
Title
Research Scientist Staff 
Email
choi15@llnl.gov 
Phone
(925) 4220217 
Organization
Not Available
ORCID: here, Google Scholar: here
Are you interested in collaboration? Please do not hesitate emailing Youngsoo!
Youngsoo is a computational math scientist in CASC under Computing directorate at LLNL. His research focuses on developing efficient reduced order models for various physical simulations for timesensitive decisionmaking multiquery problems, such as inverse problems, design optimization, and uncertainty quantification. His expertise includes various scientific computing disciplines as indicated in "Research interests" below. Together with his collaborators, he has developed various powerful model order reduction techniques, such as machine learningbased nonlinear manifold and spacetime reduced order models for nonlinear dynamical systems. He has also developed the componentwise reduced order model optimization algorithm, which enables fast and accurate computational modeling tool for latticestructure design. He is currently leading datadriven surrogate modeling development team for various physical simulations, with whom he developed the open source codes, libROM and LaghosROM. He is also involved with quantum computing research. He has earned his undergraduate degree for Civil and Environmental Engineering from Cornell University and his PhD degree for Computational and Mathematical Engineering from Stanford University. He was a postdoc at Sandia National Laboratories and Stanford University prior to joining LLNL in 2017.
YouTube/Virtual Conference/Seminar Talks [Recorded Videos]
 “Efficient physicsconstrained datadriven physical simulations,”> SIG on Machine Learning and Dynamical Systems, Alan Turing Institute March 24, 2022.
 “Efficient nonlinear manifold reduced order models with sparse shallow neural networks,” BIGMECA international workshop at SafranTech, November 18, 2021.
 libROM: Library for physicsconstrained datadriven physical simulations, DDPS seminar, LLNL, October 7, 2021.
 Physicsconstrained datadriven methods of accurately accelerating simulations and their applications, PhIML Seminar, Pacific Northwest National Laboratory, August 16, 2021.
 Colloquium at Center for Mathematics and Artificial Intelligence, April 16, 2021.
 Analysis Junior Seminars at SISSA, March 19, 2021.
 Cornell MAE Spring 2021 Colloquium, February 16, 2021.
 Where are we with datadriven surrogate modeling for various physical simulations, January 19, 2021.
 Componentwise reduced order model with its application to latticestructure design, 14th WCCM and Eccomas Congress, January 11, 2020.
 Efficient nonlinear manifold reduced order model, Machine Learning for Engineering Modeling, Simulation, and Design; Workshop at Neural Information Processing Systems, December 12, 2020.
libROM Tutorial Videos
 Poisson equation and its finite element discretization
 Poisson equation and its reduced order model
 Physicsinformed sampling procedure for reduced order models
 Local reduced order models and interpolationbased parameterization
 Projectionbased reduced order model for nonlinear system
Research Interests
 Model order reduction
 Mathematical optimization
 Numerical linear algebra
 Numerical partial differential equation
 Scientific computing
 Machine learning
 Multidisciplinary design optimization (Topology optimization)
 Quantum computing
Upcoming Presentations
 Computational Research Leadership Council (CRLC) Seminar Series, San Diego State University, California, 3:30 PM PT, February 3, 2023. Zoom Link
 Applied Math Seminar, UC Santa Barbara, California, 3 PM PT, March 10, 2023. Zoom Link
 Computational Approaches to Scientific Discovery, Hyatt Regency, San Francisco Airport, California, March 27  29, 2023.
 SIAM Conference on Optimization 2023, The Sheraton Grand Seattle, Seattle, Washington, U.S., May 31  June 3, 2023.
 17th U.S. National Congress on Computational Mechanics, Albuquerque, New Mexico, July 23  27, 2023.
 10th International Congress on Industrial and Applied Mathematics, Tokyo, Japan, August 20  25, 2023.
Presentations
 eSeminar on Scientific Machine Learning talk on Interpretable and physicsconstrained datadriven methods for physical simulations, November 4, 2022.
