Modeling the Retention of Organic Compounds by Nanofiltration and Reverse Osmosis Membranes Using Bootstrap Aggregated Neural Networks

Khaouane, Latifa; Ammi, Yamina; Hanini, Salah

doi:10.1007/s13369-016-2320-2

Cited by 24 publications

(14 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mechanisms and corresponding variables that govern solute removal by membrane filtration have been explored extensively in the literature. − By identifying nonlinear correlations between input variables and target labels without governing equations, data-driven approaches have been used to address the complexity of establishing predictive models. Recently, machine learning (ML) has gained increasing popularity in solving multivariable problems in the field of environmental science, including membrane separation and materials development. − …”

Section: Introductionmentioning

confidence: 99%

Predicting Micropollutant Removal by Reverse Osmosis and Nanofiltration Membranes: Is Machine Learning Viable?

Jeong

Chung

Tong

2021

Environ. Sci. Technol.

View full text Add to dashboard Cite

Predictive models for micropollutant removal by membrane separation are highly desirable for the design and selection of appropriate membranes. While machine learning (ML) models have been applied for such purposes, their reliability might be compromised by data leakage due to inappropriate data splitting. More importantly, whether ML models can truly understand the mechanisms of membrane separation has not been revealed. In this study, we evaluate the capability of the XGBoost model to predict micropollutant removal efficiencies of reverse osmosis and nanofiltration membranes. Our results demonstrate that data leakage leads to falsely high prediction accuracy. By utilizing a model interpretation method based on the cooperative game theory, we test the knowledge of XGBoost on the mechanisms of membrane separation via quantifying the contributions of input variables to the model predictions. We reveal that XGBoost possesses an adequate understanding of size exclusion, but its knowledge of electrostatic interactions and adsorption is limited. Our findings suggest that future work should focus more on avoiding data leakage and evaluating the mechanistic knowledge of ML models. In addition, high-quality data from more diverse experimental conditions, as well as more informative variables, are needed to improve the accuracy of ML models for predicting membrane performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting Micropollutant Removal by Reverse Osmosis and Nanofiltration Membranes: Is Machine Learning Viable?

Jeong

Chung

Tong

2021

Environ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The authors are satisfied with the ANN performance, which gives good prediction for inputs changes. Another NF/RO modelling has been implemented in [68] using bootstrap aggregated neural networks and showed it superiority when compared to single neural network and multiple linear regressions.…”

Section: Artificial Neural Network Modellingmentioning

confidence: 99%

Soft computing techniques in modelling of membrane filtration system: a review

Yusuf¹,

Wahab²,

Sudin³

2019

Desalination and Water Treatment

View full text Add to dashboard Cite

The complexity of the membrane filtration system is due to membrane fouling problem, which reduce the performance of the system. This is the most challenging issue for further membrane control system design and applications. Pursuant to the understanding of different mechanisms of fouling, various modelling approaches have been explored. Modelling of membrane bioreactor filtration system has been extensively employed for the purpose of predicting dynamic behaviour of the process. The application of soft computing in solving real-life problems has become an upward trend nowadays. This paper reviews on the application of soft computing techniques to model, predict and optimize the membrane bioreactor filtration system. A brief review on membrane filtration process for reverse osmosis and other related solid liquid separation processes is also given. Due to the non-linearity of the filtration process and almost impossible to represent it using standard mathematical equation, the application of artificial intelligent based models such as neural network, knowledge-based, fuzzy system and adaptive neuro-fuzzy is investigated and reviewed. For better prediction of models, the application of soft computing tools in the framework of optimization scheme such as genetic algorithm, particle swarm optimization, gravitational search algorithm and hybrid are also reviewed.

show abstract

“…Modeling the retention of organic compounds by NF/RO membranes is a very tool important for developing robust high-pressure membrane technologies. However, there have been fewer models to "predict" the retention of organic compounds for reasons of the complexity of this mechanistic (Libotean et al 2008;Yangali-Quintanilla et al 2008;2010;Arash et al 2013;Ammi et al 2015;Flyborg et al 2017;Khaouane et al 2017;Ammi et al 2018;2021a;2021b;Nohyeong et al 2021). These research works have been conducted to investigate the use of multiple linear regressions (MLR), artificial neural networks (ANN), bootstrap aggregated neural networks (BANN), partial least squares (PLS), and support vector machines (SVM) models based on quantitative structure-activity relationship (QSAR) to correlate, model, and predict the retention of organic compounds (neutral and ionic) by NF/RO membranes including (pharmaceuticals, endocrine disrupting compounds, pesticides, alcohols, phenols, and solvents).…”

Section: Introductionmentioning

confidence: 99%

Computing Techniques for Modeling the Retention of Polar Pharmaceutical Active Compounds by Membranes

Ammi

Si‐Moussa

Hanini

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The retention of polar pharmaceutical active compounds (PPhACs) by nanofiltration (NF) and reverse osmosis (RO) membranes is of paramount importance in membrane separation processes. The retention of 21 PPhACs was correlated using computational intelligence techniques (feedforward neural networks multi-layer perceptron, feedforward neural networks radial basis function, and support vector machines). A database of 541 retention values has been collected from the literature. The results showed a high training and predictive capacity of the FNN-MLP model for the retention of PPhACs by NF/RO with a very high correlation coefficient (R = 0.9714) and a very low root mean squared error (RMSE = 3.9139%) for the all phase, which the FNN-MLP model is better than that obtained using FNN-RBF model (R = 0.7807 and RMSE = 10.2785%) and SVM model (R = 0.9677 and RMSE = 4.1598). The sensitivity analysis was computed and emphasized that the retention of PPhACs is governed by three interactions arranged in descending order: the polarity interactions (hydrophobicity/hydrophilicity) (Relative Importance RI = 75.68%), electrostatic repulsion (RI = 58.88%), and steric hindrance (RI = 54.73% and RI = 32.25%). This research suggests that the PPhACs retention on the NF/RO strongly depend much more on the topological polar surface area.

show abstract

Modeling the Retention of Organic Compounds by Nanofiltration and Reverse Osmosis Membranes Using Bootstrap Aggregated Neural Networks

Cited by 24 publications

References 62 publications

Predicting Micropollutant Removal by Reverse Osmosis and Nanofiltration Membranes: Is Machine Learning Viable?

Predicting Micropollutant Removal by Reverse Osmosis and Nanofiltration Membranes: Is Machine Learning Viable?

Soft computing techniques in modelling of membrane filtration system: a review

Computing Techniques for Modeling the Retention of Polar Pharmaceutical Active Compounds by Membranes

Contact Info

Product

Resources

About