PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 3, 20264 citationsOpen Access

Prediction of Reverse Osmosis Membrane Fouling Using Machine Learning: MLR, ANN, and SVM at a Seawater Desalination Plant

View Full Paper
SKSiham KherrafFAFatima-Zahra AbahdouMBMaria Benbouzid

Key Points

  • The central aim is to predict transmembrane pressure during reverse osmosis desalination using machine learning methods.
  • Evaluated multiple linear regression (MLR), artificial neural networks (ANN), and support vector regression (SVR) models.
  • Utilized five input parameters: temperature, turbidity, pH, conductivity, and feedflow.
  • Employed a dataset of 195 daily measurements with augmented training samples generated using SMOGN approach.
  • Implemented two modeling strategies: a minimalist approach with significant variables (pH and conductivity) and a multivariate approach.
  • SVR model achieved the best average predictive accuracy among the tested models.
  • Performance metrics included R2, RMSE, and MAE, demonstrating varying levels of model effectiveness.
  • Robustness and significance analyses provided insights into model reliability and interpretability.

Abstract

Membrane fouling remains a major obstacle to the performance of the reverse osmosis (RO) desalination processes. Artificial intelligence (AI) is now a promising approach for the reliable modeling of these complex systems. This study evaluates three modeling techniques—multiple linear regression (MLR), artificial neural networks (ANNs), and support vector regression (SVR)—for predicting transmembrane pressure (TMP) at the Boujdour desalination plant, based on five input parameters: temperature, turbidity, pH, conductivity, and feedflow. The analysis is based on an original dataset of 195 daily measurements, and due to the absence of timestamps, the study focuses on state-to-TMP prediction rather than chronological forecasting, with no temporal generalization claimed. Approximately 2000 augmented training samples generated using a conservative SMOGN approach were used for model development, while performance evaluation relied exclusively on 39 independent real test observations. Two modeling strategies were adopted: (i) a minimalist approach based on significant variables identified by an ordinary least squares (OLS) model (pH and conductivity), and (ii) a multivariate approach integrating all parameters to capture non-linear interactions. A rigorous validation framework was put in place to avoid information leakage and ensure the robustness and generalizability of the models. Performance was evaluated using R2, RMSE, and MAE metrics, supplemented by robustness and significance analyses including bootstrap confidence intervals, paired statistical comparisons, and interpretability analyses based on permutation importance, partial dependence plots (PDPs), and individual conditional expectation (ICE) curves. The results indicate that the SVR model achieves the best average predictive accuracy among the tested models, albeit with moderate explanatory power.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Kherraf et al. (2026) studied this question.

synapsesocial.com/papers/69a67eebf353c071a6f0a8b8https://doi.org/10.3390/eng7030106
Ask AI
Helpful
Bookmark
Share
View Full Paper