Computational Mechanics & Scientific Artificial Intelligence Lab (CoMSAIL) focuses on developing the next-generation computational modeling & simulation capability for various computational mechanics problems by integrating multi-resolution data, classic numerical solver, and deep neural networks based on differentiable programming, Bayesian learning/optimization, GPU computing, and uncertainty quantification.

National Science Foundation

  • CAREER: Forward and Inverse Uncertainty Quantification of Cardiovascular Fluid-Structure Dynamics via Multi-fidelity Physics-Informed Bayesian Geometric Deep Learning (NSF OAC, 2021 – 2026).
  • OAC Core: A Machine Learning Assisted Visual Analytics Approach for Understanding Flow Surfaces (NSF OAC, 2021-2024)
  • Physics-Constrained Deep Learning for Surrogate Modeling of Dynamics of Fluids and Fluid-Structure Interaction (NSF CMMI, 2019-2022)

Office of Naval Research (ONR)

  • Young Investigator Program (YIP) Award: Physics-Preserved Neural Differentiable Computing for Predictive Modeling of Rough-Wall Turbulence. (ONR YIP, 2022 – 2025)

Air Force Office of Scientific Research

  • Optimizing Carbon/Carbon Composites Manufacturing by Identifying and Reducing Key Uncertainties for Hypersonic Applications (AFOSR, 2022 – 2025)

Defense Advanced Research Projects Agency (DARPA)

  • Physics-Informed Learning for Multiscale Systems (DARPA, 2018 – 2020)

Lucy Family Institute for Data & Society

  • Rapid Personalized Image-Based Cardiovascular Flow Modeling Using Bayesian Deep Learning (Lucy, 2022 – 2023)

ND Energy Center for Sustainable Energy

ND Environmental Change Initiative (ECI)

  • Wind Energy Harvesting based on Flow-induced Vibrations and Community Acceptance (Postdoc Fellowship, 2022-2023)


  • AnalytiXIN Manufacturing Data Asset Research (AnalytiXIN, 20222-2024)