article · Desalination and Water Treatment
Machine learning models can accurately predict key performance indicators in wastewater treatment facilities. Evaluating operations at the AlHayer wastewater treatment plant in Saudi Arabia, data on chemical oxygen demand, biological oxygen demand, and suspended solids were analysed. The plant demonstrated effective removal of suspended solids, organic matter, and nutrients. Four computational techniques were evaluated to estimate these water quality measures: logistic regression, random forest, gradient boosting, and support vector regression. The findings demonstrate that ensemble learning approaches deliver the highest accuracy. Random forest achieved determination coefficients of 91 percent for chemical oxygen demand and 95 percent for suspended solids. Meanwhile, gradient boosting provided the most accurate predictions for biological oxygen demand at 92 percent. These results highlight ensemble algorithms as effective soft solutions for monitoring treatment performance.
Accurate tracking of water quality parameters like oxygen demand and suspended solids is essential for safe wastewater treatment. Traditional physical and chemical testing can be resource-intensive, whereas computational modelling offers rapid performance estimates. Demonstrating that ensemble learning algorithms reliably predict these treatment metrics can help plant operators optimise monitoring processes and ensure environmental standards are consistently met.
This work applies directly to wastewater treatment plant management and environmental monitoring software. Operators and utility managers could integrate these validated algorithms into digital control platforms to support operational adjustments and monitoring. Having been tested on operational data from an active treatment facility, the modelling approach represents applied research ready for software integration.
AI-generated from the published abstract. Always read the original work before citing.
This study investigates the use of developed machine learning techniques for modeling the performance of AlHayer, Saudi Arabia, wastewater treatment plant (ALWTP). Three physio-chemical characteristics were measured and predicted, including chemical oxygen demand (COD), biological oxygen demand (BOD), and suspended solids (SS), at ALWTP. The pre-evaluation of collected data revealed the effective capabilities of ALWTP for the removal of suspended solids, organic, and nutrient pollutants. To estimate the physio-chemical characteristics of ALWATP, four developed machine learning techniques were evaluated and compared. Logistic regression (LR), random forest (RF), gradient boosting (GB), and support vector regression (SVR) were designed. The evaluation of the proposed models showed RF outperformed other proposed models for estimating COD and SS with accuracy 91 % and 95 % in terms coefficient of determination (R2); however, GB was found the best, with accuracy 92 %, for detecting the BOD performance of ALWATP. This indicates ensemble learning models, RF and GB, can be considered a superiority soft solution for estimating physio-chemical characteristics of wastewater treatment plant.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.dwt.2024.100524
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
