NSCC’s supercomputer helps perform high-throughput computations to accelerate the process of alloy development and to make it more cost effective.

Traditional pathways in the development of new alloys often occur through several empirical observations and optimising the composition and fabrication methodology. Such conventional methods may take up to 20 years of work before the alloy is ready for deployment.

A team of researchers at the Institute of High Performance Computing (IHPC), A*STAR are leveraging NSCC’s supercomputing resources to perform high-throughput computations and experiments coupled with machine learning techniques. This helps accelerate the process of alloy development to just 3 years in the case of fabricating a novel high entropy alloy (HEA).

To achieve this, IHPC is leveraging various domain expertise that covers first-principles simulations, molecular dynamics, and computational thermodynamics to generate a database that is used to train the machine learning model. Such a database holds a huge amount of data and requires large-scale, highperformance computing resources to analyse.

By using NSCC’s resources, the team has been able to generate more than 1 million data points that have been used to train machine learning models that predict the microstructural phase of an HEA for a given composition.

To find out more about the NSCC’s HPC resources and how you can tap on them, please contact [email protected].


NSCC NewsBytes April 2021

Other Case Studies

Better AI for safer self-driving

Strengthening the safety and robustness of AI in self-driving vehicles using NSCC’s high performance computing resources. Artificial Intelligence (AI) technologies are gaining...

Reducing the risk of fires with the help of supercomputers

Unlocking the interactive physics in two-phase chemically reacting flows with NSCC’s high performance computing resources to mitigate fires in buildings and enclosed spaces. Fire...

Using Machine Learning to identify and improve protein-ligand binding affinity predictions

Researchers from NTU are utilising NSCC’s supercomputing resources to improve the performance of learning models in molecular data analysis. AI is expected to play an...