A*STAR Research

Under the mentorship of Dr. Jarvis Loh, Principal Scientist I / Group Manager (AI for Materials) at A*STAR

“The Agency for Science, Technology and Research (A*STAR) is Singapore's lead public sector agency that spearheads economic oriented research to advance scientific discovery and develop innovative technology.”

I've spent the '21 and '22 Summers doing a paid internship at A*STAR. In my first summer at A*STAR’s institute of high performance computing, I worked with my mentor, a Principal Scientist I / Group Manager (AI for Materials) at A*STAR, on researching the utilisation of Graph Representation Learning to guide Chemical Space Navigation, applying machine learning to create a “latent space” for molecules. Simply, a latent space for molecules would provide the same powerful tools the periodic table has for elements. This model would organise molecules so that patterns became visible, allowing for easier property prediction and discovery of new molecules with target properties.

From ‘22 Jan to present, I've been conducting an independant research project at A*STAR. In addressing our climate crisis, the development of solar technologies are paramount. As a continuation of my paid internship at A*STAR, I’ve chosen to research the use of machine learning as a way to efficiently screen new perovskite materials for solar panels. The model learns how to predict the bandgap and stability of perovskites given a public database, predicts the properties of unknown perovskites, and finally filters them down to predict hitherto-new materials that could accelerate our transition to renewables. I’m in the process of writing and publishing a paper with our results.



A*STAR 2nd Internship Research Abstract







A*STAR 1st Internship Research Report