Call For Paper - Upcoming Conferences
Research Article | Open Access | Download PDF
Volume 13 | Issue 7 | Year 2026 | Article Id. IJME-V13I7P109 | DOI : https://doi.org/10.14445/23488360/IJME-V13I7P109

Optimizing Cylindrical Air Gap Membrane Distillation: A Random Forest Machine Learning Framework for Performance Analysis

Vandita Thantharate shahu, Prakash Dhopte, Arun Kose, Nitin Choudhary

Received Revised Accepted Published
01 May 2026 23 Jun 2026 08 Jul 2026 30 Jul 2026

Citation :

Vandita Thantharate shahu, Prakash Dhopte, Arun Kose, Nitin Choudhary, "Optimizing Cylindrical Air Gap Membrane Distillation: A Random Forest Machine Learning Framework for Performance Analysis," International Journal of Mechanical Engineering, vol. 13, no. 7, pp. 108-121, 2026. Crossref, https://doi.org/10.14445/23488360/IJME-V13I7P109

Abstract

The present study analyses the machine learning model of a Cylindrical Air Gap Membrane Distillation (CAGMD) system using a concentric PTFE membrane and copper condenser using a Random Forest (RF)-based machine learning framework. The experimental permeate flux, GOR and STEC were predicted using a dataset of 36 experimental runs with three inputs, namely: feed temperature (45-75°C), feed flow rate (1-3 lpm) and coolant flow rate (1-3 lpm). The RF models were highly accurate, with training R2 values of 0.978 (flux), 0.953 (GOR), and 0.904 (STEC), and the RF models were backed by good cross-validation results. Feed temperature was found in feature importance and SHAP analysis as the most influential parameter, whereas feed flow rate and energy recovery were the most influential parameters with secondary effects, and coolant flow rate was not significant. A parametric analysis also provided the interactions among operating variables. A Genetic Algorithm (GA) coupled with the RF model identified optimal conditions (Tf = 71.71°C, FFR = 1.295 lpm, CFR = 2.665 lpm), yielding Flux = 7.176 kg m⁻² h⁻¹, GOR = 3.308, and STEC = 82.88 kWh m⁻³, with substantial energy reduction. The suggested RFGA hybrid model is a practical and interpretable method of optimization of next-generation CAGMD systems.

Keywords

Cylindrical Air Gap Membrane Distillation, Random Forest, Machine Learning, Genetic Algorithm, Permeate flux, Feature importance, SHAP.

