Abstract
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.
School
School of Sciences and Engineering
Department
Environmental Engineering Program
Degree Name
MS in Environmental Engineering
Graduation Date
Spring 6-15-2025
Submission Date
5-27-2025
First Advisor
Essam Mohamed
Committee Member 1
Tamer ElBatt
Committee Member 2
Ehab Mina
Extent
121 p.
Document Type
Master's Thesis
Institutional Review Board (IRB) Approval
Not necessary for this item
Recommended Citation
APA Citation
Seif, E. M.
(2025).Multi-Parameter Optimization of Brine Desalination Using Machine Learning [Master's Thesis, the American University in Cairo]. AUC Knowledge Fountain.
https://fount.aucegypt.edu/etds/2540
MLA Citation
Seif, Elaf MMAN. Multi-Parameter Optimization of Brine Desalination Using Machine Learning. 2025. American University in Cairo, Master's Thesis. AUC Knowledge Fountain.
https://fount.aucegypt.edu/etds/2540