We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Support Vector Machines for Evaluating the Impact of the Forward Osmosis Membrane Characteristics on the Rejection of the Organic Molecules
Summary
Researchers applied support vector machine modeling to predict the rejection of 53 neutral organic molecules by forward osmosis membranes based on membrane characteristics. The SVM model was validated and compared against other modeling approaches, providing a data-driven tool for optimizing forward osmosis membrane selection in water treatment applications.
The forward osmosis (FO) process is currently being studied more despite other energy-consuming processes. In addition, several works show the performance of FO membranes as its major challenges, the study of the rejection of different molecules, energy consumption, and modelling of different objectives related to this process. The main purpose of our study was to evaluate the impact of the FO membranes characteristics on the rejection of organic molecules (neutral) by modelling of the latter. However, the current work deals with the application of Support Vector Machines (SVM) for predicting the rejection of organic molecules (53) by the FO membranes. In addition, the SVM model was compared with two other models: Artificial Neural Network (ANN) and Multiple Linear Regression (MLR). The coefficient of correlation (R) for the testing data was applied to display the best SVM model. The SVM model generated with Radial Basis Function (RBF) as the kernel function showed the best R value equal to 0.8526. MLR and ANN models had R values of 0.7630 and 0.8723, respectively.
Sign in to start a discussion.
More Papers Like This
Elucidating governing factors of PFAS removal by polyamide membranes using machine learning and molecular simulations
Researchers used machine learning models to identify the key factors controlling how well polyamide membranes filter out PFAS — the so-called 'forever chemicals' that contaminate drinking water — finding that electrical charge interactions between the chemicals and the membrane are the dominant force. This approach offers a data-driven way to design better water filtration membranes for removing these persistent pollutants.
Modeling and multi-objective optimization of forward osmosis process
Researchers developed and optimized a mathematical model for forward osmosis processes used in wastewater treatment and seawater desalination. The study demonstrated that gradient-based optimization with temperature- and agent-dependent parameters can improve process efficiency, which is relevant to membrane technologies that may help address microplastic contamination in water systems.
Forward Osmosis Membrane: Review of Fabrication, Modification, Challenges and Potential
This review examines the fabrication and modification of forward osmosis membranes, a low-energy water treatment technology that uses osmotic pressure rather than hydraulic pressure for separation. Researchers discuss current challenges including membrane fouling, draw solute selection, and internal concentration polarization, while highlighting the potential of forward osmosis for applications such as desalination and wastewater treatment.
Artificial Intelligence Application in Membrane Processes and Prediction of Fouling for Better Resource Recovery
This review examines how artificial intelligence algorithms including neural-fuzzy interference systems can predict membrane fouling in water treatment processes, improve membrane selection, and optimize filtration parameters to enhance contaminant rejection and reduce operational costs.
Forward Osmosis
This appears to be a brief chapter introduction covering the principles of forward osmosis membrane technology for water treatment. Forward osmosis membranes are being investigated for microplastic removal from water, making this treatment technology relevant.