Rheoinformatic

Milad Saadat

EmailGitHubGoogle Scholar ORCIDTwitter



Education

  • Ph.D. in Mechanical Engineering (2024), Northeastern University
  • M.Sc. in Mechanical Engineering - Energy Conversion (2020), K. N. Toosi University of Technology
  • B.Sc. in Mechanical Engineering (2017), K. N. Toosi University of Technology

Milad Saadat, a Ph.D. graduate in the Mechanical and Industrial Engineering department, is immersed in research focused on data-driven solutions in mathematics and material design and discovery. Recognized for his academic endeavors, Milad was honored with the prestigious “2022 John and Katharine Cipolla PhD Merit” and “2024 Akira Yamamura Research Ph.D.” awards.

With a strong background in thermofluid sciences and numerical techniques, his research centers on two key areas:

  1. Physics-Informed Machine Learning for Material Discovery:
    • Applying physics-informed surrogate models for replicating rheometry and minimizing the experimental workload (digital twins).
    • Concentrating on pioneering methodologies for modeling and predicting material behavior.
  2. Innovative Approaches to Tackle Complex Equations:
    • Introducing inventive techniques for solving diverse equations, including fractional integro-differential equations in both forward and inverse directions.
    • harnessing machine learning for effective solutions to traditionally intricate mathematical problems.

Publications

Data-driven constitutive meta-modeling of nonlinear rheology via multifidelity neural networks

Milad Saadat, William H. Hartt V, Norman J. Wagner, Safa Jamali

Journal of Rheology · 2024


Data-driven selection of constitutive models via rheology-informed neural networks (RhINNs)

Milad Saadat, Mohammadamin Mahmoudabadbozchelou, Safa Jamali

Rheologica Acta · 2022