Student researchers from the National Center for Supercomputing Applications and the University of Illinois Urbana-Champaign were lead authors on a paper titled, “FAIR principles for AI models with a practical application for accelerated high energy diffraction microscopy,” which earned an HPCwire Readers’ Choice award that was formally announced at SC22 on Nov. 14.
Nikil Ravi and Pranshu Chaturvedi, along with scientists from the Argonne National Laboratory and the University of Chicago, introduced a novel set of practical, concise, and measurable FAIR (Findable, Accessible, Interoperable, Reusable) principles for AI models. They showcased their approach with a domain-agnostic computational framework that brings together the Advanced Photon Source at Argonne, the Materials Data Facility, the Data and Learning Hub for Science, funcX, Globus, the ThetaGPU supercomputer, and the SambaNova DataScale system at the Argonne Leadership Computing Facility.
Researchers combined Nvidia A100 GPUs, Nvidia TensorRT, Docker, Apptainer (formerly Singularity), and the SambaNova DataScale system to demonstrate the use of AI surrogates to enable accelerated and FAIR AI-driven discovery for high-energy diffraction microscopy. The work presents a domain-agnostic computational framework to enable autonomous AI-driven discovery at scale and is showcased in the context of accelerated high-energy diffraction microscopy.
It’s an honor to receive the HPCwire award for our work. The project was highly collaborative and we put a lot of effort into it. It is wonderful to see it get recognized on a global scale.Nikil Ravi, NCSA student researcher
Ravi also received a Fiddler Undergraduate Innovation Fellowship award and Outstanding Oral Presentation Award at the Undergraduate Research Symposium at UIUC for this research. Both Ravi and Chaturvedi participated in NCSA’s Students Pushing Innovation (SPIN) program.
“I started working with my mentor, Dr. Eliu Huerta, through NCSA’s SPIN program,” Ravi said. “The SPIN internship program helped connect me with many like-minded peers and provided a lot of resources and support. It was also through the SPIN internship that I learnt how to use HPC systems and that knowledge really helped me with my research.”
Read more about the paper here.