2021 - present: PhD Candidates in Chemical Engineering, University of New South Wales(UNSW Sydney), Sydney, Australia.
2017 - 2020: M.Science in Petroleum Engineering, University of Tehran, Iran
2013 - 2017: B. Science in Petroleum Engineering, University of Tehran, Iran
Project title: Machine learning assisted study of photocatalysts
Photocatalytic reactions have shown their potential in solving a wide range of environmental and energy problems in recent years. Hydrogen generation is one of the most interesting applications of photocatalytic reactions which generate H2 as an environmentally friendly clean energy carrier by harvesting solar energy. The design and discovery of an efficient photocatalyst to maximize the reaction yield is the most challenging part of photocatalytic study yet. Because of the lack of a robust detailed and generalized model, most of the studies in this area are limited to experimentations that are accurate while highly time and resource consuming. In addition, a lot of material properties cannot be measured. Here, data-driven analysis comes in to tackle the problem by understanding patterns between experimental data.
Comparing these patterns with available discovered knowledge helps to modify both data-driven inference and current understanding of the photocatalytic problem. Moreover, machine learning algorithms especially deep learning reinforce the computational part of the problem which mostly is based on MD, DFT, and TDDFT by providing a parallelizable model for material property prediction in a fraction of a second for accelerating combinatorial analysis. The final aim of the proposed project is to prepare a domain knowledge-supported data-driven framework to capture a high-level material structure-property-process parameter-activity model.
- Scientia Prof Rose Amal
- Dr Hassan Masood
- A/Prof Vidhyasaharan Sethu
- A/Prof Wey Yang Teoh
Funding: ARC Funded Project
Linkedin Profile: https://www.linkedin.com/in/yousof-haghshenas-16b855131