Elias Assaad
What inspired you to pursue this project and join the DAMC CDT?
My academic background is in Chemical Engineering from the University of Manchester. In my second year, I took an online data science course and found a strong interest for the field. Since then, I’ve been eager to combine my engineering foundation with data science to explore new applications within my university, which led me to an undergraduate research position focusing on predicting key performance indicators of personal care fluids using process analytical technology.
During my undergraduate research work, I started to value the flexibility of independent work, the process extrapolating new insights from existing literature, and interdisciplinary collaboration. These experiences motivated me to pursue a PhD, with the aim being at the forefront of research that provides value for industry. I chose my project because it allows me to continue my passion for improving chemical-related technologies through machine learning and experimental work, which both approaches often inform each other.
The CDT was an ideal environment for me, as I wanted to learn about a variety of interdisciplinary topics beyond my immediate research, such as robotics, DFT, crystallography, and so forth. This allows me become more well-informed for my future in research and empowered me to understand and collaborate with other like-minded researchers from diverse backgrounds."
What is your research project about, and what impact do you hope it will have?
My research project aims to develop an automated computational workflow to discovery new materials for solid oxide cells for green hydrogen and electricity production. The industrial sponsor for my project, Ceres Power, is leading in efficiency, but requires improved materials for better performance and sustainability. This is because they are focusing on intermediate-temperature solid oxide cell applications to minimize material degradation while maintaining operational efficiency. The project will leverage unsupervised and supervised learning techniques to predict material properties from existing data and utilize diffusion models to create novel material composition with optimized properties for solid oxide cells. My project will deliver impact via: (1) developing multi-purpose computational tools that can accelerate materials discovery across various energy applications, and (2) advancing Ceres Power's technology with optimized materials that enable more efficient and sustainable solutions, directly contributing to environmental sustainability.
What has been the most exciting or rewarding part of your PhD journey so far? How does your project benefit from being part of an interdisciplinary CDT like DAMC?
The most exciting part of my PhD has been identifying top-performing compositions through my computational models which show promising for industrial applications. Coming from an engineering background, the DAMC environment accelerated my chemistry knowledge, which allowed me to develop deeper insights in my own project. The numerous lectures offered by the DAMC (data science, electronic structure, DFT, etc.) helped me quickly get up to speed alongside my peers, ensuring I can engage with a wide range of research challenges.