Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Multi-Parameter Optimization of Brine Desalination Using Machine Learning
Air Gap Membrane Distillation (AGMD) is a promising desalination technology with significant potential for addressing global water scarcity. However, the interplay of operational parameters significantly impacts its performance, making optimization a challenging task. This research focuses on brine...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613425314562048 |
|---|---|
| access_status_str | Open Access |
| author | Seif, Elaf MMAN |
| author_browse | Seif, Elaf MMAN |
| author_facet | Seif, Elaf MMAN |
| author_sort | Seif, Elaf MMAN |
| collection | Thesis |
| description | Air Gap Membrane Distillation (AGMD) is a promising desalination technology with significant potential for addressing global water scarcity. However, the interplay of operational parameters significantly impacts its performance, making optimization a challenging task. This research focuses on brine desalination as a means to mitigate the negative environmental impacts of brine disposal which will eventually help in provide a sustainable solution for handling brine while producing freshwater. The study seeks to develop a predictive model and optimize the AGMD process for efficient brine desalination. To achieve this, Response Surface Methodology (RSM) and Artificial Neural Networks (ANNs) were utilized to develop predictive models for AGMD desalination. Results have shown that both RSM and ANN achieved comparable performance, with ANN providing slightly better accuracy. The ANN model is trained and validated using experimental data while varying membrane pore size, feed salinity, feed flow rate and feed temperature to predict two critical performance metrics: permeate flux and specific thermal energy consumption (STEC). Different activation functions and different numbers of neurons were tested. The sigmoid activation function was found to be the most effective with 10 neurons resulting in a RMSE of 0.03. The model achieved an R² value of 98.42%, 97.91%, and 97.80% for the training, validation, and test datasets, respectively. For the combined dataset, the model attained an R² value of 98.26%. While flux predictions yielded a higher R² value of 99.28% compared to STEC which achieved an R² value of 97.04%, showing higher precision in the prediction of permeate flux. Although RSM provides more interpretable insights into the effect of different parameters, ANN models are more suitable for integration into real-time process control systems where adaptability and continuous learning from new data are essential. Differential evolution is then applied using the ANN model to predict optimal performance metrics by assigning different weights to flux and STEC. This approach allows for the identification of operating conditions that best meet specific application needs, ensuring a balance between water production and energy efficiency. Optimization results demonstrated a trade-off between maximizing flux and minimizing STEC for both membrane types, with the 0.22 µm membrane achieving a 140.5% increase in flux and the 0.45 µm membrane achieving an 83.2% increase across scenarios. By addressing the challenges of brine desalination through AGMD, this study provides an approach for reducing the environmental risks associated with brine disposal through enabling the efficient recovery of freshwater from brine. |
| format | Thesis |
| id | oai:fount.aucegypt.edu:etds-3589 |
| institution | American University in Cairo (Egypt) |
| last_indexed | 2026-06-10T12:35:56.457Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from AUC Knowledge Fountain — bepress |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | AUC Knowledge Fountain |
| publisherStr | AUC Knowledge Fountain |
| record_format | dspace |
| source_str | AUC Knowledge Fountain — bepress |
| spelling | oai:fount.aucegypt.edu:etds-3589 Multi-Parameter Optimization of Brine Desalination Using Machine Learning Seif, Elaf MMAN Air Gap Membrane Distillation (AGMD) is a promising desalination technology with significant potential for addressing global water scarcity. However, the interplay of operational parameters significantly impacts its performance, making optimization a challenging task. This research focuses on brine desalination as a means to mitigate the negative environmental impacts of brine disposal which will eventually help in provide a sustainable solution for handling brine while producing freshwater. The study seeks to develop a predictive model and optimize the AGMD process for efficient brine desalination. To achieve this, Response Surface Methodology (RSM) and Artificial Neural Networks (ANNs) were utilized to develop predictive models for AGMD desalination. Results have shown that both RSM and ANN achieved comparable performance, with ANN providing slightly better accuracy. The ANN model is trained and validated using experimental data while varying membrane pore size, feed salinity, feed flow rate and feed temperature to predict two critical performance metrics: permeate flux and specific thermal energy consumption (STEC). Different activation functions and different numbers of neurons were tested. The sigmoid activation function was found to be the most effective with 10 neurons resulting in a RMSE of 0.03. The model achieved an R² value of 98.42%, 97.91%, and 97.80% for the training, validation, and test datasets, respectively. For the combined dataset, the model attained an R² value of 98.26%. While flux predictions yielded a higher R² value of 99.28% compared to STEC which achieved an R² value of 97.04%, showing higher precision in the prediction of permeate flux. Although RSM provides more interpretable insights into the effect of different parameters, ANN models are more suitable for integration into real-time process control systems where adaptability and continuous learning from new data are essential. Differential evolution is then applied using the ANN model to predict optimal performance metrics by assigning different weights to flux and STEC. This approach allows for the identification of operating conditions that best meet specific application needs, ensuring a balance between water production and energy efficiency. Optimization results demonstrated a trade-off between maximizing flux and minimizing STEC for both membrane types, with the 0.22 µm membrane achieving a 140.5% increase in flux and the 0.45 µm membrane achieving an 83.2% increase across scenarios. By addressing the challenges of brine desalination through AGMD, this study provides an approach for reducing the environmental risks associated with brine disposal through enabling the efficient recovery of freshwater from brine. 2025-06-15T07:00:00Z thesis application/pdf https://fount.aucegypt.edu/etds/2540 https://fount.aucegypt.edu/context/etds/article/3589/viewcontent/Thesis_Final_Elaf_Seif.pdf Theses and Dissertations AUC Knowledge Fountain Optimization Brine Desalination Modelling Response Surface Methodology Machine Learning Computational Engineering Environmental Engineering |
| spellingShingle | Optimization Brine Desalination Modelling Response Surface Methodology Machine Learning Computational Engineering Environmental Engineering Seif, Elaf MMAN Multi-Parameter Optimization of Brine Desalination Using Machine Learning |
| title | Multi-Parameter Optimization of Brine Desalination Using Machine Learning |
| title_full | Multi-Parameter Optimization of Brine Desalination Using Machine Learning |
| title_fullStr | Multi-Parameter Optimization of Brine Desalination Using Machine Learning |
| title_full_unstemmed | Multi-Parameter Optimization of Brine Desalination Using Machine Learning |
| title_short | Multi-Parameter Optimization of Brine Desalination Using Machine Learning |
| title_sort | multi parameter optimization of brine desalination using machine learning |
| topic | Optimization Brine Desalination Modelling Response Surface Methodology Machine Learning Computational Engineering Environmental Engineering |
| url | https://fount.aucegypt.edu/etds/2540 https://fount.aucegypt.edu/context/etds/article/3589/viewcontent/Thesis_Final_Elaf_Seif.pdf |
| work_keys_str_mv | AT seifelafmman multiparameteroptimizationofbrinedesalinationusingmachinelearning |