The Office of International Affairs and Overseas Students at Persian Gulf University announced a call for hiring one joint dual certificate post doc researcher for a project on the application of machine learning in developing membrane technologies in collaboration between Persian Gulf University and Qatar University. The details of the call can be found as follows:

Title:
The Application of Machine Learning in Developing Membrane Technologies

Supervisors

Dr. Seçkin Karagöz, Chemical Engineering Department, Qatar University
Dr. Ahmad Keshavarz, ICT Research Institute, Persian Gulf University
Dr. Arash Khosravi, Chemical Engineering Department, Persian Gulf University

Funding and Duration

Duration: 1 to 2 years remotely or partially remote
Funding: Monthly salary.  

Completion

JCR indexed publications are required to complete the project, and individual completion certificates will be issued from each supervision side.

Who can apply?

PhD holders familiar with artificial intelligence with background in relevant disciplines such as Chemical Engineering, Computer Engineering, Electrical Engineering, etc.
Competences recommended:
Artificial Intelligence; Machine Learning; Python/R Programming; Preliminary knowledge of Material Science

How to apply?

Please submit the required documents with the email subject of “ApplicantName_PostDoc” to:

arash.khosravi [at] pgu.ac.ir

Strict deadline: 15 March 2022.

Required documents

- Recommendation from Supervisor(s)
- CV and Motivation Letter (one page)
- Competencies Certificates (Recommended)
- English Proficiency Certificates (Recommended)

.

.

.

More Description

Overview

Membrane technologies play an increasingly important role in various industrial sectors in order to separation and purification of gas and vapor mixtures, water treatment, quality control, and other separation processes [1]. They offer many advantages such as high-quality product, low chemical consumption, low operating cost, low energy consumption,  lower footprint, and easy scale up [2]. In spite of the widespread use of membranes and their huge benefits they suffer from selectivity-permeability trade off [3]. There are numerous features influencing the performance of membranes so the prediction of permeability and selectivity is somehow challenging using conventional modeling [4-6].  

Machine learning (ML) models have been applied in chemistry and materials discovery with outstanding results [7, 8]. ML has facilitated the construction of a non-linear relationship between operating and structural parameters and the performance of membranes [9, 10]. Barentt et al. trained a ML model by a small proportion of experimental data for separation of some gas pairs. Then, trained ML model was used for the prediction of gas separation performance of a larger dataset which did not taste for these properties. By using the ML, they predicted and eventually synthesized some new polymers that led to breaking upper bound in gas separation [7]. Zhu et al. also carried out a research for predicting the gas permeability of polymers and developed a model which is publicly available [6]. There are some public advanced models and datasets in membrane science which will facilitate the research in this field. The ML algorithms are also readily interpretable and provide the researchers with a golden opportunity for establishment of a comprehensive platform for membrane design.

The aim of this project is to develop and implement an interpretable ML algorithm for polymeric membrane design and prediction of the performance. The dense and porous mixed matrix membranes for different processes may be studied. The featurization is performed with inspiration from statistical thermodynamics and practical aspects of manipulation of membranes.

References

1. Baker, R.W., Membrane technology and applications. 2012: John Wiley & Sons.

2. Hashemifard, S.A., et al., Synthetic polymeric membranes for gas and vapor separations, in Synthetic Polymeric Membranes for Advanced Water Treatment, Gas Separation, and Energy Sustainability. 2020, Elsevier. p. 217-272.

3. Patel, S.K., et al., The relative insignificance of advanced materials in enhancing the energy efficiency of desalination technologies. Energy & Environmental Science, 2020. 13(6): p. 1694-1710.

4. Yip, N.Y. and M. Elimelech, Performance limiting effects in power generation from salinity gradients by pressure retarded osmosis. Environmental science & technology, 2011. 45(23): p. 10273-10282.

5. Yang, Z., H. Guo, and C.Y. Tang, The upper bound of thin-film composite (TFC) polyamide membranes for desalination. Journal of Membrane Science, 2019. 590: p. 117297.

6. Zhu, G., et al., Polymer genome–based prediction of gas permeabilities in polymers. Journal of Polymer Engineering, 2020. 40(6): p. 451-457.

7. Barnett, J.W., et al., Designing exceptional gas-separation polymer membranes using machine learning. Science advances, 2020. 6(20): p. eaaz4301.

8. Fetanat, M., et al., Machine Learning for Advanced Design of Nanocomposite Ultrafiltration Membranes. Industrial & Engineering Chemistry Research, 2021. 60(14): p. 5236-5250.

9. Eugene, E.A., W.A. Phillip, and A.W. Dowling, Data science-enabled molecular-to-systems engineering for sustainable water treatment. Current Opinion in Chemical Engineering, 2019. 26: p. 122-130.

10. Al Aani, S., et al., Can machine language and artificial intelligence revolutionize process automation for water treatment and desalination? Desalination, 2019. 458: p. 84-96.