A combined support vector regression with a firefly algorithm for prediction of energy consumption in wastewater treatment plants DOI Creative Commons
Mohammed Achite, Saeed Samadianfard, Nehal Elshaboury

и другие.

Water Science & Technology, Год журнала: 2024, Номер 90(10), С. 2747 - 2763

Опубликована: Ноя. 15, 2024

ABSTRACT Wastewater treatment plants (WWTPs) comprise energy-intensive processes, serving as primary contributors to overall WWTP costs. This research study proposes a novel approach that integrates support vector regression (SVR) with the firefly algorithm (FFA) for prediction of energy consumption in Chlef City, Algeria. The database comprises comprehensive set 1,653 samples, capturing diverse information categories. It includes chemical and physical characteristics, encompassing oxygen demand, 5-day biochemical potential hydrogen, water temperature, total suspended sediment basin, influent N-NH3 concentration, number aerators, operating time. Additionally, hydraulic energy-related parameters are represented by flow entered at station consumed respectively. Finally, meteorological data, comprising rainfall, relative humidity, aridity index, part dataset required analysis. In this regard, 15 different models correspond combinations input assessed study. results show SVR–FFA-15 can render an improvement accuracy WWTPs. provides useful tool managing wastewater makes insightful recommendations future savings.

Язык: Английский

Ensemble machine learning prediction of anaerobic co-digestion of manure and thermally pretreated harvest residues DOI
Đurđica Kovačić, Dorijan Radočaj, Mladen Jurišić

и другие.

Bioresource Technology, Год журнала: 2024, Номер 402, С. 130793 - 130793

Опубликована: Май 3, 2024

Язык: Английский

Процитировано

10
Machine learning-aided inverse design for biogas upgrading through biological CO2 conversion DOI Creative Commons
Jiasi Sun, Yue Rao, Zhen He

и другие.

Bioresource Technology, Год журнала: 2024, Номер 399, С. 130549 - 130549

Опубликована: Март 9, 2024

Язык: Английский

Процитировано

3
A novel approach for multivariate time series interval prediction of water quality at wastewater treatment plants DOI Creative Commons
Siyu Liu, Zhaocai Wang, Yanyu Li

и другие.

Water Science & Technology, Год журнала: 2024, Номер 90(10), С. 2813 - 2841

Опубликована: Ноя. 12, 2024

ABSTRACT This study proposes a novel approach for predicting variations in water quality at wastewater treatment plants (WWTPs), which is crucial optimizing process management and pollution control. The model combines convolutional bi-directional gated recursive units (CBGRUs) with adaptive bandwidth kernel function density estimation (ABKDE) to address the challenge of multivariate time series interval prediction WWTP quality. Initially, wavelet transform (WT) was employed smooth data, reducing noise fluctuations. Linear correlation coefficient (CC) non-linear mutual information (MI) techniques were then utilized select input variables. CBGRU applied capture temporal correlations series, integrating Multiple Heads Attention (MHA) mechanism enhance model's ability comprehend complex relationships within data. ABKDE employed, supplemented by bootstrap establish upper lower bounds intervals. Ablation experiments comparative analyses benchmark models confirmed superior performance point prediction, analysis forecast period, fluctuation detection Also, this verifies broad applicability robustness anomalous contributes significantly improved effluent efficiency control WWTPs.

Язык: Английский

Процитировано

3
Comparative Evaluation of Ensemble Machine Learning Models for Methane Production from Anaerobic Digestion DOI Creative Commons
Dorijan Radočaj, Mladen Jurišić

Fermentation, Год журнала: 2025, Номер 11(3), С. 130 - 130

Опубликована: Март 7, 2025

This study provides a comparative evaluation of several ensemble model constructions for the prediction specific methane yield (SMY) from anaerobic digestion. From authors’ knowledge based on existing research, present their accuracy and utilization in digestion modeling relative to individual machine learning methods is incomplete. Three input datasets compiled samples using agricultural forestry lignocellulosic residues previous studies were used this study. A total six five evaluated per dataset, whose was assessed robust 10-fold cross-validation 100 repetitions. Ensemble models outperformed one out three terms accuracy. They also produced notably lower coefficients variation root-mean-square error (RMSE) than most accurate (0.031 0.393 dataset A, 0.026 0.272 B, 0.021 0.217 AB), being much less prone randomness training test data split. The optimal generally benefited higher number included, as well diversity principles. Since reporting final fitting single split-sample approach highly randomness, adoption multiple repetitions proposed standard future studies.

