Find Academic Supervisors

Somdatta GoswamiView profile

Assistant Professor

• Scientific Machine Learning
• Artificial Intelligence for Science
• Computational Mechanics
• +3 more

Somdatta Goswami serves as Assistant Professor in Civil and Systems Engineering and Applied Mathematics and Statistics at Johns Hopkins University, with dual affiliations at the Institute for Data Intensive Engineering and Science (IDIES) and Hopkins Extreme Materials Institute (HEMI). She leads the Centrum IntelliPhysics research group developing AI-driven methodologies for scientific discovery. Her educational trajectory includes: Bachelor's in Civil Engineering from Birla Institute of Technology, Mesra (2011) Master's in Structural Engineering from Indian Institute of Engineering Science and Technology (2013) PhD in Civil Engineering and Structural Mechanics from Bauhaus University-Weimar, Germany (2020) funded by DAAD Dr. Goswami's research pioneers Scientific Machine Learning at the intersection of computational mechanics and AI, focusing on neural operator architectures that accelerate physics-based simulations. Her group develops methods for long-time horizon prediction, multiscale multiphysics modeling, and real-time inference in complex systems through latent space representations and physics-informed learning. Current emphases include cardiac digital twins, structural response under natural hazards, and RNA electrophoresis modeling. Analysis of her 2024-2025 publications reveals dominant trends in latent operator learning, physics-informed neural networks, and hybrid solvers combining traditional numerical methods with deep learning. These innovations enable breakthroughs in computational efficiency across engineering and biological domains, particularly in multiscale modeling and uncertainty-aware simulation. Her scientific recognition includes: National Science Foundation’s National Artificial Intelligence Research Resource (NAIRR) Pilot Johns Hopkins University Discovery Award 2024 Dr. Goswami mentors PhD candidates including Dibakar Roy Sarkar (Creel Family Engineering Fellow), Sharmila, and Maryam. Major research funding comprises: NSF grant for "Cardiac Digital Twins" with Kevrekidis, Trayanova, and Maggioni NSF grant for exascale AI-integrated simulations with UT Austin DOE grant for uncertainty-informed latent operators with Shields, Graham-Brady, and Kevrekidis Johns Hopkins Discovery Award for biological systems modeling The Centrum IntelliPhysics group operates within JHU's Latrobe Hall, collaborating with IDIES and HEMI on interdisciplinary projects spanning computational mechanics, materials science, and biological systems. Their work integrates high-performance computing with novel neural architectures to solve previously intractable scientific problems.

Stefan HeinzView profile

Professor

• Mathematical Modeling
• Multiscale Processes
• Stochastic Analysis
• +5 more

Professor Stefan Heinz is an academic at the University of Wyoming , affiliated with the School of Computing as an Adjunct Professor. He holds a Ph.D. in Physics from the Heinrich-Hertz Institute, Berlin (1990) and an M.Sc. in Physics from Humboldt-Universitaet zu Berlin (1986). Research Interests: Mathematical Modeling Multiscale Processes Stochastic Analysis Monte Carlo Simulations Computational Fluid Dynamics Turbulence, Combustion, and Multiphase Flows His recent publications focus on hybrid turbulence modeling , machine learning applications for fluid dynamics , and physically consistent simulation methods , particularly for separated flows and atmospheric systems . Key keywords from his work include: Hybrid RANS-LES , Continuous Eddy Simulation , Probability Density Functions , Dynamic LES , von Kármán Constant , and Stochastic Micro-Mixing . Scientific Awards include: 2022 Adjunct Professor, University of Wyoming School of Computing 2022 Finalist for Provost Term Professorship 2015 Associate Fellow, American Institute of Aeronautics and Astronautics (AIAA) 2011 Outstanding Dissertation Supervision Award 2008 Extraordinary Merit in Research He has taught advanced courses in Stochastic Modeling (MATH 5490) and Mathematical Modeling (MATH 4300) since 2004. He organized the 2014 RMMC Summer School and led workshops on the 100 Years of Fokker-Planck Equation (2017) and Turbulence Benchmarking (2019).