Koric research on artificial intelligence featured by Advances in Engineering


Seid KoricSeid Koric’s work on artificial intelligence confluence was recently highlighted by Advances in Engineering, a Canadian establishment that disseminates results of excellent scientific and engineering research throughout the world.

The featured research – by MechSE undergrad Hunter Kollmann, NCSA Postdoctoral Research Assistant Diab W. Abueidda (and MechSE alumnus), NCSA Technical Assistant Director and MechSE Research Associate Professor Seid Koric, NCSA Research Scientist Erman Guleryuz, and CAII Affiliate Professor Nahil Sobh – demonstrated how the team developed a new deep learning model at the National Center for Supercomputing Applications (NCSA) and its Industry Program and the Center for Artificial Intelligence Innovation (CAII). Their deep learning model is based on a sophisticated convolutional neural network (CNN) that predicts optimal metamaterial designs.

Their work is currently published in Materials and Design. The focus of their research is on topology optimization (TO), a mathematical method that optimizes material layout by considering load, boundary conditions, and constraints, in order to determine the best metamaterials for a given design space. TO focuses on material functionality and efficiency, unconstrained by traditional aesthetics and design. The sheer amount of data this method requires is nearly impossible to analyze, calculate, and process without the involvement of high-performance computing, which is not always within reach for everyone.

Access barriers include the high cost of purchasing, developing, maintaining the systems, the specialized software and technical expertise necessary to operate it, and the increasing demand further restricting its availability. Consequently, this also creates access barriers to topology optimization-based material design, limiting the development of metamaterials and architectural innovation. The team turned to artificial intelligence, collaboration, and deep learning to address these gaps.

MechSE and NCSA previously reported on the team’s research findings, and the work was the basis of the HPC Innovation Excellence Award the team received from Hyperion Research in late 2020.