Dr. Ryan King is a senior scientist in the Complex Systems Simulation & Optimization Group within the Computational Science Center. His research focuses on optimization, machine learning, and uncertainty quantification (UQ) applied to complex energy systems and turbulent flows. Ryan leads projects on physics-informed deep learning, wind farm surrogate modeling and optimization, and multi-fidelity UQ. During his Ph.D., Ryan developed adjoint optimization techniques to improve wind plant design and created a new data-driven machine learning closure for turbulence modeling in large eddy simulations. Prior to graduate school, Ryan worked as an engineer at RES Americas where he was involved in the design and construction of over 750 MW of operational wind energy.
Research Interests
Turbulent flows
Deep learning
Uncertainty quantification
Stochastic optimization
Adjoint methods
Education
Ph.D., Mechanical Engineering, University of Colorado
B.S., Mechanical Engineering, Massachusetts Institute of Technology
Professional Experience
Energy Resource Engineer & Turbine Engineer, Renewable Energy Systems Americas Inc. (2009–2012)
Associations and Memberships
Group leader, NREL Artificial Intelligence Working Group
Featured Work
Adversarial Super-Resolution of Climatological Wind and Solar Data, PNAS (2020)
Wake Steering Optimization Under Uncertainty, Wind Energy Science (2020)
Multifidelity Uncertainty Quantification With Applications in Wind Turbine Aerodynamics, American Institute of Aeronautics and Astronautics Inc. Scitech Forum (2019)
Optimization of Wind Plant Layouts Using an Adjoint Approach, Wind Energy Science (2017)
Autonomic Closure for Turbulence Simulations, Phys. Rev. E (2016)
Awards and Honors
Outstanding Mentor Award, NREL (2018 & 2019)
Share