Язык: Английский

Процитировано

0
Navigating future wastewater treatment plants with artificial intelligence: Applications, challenges, and innovations DOI
Xingyu Chen, Zhongfang Lei, Jo‐Shu Chang

и другие.

Journal of Cleaner Production, Год журнала: 2025, Номер unknown, С. 145467 - 145467

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Biomimicry-Inspired Automated Machine Learning Fit-for-Purpose Wastewater Treatment for Sustainable Water Reuse DOI Open Access
Vasileios Alevizos, Zongliang Yue,

Sabrina Edralin

и другие.

Water, Год журнала: 2025, Номер 17(9), С. 1395 - 1395

Опубликована: Май 6, 2025

The growing global freshwater scarcity urgently requires innovative wastewater treatment technologies. This study hypothesized that biomimicry-inspired automated machine learning (AML) could effectively manage variability through adaptive processing techniques. Utilizing decentralized swarm intelligence, specifically the Respected Parametric Insecta Swarm (RPIS), system demonstrated robust adaptability to fluctuating influent conditions, maintaining stable effluent quality without centralized control. Bio-inspired oscillatory control algorithms maintained stability under dynamic scenarios, while sensor feedback enhanced real-time responsiveness. Machine (ML) methods inspired by biological morphological evolution accurately classified characteristics (F1 score of 0.91), optimizing resource allocation dynamically. Significant reductions were observed, with chemical consumption decreasing approximately 11% and additional energy usage declining 14%. Furthermore, bio-inspired membranes selective permeability substantially reduced fouling, minimal fouling for up 30 days. Polynomial chaos expansions efficiently approximated complex nonlinear interactions, reducing computational overhead 35% parallel processing. Decentralized allowed rapid recalibration parameters, achieving pathogen removal turbidity near 3.2 NTU (Nephelometric Turbidity Units), total suspended solids consistently below 8 mg/L. Integrating biomimicry AML thus significantly advances sustainable reclamation practices, offering quantifiable improvements critical resource-efficient water management.

Язык: Английский

Процитировано

0
Meta-tuning and fast optimization of machine learning models for dynamic methane prediction in anaerobic digestion DOI
Alberto Meola,

Kläus Wolf,

Sören Weinrich

и другие.

Bioresource Technology, Год журнала: 2025, Номер unknown, С. 132654 - 132654

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Carbon to nitrogen ratio and organic loading rate optimization of sewage sludge and rice straw: Economic analysis and anaerobic digestion process understandings through machine learning DOI

Qian Li-an,

Ji Qi, Dabin Huang

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 136789 - 136789

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Machine learning facilitated the conceptual design of an alum dosing system for phosphorus removal in a wastewater treatment plant DOI Creative Commons
Jiasi Sun, Yanran Xu, Haoran Yang

и другие.

Chemosphere, Год журнала: 2024, Номер 351, С. 141154 - 141154

Опубликована: Янв. 9, 2024

Язык: Английский

Процитировано

2
Understanding machine learning predictions of wastewater treatment plant sludge with explainable artificial intelligence DOI
Fuad Bin Nasir, Jin Li

Water Environment Research, Год журнала: 2024, Номер 96(10)

Опубликована: Сен. 25, 2024

Abstract This study investigates the use of machine learning (ML) models for wastewater treatment plant (WWTP) sludge predictions and explainable artificial intelligence (XAI) techniques understanding impact variables behind prediction. Three ML models, random forest (RF), gradient boosting (GBM), tree (GBT), were evaluated their performance using statistical indicators. Input variable combinations selected through different feature selection (FS) methods. XAI employed to enhance interpretability transparency models. The results suggest that prediction accuracy depends on choice model number variables. found be effective in interpreting decisions made by each model. provides an example production applying understand factors influencing it. Understandable interpretation can facilitate targeted interventions process optimization improve efficiency sustainability processes. Practitioner Points Explainable play a crucial role promoting trust between real‐world applications. Widely practiced used predict United States plant. Feature methods reduce required input without compromising accuracy. explain driving

Язык: Английский

Процитировано

2