References

  1. A.M. Alklaibi, and Noam Lior, “Membrane-Distillation Desalination: Status and Potential,” Desalination, vol. 171, no. 2, pp. 113-131, 2005.
    [    CrossRef] [Google Scholar] [Publisher Link]
  2. Y. Elhenawy et al., “Experimental Investigation Of Two Novel Arrangements of Air Gap Membrane Distillation Module with Heat Recovery,” Energy Reports, vol. 8, pp. 8563-8573, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  3. A.M. Alklaibi, and Noam Lior, “Transport Analysis of Air-Gap Membrane Distillation,” Journal of Membrane Science, vol. 255, no. 1-2, pp. 239-253, 2005.
    [    CrossRef] [Google Scholar] [Publisher Link]
  4. Vandita T. Shahu, and S. B. Thombre, “Analysis and Optimization of a New Cylindrical Air Gap Membrane Distillation System,” Water Supply, vol. 20, no. 1, pp. 361-371, 2020.
    [    CrossRef] [Google Scholar] [Publisher Link]
  5. Vandita Thantharate Shahu, and Shashikant B. Thombre, “Theoretical and Experimental Investigation of Cylindrical Air Gap Membrane Distillation System and Effect of the Membrane Support Net on its Performance,” Environmental Science and Pollution Research, vol. 31, pp. 7775-7792, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  6. Baek-Gyu Im et al., “Theoretical Modeling and Simulation of AGMD and LGMD Desalination Processes Using a Composite Membrane,” Journal of Membrane Science, vol. 565, pp. 14-24, 2018.
    [    CrossRef] [Google Scholar] [Publisher Link]
  7. Hongxin Geng et al., “Study on the Heat and Mass Transfer in AGMD Module with Latent Heat Recovery,” Desalination and Water Treatment, vol. 57, no. 33, pp. 15276-15284, 2016.
    [    CrossRef] [Google Scholar] [Publisher Link]
  8. M. Rahimi et al., “CFD and Experimental Studies of Fouling of a Microfiltration Membrane,” Chemical Engineering and Processing: Process Intensification, vol. 48, no. 9, pp. 1405-1413, 2009.
    [    CrossRef] [Google Scholar] [Publisher Link]
  9. Afshin Pak et al., “CFD Modeling of Porous Membranes,” Desalination, vol. 222, no. 1-3, pp. 482-488, 2008.
    [    CrossRef] [Google Scholar] [Publisher Link]
  10. Waad H. Abuwatfa et al., “A Review on Membrane Fouling Prediction Using Artificial Neural Networks (ANNs),” Membranes, vol. 13, no. 7, pp. 1-29, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  11. Sue Sin Chong et al., “Advances of Machine Learning in Materials Science: Ideas and Techniques,” Frontiers of Physics, vol. 19, no. 1, pp. 1-40, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  12. Ruoqing Wang, and Wei He, “Accelerating Solar-Powered Desalination Deployment Through Transferable Learning,” Communications Materials, vol. 5, pp. 1-14, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  13. Faizan Ahmed et al., “An Experimental Evaluation, Performance Analysis, and Improvement of Water Desalination System using Optimized Machine Learning,” Process Integration and Optimization for Sustainability, vol. 10, pp. 737-752, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  14. Voravich Ganthavee, and Antoine Prandota Trzcinski, “Artificial Intelligence and Machine Learning for the Optimization of Pharmaceutical Wastewater Treatment Systems: A Review,” Environmental Chemistry Letters, vol. 22, pp. 2293-2318, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  15. Abdullah Alkhammash, “Intelligence Analysis of Membrane Distillation via Machine Learning Models for Pharmaceutical Separation,” Scientific Reports, vol. 14, no. 1, pp. 1-13, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  16. Zhonglin Cao et al., “Machine Learning in Membrane Design: From Property Prediction to AI-Guided Optimization,” Nano Letters, vol. 24, no. 10, pp. 2953-2960, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  17. Haoyu Yin et al., “Machine Learning for Membrane Design and Discovery,” Green Energy and Environment, vol. 9, no. 1, pp. 54-70, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  18. Cody L. Ritt et al., “Machine Learning Reveals Key Ion Selectivity Mechanisms in Polymeric Membranes with Subnanometer Pores,” Science Advances, vol. 8, no. 2, pp. 1-9, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  19. Abdelfattah Amari et al., “Study of Membranes with Nanotubes to Enhance Osmosis Desalination Efficiency by Using Machine Learning towards Sustainable Water Management,” Membranes, vol. 13, no. 1, pp. 1-18, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  20. Qisong Xu et al., “Synergizing Machine Learning, Molecular Simulation and Experiment to Develop Polymer Membranes for Solvent Recovery,” Journal of Membrane Science, vol. 678, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  21. Jowaher Alanazi et al., “Application of Different Mathematical Models based on Artificial Intelligence Technique to predict the Concentration Distribution of Solute Through a Polymeric Membrane,” Ecotoxicology and Environmental Safety, vol. 262, pp. 1-9, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  22. Ali K. Shargh, and Niaz Abdolrahim, “An Interpretable Deep Learning Approach for Designing Nanoporous Silicon Nitride Membranes with Tunable Mechanical Properties,” NPJ Computational Materials, vol. 9, pp. 1-10, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  23. Mostafa Delpisheh et al., “Leveraging Machine Learning in Porous Media,” Journal of Materials Chemistry A, vol. 12, no. 32, pp. 20717-20782, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  24. Muteb Alanazi, and Tareq Nafea Alharby, “Computational Evaluation Using Machine Learning for Analysis of Membrane Desalination Process Powered by Solar Energy,” Scientific Reports, vol. 15, no. 1, pp. 1-12, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  25. Pooria Behnam et al., “Development of Machine Learning and Stepwise Mechanistic Models for Performance Prediction of Direct Contact Membrane Distillation Module – A Comparative Study,” Chemical Engineering and Processing: Process Intensification, vol. 173, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  26. Mohamed Abd Elaziz et al., “Machine Learning-Aided Modeling for Predicting Freshwater Production of a Membrane Desalination System: A Long-Short-Term Memory Coupled with Election-Based Optimizer,” Alexandria Engineering Journal, vol. 86, pp. 690-703, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  27. Bashar H. Ismael et al., “Permeation Flux Prediction of Vacuum Membrane Distillation Using Hybrid Machine Learning Techniques,” Membranes, vol. 13, no. 12, pp. 1-19, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  28. Scott Lundberg, and Su-In Lee, “A Unified Approach to Interpreting Model Predictions,” Arxiv Preprint, pp. 1-10, 2017.
    [    CrossRef] [Google Scholar] [Publisher Link]
  29. Ahmad S. Jawed et al., “ANN-GA Driven Prediction and Optimization for Upscaling Photothermal Air-Gap Membrane Distillation Systems using Octy-Cu/PVDF Membranes,” Journal of Environmental Chemical Engineering, vol. 13, no. 4, pp. 1-16, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  30. Lobna Nassar et al., “Optimizing Operating Parameters for the Scalability of Photothermal Membrane Distillation using Machine Learning Techniques,” Desalination, vol. 613, pp. 1-14, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  31. Isabel Requena et al., “Application of Machine Learning to Characterize the Permeate Quality in Pilot-Scale Vacuum-Assisted Air Gap Membrane Distillation Operation,” Membranes, vol. 13, no. 11, pp. 1-21, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]