Curriculum Vitae

Fields Of Interest

Energy transition, Dynamical systems & control, Reduced-order modeling, Physics-informed machine learning, Uncertainty Quantification

Education

Ph.D., Applied Mathematics, University of Arizona, 2025 (expected)
M.S., Applied Mathematics, University of Arizona, 2021
B.S., Mathematics & Physics, University of Arizona, 2016

Research

Machine Learning Statistical Evolution of the Coarse-Grained Velocity Gradient Tensor We incorporate modern ML architectures in physics-informed reduced order models of the inherently chaotic evolution of the velocity gradient tensor in isotropic turbulence.
- Physics-informed machine learning, interpretable ML, transformers, statistical mechanics, stochastic differential equations, reduced-order modeling, big data
Optimal Natural Gas Flows in a Network with Uncertainty We work to determine optimal flows on a natural gas network under the coupled gas and energy grids upon inclusion of intermittent renewable energies and under stressing scenarios.
- PDE-constrained optimization, differentiable programming, dynamical systems, numerics, optimal (stochastic) control, optimization under uncertainty

Work experience

2020-05-13 to present: Graduate Student Researcher, Los Alamos National Laboratory
2020-05-13 to present: Graduate Research Assistant, University of Arizona
2023-05-13 to 2023-08-15: Google Summer of Code, NumFocus, Contributor, Julia/SciML
- Developed software to symbolically discretize a given PDE on a staggered grid and handle boundary conditions
2016-05-13 to 2019-08-15: Sofware Engineer II, Raytheon Missile Systems, Tucson, AZ
- Led a small team designing, implementing, and integrating an embedded software subsystem.
- Worked as scrum master to remove impediments, communicate timelines and expectations intra- and inter-team, and triage and alleviate failures.

Fellowships

Orin Flanigan Scholarship: Pipeline Simulation Interest Group
NSF Data-Driven Research Training Group Traineeship
Roots for Resilience Data Science Scholarship

Development Tools

Languages: Julia (SciML/DifferentialEquations/Flux), Python (pytorch/tensorflow), C/C++, Bash, Matlab, Ada, Cuda
HPC: Slurm, MPI
Methodologies: Continuous integration, Test-driven development, Agile
Open-source/collaboration: git, github, workflows
ML Workflows: Pytorch, TensorFlow, Flux

Service and leadership

Aug 2023: Organized and presented Programming for Applied Mathematicians Bootcamp for incoming graduate students
Jul 2023: Mentored undergraduate student as part of NSF Data-Driven REU
Apr 2023: Organized and presented Introduction to Parallelization for NSF Data-Driven Research Training
Mar 2023: Graduate Mentor for American Statistical Association DataFest Competition
Quarterly: Organized and presented Introduction to HPC seminar for Math PhD students
2021-22: SIAM Brown Bag Student Colloquium Organizer
2018-19: Certified Scrum Master: Scaled Agile Framework

Human Languages

English
- Native Speaker
Spanish
- Basic

Publications & Talks

Improving velocity gradient statistical topology using parameterized Lagrangian deformation networks

Criston Hyett, Yifeng Tian, Mikhail Stepanov, Daniel Livescu, Michael Chertkov, "Improving velocity gradient statistical topology using parameterized Lagrangian deformation networks." preparation, 2024.

Differentiable Simulator For Dynamic and Stochastic Optimal Gas and Power Flows

Criston Hyett, Laurent Pagnier, Jean Alisse, Igal Goldshtein, Lilah Saban, Robert Ferrando, Michael Chertkov, "Differentiable Simulator For Dynamic and Stochastic Optimal Gas and Power Flows." In the proceedings of (To appear) 2024 63nd IEEE Conference on Decision and Control (CDC), 2024.

Control of Line Pack in Natural Gas System: Balancing Limited Resources under Uncertainty

Criston Hyett, Laurent Pagnier, Jean Alisse, Lilach Sabban, Igal Goldshtein, Michael Chertkov, "Control of Line Pack in Natural Gas System: Balancing Limited Resources under Uncertainty." arXiv2304.01955, 2023.

Physics-informed Machine Learning for Reduced-order Modeling of Lagrangian Turbulence

Yifeng Tian, Michael Woodward, Mikhail Stepanov, Chris Fryer, Criston Hyett, Michael Chertkov, Daniel Livescu, "Physics-informed Machine Learning for Reduced-order Modeling of Lagrangian Turbulence." Bulletin of the American Physical Society, 2022.

