ISCL members perform research at the intersection of data science, applied mathematics, and high-performance computing to enhance the understanding of complex multifidelity and multiphysics phenomena in various applications. In other words - we create science-based AI algorithms for applications in mechanical and aerospace engineering, Earth systems modeling, nuclear fusion, and more. ISCL has access to multiple HPC resources such as Bebop/Swing/Polaris/Aurora/Sophia (at Argonne), Gilbreth/Anvil (Purdue), and Perlmutter (NERSC).
An overview of our various research directions may be found in the following talks (starting oldest first): [1], [2], [3], [4], [5], [6], [7] . Further information about publications can be found on Google Scholar and our software contributions are available on Github. A collection of posters of our work is available here. ISCL eagerly welcomes possibilities for education, collaboration, and consulting! Feel free to reach out to us for any questions. We also run a scientific machine learning seminar series with leading researchers in our area of study - check it out here!
News
- ISCL sends numerous members to the prestigious (funded and invite-only) IMSI workshops at the University of Chicago! Ashwin, Hojin, and Kanad will attend a workshop on the foundations of generative models while Yelim will go to the Workshop on Unpacking AI Weather Emulators. Melissa will go to both! Congratulations!
- Announcing a new preprint by Kanad Sen where we develop a spectral loss function for graph-based deep learning surrogates of multiscale dynamical systems. This extends Dibyajyoti Chakraborty's work on the binned spectral losses to unstructured grids, scalably. Read more here.
- Pleased to announce a few new honors for the group. Romit was awarded the John Argyris Award for Young Scientists by the International Association for Computational Mechanics, an ASME Rising Star of Mechanical Engineering award, and a Distinguished Young Alumni award by the Birla Institute of Technology, Mesra.
- Our article on a lightweight 3D deep learning emulator for the atmosphere (LUCIE-3D) was published in Geoscientific Model Development! Congratulations to Haiwen Guan (now postdoc at Argonne National Laboratory) for leading this work! Read more here.
- See other archived news here.
Sponsors
