Academic Credentials
  • Ph.D., Mechanical Engineering, University of Utah, 2026
  • M.S., Mechanical Engineering, University of Utah, 2022
  • B.S., General Engineering, Fort Lewis College, 2020

Donovan Birky, Ph.D., specializes in computational solid mechanics, finite element modeling (FEM), and physics-informed machine learning (PIML) for material modeling. Through his work, he has leveraged high-fidelity simulations and machine learning to develop interpretable material models that improve predictive capabilities while maintaining engineering trust and transparency. His expertise includes constitutive modeling, computational mechanics, machine learning for engineering applications, uncertainty quantification, and the development of physics-based surrogate models.

Prior to joining Exponent, Dr. Birky received his Ph.D. in Mechanical Engineering from the University of Utah. His doctoral research focused on developing physics-informed machine learning methods for modeling the yield behavior of porous ductile metals. He created a PIML framework that generated closed-form material models with fewer underlying assumptions than traditional analytical approaches, while enabling rigorous uncertainty quantification and improved characterization of microstructural variability.

Dr. Birky's research experience also includes structural dynamics and surrogate modeling. As an undergraduate at Fort Lewis College, he developed a physics-informed neural network framework to predict the dynamic response of structural beams, further advancing his expertise at the intersection of mechanics, simulation, and machine learning.