Lagrangian Large Eddy Simulations via Physics Informed Machine Learning

Yifeng Tian, Michael Woodward, Mikhail Stepanov, Chris Fryer, Criston Hyett, Daniel Livescu, Michael Chertkov, "Lagrangian Large Eddy Simulations via Physics Informed Machine Learning." arXiv preprint arXiv:2207.04012, 2022.

Physics Informed Machine Learning of SPH: Machine Learning Lagrangian Turbulence

Michael Woodward, Yifeng Tian, Criston Hyett, Chris Fryer, Daniel Livescu, Mikhail Stepanov, Michael Chertkov, "Physics Informed Machine Learning of SPH: Machine Learning Lagrangian Turbulence." arXiv preprint arXiv:2110.13311, 2021.

Talks

Physics Informed Machine Learning with Smoothed Particle Hydrodynamics: Compressiblity and Shocks

Michael Woodward, Yifeng Tian, Criston Hyett, Chris Fryer, Daniel Livescu, Mikhail Stepanov, Michael Chertkov, "Physics Informed Machine Learning with Smoothed Particle Hydrodynamics: Compressiblity and Shocks." Bulletin of the American Physical Society, 2022.

Lagrangian Large Eddy Simulations via Physics-Informed Machine Learning

Michael Chertkov, Yifeng Tian, Mikhail Stepanov, Chris Fryer, Michael Woodward, Criston Hyett, Daniel Livescu, "Lagrangian Large Eddy Simulations via Physics-Informed Machine Learning." Bulletin of the American Physical Society, 2022.

Applicability of Machine Learning Methodologies to Model the Statistical Evolution of the Coarse-Grained Velocity Gradient Tensor

Criston Hyett, Yifeng Tian, Michael Woodward, Michael Chertkov, Daniel Livescu, Mikhail Stepanov, "Applicability of Machine Learning Methodologies to Model the Statistical Evolution of the Coarse-Grained Velocity Gradient Tensor." Bulletin of the American Physical Society, 2022.

Physics Informed Machine Learning of Smooth Particle Hydrodynamics: Validation of the Lagrangian Turbulence Approach

Michael Woodward, Yifeng Tian, Michael Chertkov, Mikhail Stepanov, Daniel Livescu, Criston Hyett, Chris Fryer, "Physics Informed Machine Learning of Smooth Particle Hydrodynamics: Validation of the Lagrangian Turbulence Approach." In the proceedings of APS Division of Fluid Dynamics Meeting Abstracts, 2021.

Physics Informed Machine Learning of Smooth Particle Hydrodynamics: Solving Inverse Problems using a mixed mode approach

Michael Woodward, Michael Chertkov, Yifeng Tian, Mikhail Stepanov, Daniel Livescu, Criston Hyett, Chris Fryer, "Physics Informed Machine Learning of Smooth Particle Hydrodynamics: Solving Inverse Problems using a mixed mode approach." In the proceedings of APS Division of Fluid Dynamics Meeting Abstracts, 2021.

Machine Learning Statistical Evolution of the Coarse-Grained Velocity Gradient Tensor

Criston Hyett, Michael Chertkov, Yifeng Tian, Daniel Livescu, Mikhail Stepanov, "Machine Learning Statistical Evolution of the Coarse-Grained Velocity Gradient Tensor." In the proceedings of APS Division of Fluid Dynamics Meeting Abstracts, 2021.

Machine Learning Lagrangian Large Eddy Simulations with Smoothed Particle Hydrodynamics

Yifeng Tian, Michael Chertkov, Michael Woodward, Mikhail Stepanov, Chris Fryer, Criston Hyett, Daniel Livescu, "Machine Learning Lagrangian Large Eddy Simulations with Smoothed Particle Hydrodynamics." In the proceedings of APS Division of Fluid Dynamics Meeting Abstracts, 2021.

Data-Analysis of the Coarse-Grained Velocity Gradient Tensor

Criston Hyett, Yifeng Tian, Michael Chertkov, Daniel Livescu, Mikhail Stepanov, "Data-Analysis of the Coarse-Grained Velocity Gradient Tensor." In the proceedings of APS Division of Fluid Dynamics Meeting Abstracts, 2021.

Machine Learning Statistical Lagrangian Geometry of Turbulence

Criston Hyett, Michael Chertkov, Yifeng Tian, Daniel Livescu, "Machine Learning Statistical Lagrangian Geometry of Turbulence." In the proceedings of APS Division of Fluid Dynamics Meeting Abstracts, 2020.

References

PhD Advisor, Dr. Michael Chertkov
PhD Advisor, Dr. Daniel Livescu