathways have been proposed. developed this study can be effectively applied remediate water contaminated LVF.

Язык: Английский

---

Enhancing the Prediction of Influent Total Nitrogen in Wastewater Treatment Plant Using Adaptive Neuro-Fuzzy Inference System–Gradient-Based Optimization Algorithm

Water, Год журнала: 2024, Номер 16(21), С. 3038 - 3038

Опубликована: Окт. 23, 2024

For the accurate estimation of daily influent total nitrogen sewage plants, a novel hybrid approach is proposed in this study, where gradient-based optimization (GBO) algorithm employed to adjust hyper-parameters an adaptive neuro-fuzzy system (ANFIS). Several benchmark methods for optimizing ANFIS parameters are compared, which include particle swarm (PSO), gray wolf (GWO), and (GBO). The prediction accuracy ANFIS-GBO model evaluated against other models using four statistical measures: root-mean-squared error (RMSE), mean absolute (MAE), Nash–Sutcliffe efficiency (NSE), coefficient determination (R2). Test results show that suggested outperforms standalone ANFIS, ANFIS-PSO ANFIS-GWO from treatment plant. ANFIS-PSO, ANFIS-GWO, seven distinct input combinations predict TNinf. both testing training periods demonstrate these models, namely ANFIS-GBO, exhibit highest level seventh combination (Qw, pH, SS, TP, NH3-N, COD, BOD5). ANFS-GBO-7 reduced RMSE ANFIS-7, ANFIS-PSO-7, ANFIS-GWO-7 by 21.77, 10.73, 6.81%, respectively, test stage. Results further increasing number (NH3-N, BOD) as improves models’ ability make predictions. outcomes can potentially be (TNinf) full-scale wastewater plants.

Язык: Английский

---

Treatment of molasses-based alcohol distillery wastewater using Electro-Fenton oxidation: Optimization and model prediction by response surface methodology

Journal of Environmental Management, Год журнала: 2024, Номер 372, С. 123221 - 123221

Опубликована: Ноя. 20, 2024

Язык: Английский

---