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
- Romit presented work related to the learning of chaotic dynamical systems using deep learning without the use of backpropagation through time at USNCTAM, Pasadena, 2026. This was an invited keynote (thank you to Professor Souvik Chakraborty for the invitation).
- Hojin Kim's masterclass article on differentiable physics based turbulence modeling for three-dimensional wall-bounded flows is accepted to Computers and Fluids. Learn more here. Congrats Hojin!
- The first two students of ISCL defend with PhD degrees in Informatics from Penn State! Dibyajyoti Chakraborty and Haiwen Guan have made seminal contributions to scientific machine learning in their time with us and will be flying the ISCL Flag high in their future journeys. Thank you for the honor of being your advisor!
- A new preprint led by Hojin Kim and Dibyajyoti Chakraborty explores how a conditional multidiffusion model can recover near-wall boundary layer flow-fields for hypersonic turbulent Couette flow. This is in collaboration with Profs. Scalo and Toki at Purdue University. Read our preprint here.
- Pleased to announce a new project supported by Eli Lilly Company and the Purdue University Research Alliance Center. In this effort, we will be developing agentic workflows for automating scientific machine learning for biofluids applications in collaboration with Purdue Professors Arezoo Ardekani, Ilias Bilionis, and Hector Gomez.
- Announcing a new preprint led by Ashwin Suriyanarayanan on a novel approach to deep learning for turbulence closures using data assimilation for training data generation. An Arxiv preprint is here.
- Melissa Adrian wins an outstanding poster presentation award at the Purdue University Indianapolis Research Symposium - congrats!
- We welcome Dr. Sen Wang from the University of Notre Dame as a new postdoctoral scholar at ISCL. Sen previously worked on experimental and computational marine fog microphysics and will lead research into diffusion modeling for urban digital twins. Welcome!
- See other archived news here.
Sponsors
