Megan Ebers

NSF GRFP PhD Candidate

I am currently a PhD candidate at the University of Washington in Seattle, WA, advised by Dr. Kat M Steele (Mechanical Engineering) and Dr. J Nathan Kutz (Applied Mathematics) imposing biomechanical structure on machine learning for biolocomotive simulation.

As an engineer with expertise in both applied math and biomechanical simulation, I bring a unique perspective that can help biomechanists develop and deploy state-of-the-art machine learning and think more deeply about the mathematics behind their simulations, as well as challenge the field of applied mathematicians to think about the broader applications of their work.

When I'm not neck-deep in Matlab code, you'll find me in the mountains hiking, climbing, or snowboarding.

I am supported by the NSF Graduate Research Fellowship Program.


Research

I use data-driven approaches to address shortcomings and challenges of first principles-based models. My research aims to impose biomechanical structure on machine learning for resolving dynamic inconsistencies (discrepancies) in biolocomotive simulation. Ultimately, I want to develop data-driven approaches to predict changes in human movement after brain injury.

The first step to accomplish this is to lay the theoretical groundwork for a discrepancy modeling framework. Physics-based and first-principles models pervade the engineering and physical sciences, allowing for the ability to model the dynamics of complex systems with a prescribed accuracy. The approximations used in deriving governing equations often result in discrepancies between the model and sensor-based measurements of the system, revealing the approximate nature of the equations and/or the signal-to-noise of the sensor itself.

In modern dynamic systems, such discrepancies between the model and data can lead to poor prediction and quantification of the system under consideration, often undermining the ability to produce accurate and precise control algorithms. We introduce a discrepancy modeling framework which evaluates the potential for discovering missing deterministic physics and/or parameterization of the underlying noise processes that compromise model based systems.


Education

University of Washington

PhD
Mechanical Engineering and Applied Mathematics

Co-PIs: Dr. Katherine M Steele and Dr. J Nathan Kutz

September 2018 - present

University of Washington

MS
Mechanical Engineering
Applied Mathematics
September 2018 - present

Colorado School of Mines

BS
Mechanical Engineering

Biomechanical Engineering minor

August 2014 - May 2018