Big brains over at the National Energy Research Scientific Computing Center (NERSC) have decided that ORNL's data scientist, Massimiliano "Max" Lupo Pasini, is doing some next-level work. He's gone and secured himself the prestigious NERSC High Performance Computing Achievement Award. Since 2013, this accolade has been earmarking the efforts of junior scientists who make the most out of NERSC's computing offerings for their research.
Awarded for his "Groundbreaking contributions to scientific machine learning," particularly through developing the HydraGNN, Lupo Pasini is no stranger to the spotlight. HydraGNN, a scalable multi-headed graph neural network, has been making waves in the field of AI-accelerated material design. It's the kind of work that takes a predictive look into how the itsy bitsy details of materials at an atomic scale can affect their macro properties. "I am very honored to have been selected as recipient of this award," Lupo Pasini told Oak Ridge National Laboratory. "NERSC is a widely utilized facility by researchers all over the world, and I knew that this would make the selection of the recipient a highly competitive process."
An Italian native with a doctorate from Emory University tucked under his belt, Lupo Pasini began his tenure at ORNL in 2018, initially as a postdoctoral research associate before jumping onto the full-time staff bandwagon a year later. The award, in some part at least, recognizes the strides made in his journey through the wilds of AI and deep learning.
With the help of NERSC's high-tech capabilities, Lupo Pasini and colleagues have been generating massive amounts of accurate first-principles data. This number-crunching lets them wrangle up scalable, robust AI capabilities trained on this data to push forward the DOE's goals for material science. "NERSC allowed me to advance my research in materials science on multiple fronts," Lupo Pasini explained to Oak Ridge National Laboratory. "On the one hand, I was able to generate large volumes of highly accurate first-principles data. On the other hand, I was able to develop scalable, robust AI capabilities trained on the generated first-principles data to advance materials science technologies under the DOE portfolio to help maintain U.S. competitiveness in material science." Nabbing the NERSC award means Lupo Pasini gets to have his work featured in a NERSC press release and also score an invite to spill the beans on his research at the NERSC seminar series.