 Data Science Seminar talk at LBL on Interpretable and physicsconstrained datadriven methods for physical simulations, October 27, 2022.
 ML/AI Engineering Cohort handson Workshop talk on Interpretable and structurepreserving datadriven methods for physical simulations, October 20, 2022.
 SIAM Conference on Mathematics of Data Science talk on Nonlinear manifold reduced order models with shallow sparse neural network, September 30, 2022.
 Talk at Widely Applied Mathematics Seminar talk at Harvard University on Interpretable and physicsconstrained datadriven methods for physical simulations, September 29, 2022.
 MMICC kickoff meeting talk on Interpretable and physicsconstrained datadriven methods for physical simulations, September 29, 2022.
 WSC all hands meeting talk, LLNL on interpretable and explainable datadriven methods for physical simulations, September 28, 2022.
 Data Learning Working Group talk, Imperial College London on Interpretable and structurepreserving datadriven methods for physical simulations, September 20, 2022.
 A contributed talk at WCCM2022 on Nonlinear manifold to componentwise reduced order models towards multiscale problems, July 31  August 5, 2022.
 A contributed talk at SIAM Annual Meeting 2022 on Efficient Reduced Order Models for Fluid Dynamics: from linear to nonlinear manifold solution representation, July 11  July 15, 2022.
 A contributed talk at WCCMAPCOM Yokohama 2022 on Nonlinear manifold to componentwise reduced order models towards multiscale problems July 31  August 5, 2022.
 MLDL workshop talk on gLaSDI: Parametric physicsinformed greedy latent space dynamics identification on July 25th, 2022.
 A HLCS seminar talk on Interpretable and Explainable Datadriven Methods for Physical Simulations July 5, 2022.
 An invited talk at IAPUQ on "Latent Space Dynamics Learning," May 27, 2022.
 A contributed talk at SIAM Conference on Uncertainty Quantification 2022 on “Efficient hyperreduced datadriven nonlinear manifold reduced order model,” April 13, 2022.
 An invited talk at SIG on Machine Learning and Dynamical Systems, Alan Turing Institute on “Efficient physicsconstrained datadriven physical simulations,”> March 24, 2022.
 An invited talk at Colloquium on Artificial Intelligence Research and Optimization at Louisiana State University on “Physicsconstrained datadriven physical simulations, using machine learning,” March 2, 2022.
 An invited talk at AIx/Digital Twin Seminar Series at Applied Materials on “Marrying Physics and Data to Accurately Accelerate Simulations,” March 1, 2022.
 An invited talk at Nuclear and Chemical Science (NACS) Seminar, LLNL on “Towards physicsconstrained machine learningbased physical simulations,” February 16, 2022.
 An invited talk at MICDE/AIM Fall 2021 Seminar Series at University of Michigan on “Physicsconstrained datadriven methods for accurately accelerating simulations,” December 3, 2021.
 A contributed talk at 33rd Nordic Seminar on Computational Mechanics on Nonlinear manifold to componentwise reduced order models towards multiscale problems, November 25th, 2021.
 A contributed talk at BIGMECA international workshop at SafranTech on “Efficient nonlinear manifold reduced order models with sparse shallow neural networks,” November 18, 2021.
 An invited talk on “Reliable and generalizable datadriven physical simulations,” SGAIAAAI21, November 6, 2021.
 A seminar talk on “Datadriven methods of accelerating physical simulations and their applications” for CRLC (Computational Research Leadership Council) seminar series at the University of Houston Clear Lake, November 1, 2021.
 A seminar talk at DDPS seminar series, October 7, 2021.
 A contributed talk at minisymposium (MS 49) on advances in reduced order modeling of solids, fluids and porous media, MMLDTCSET 2021, September 2629, 2021.
 A contributed talk at minisymposium on model order reduction for physical simulations, 16th U.S. National Congress on Computational Mechanics, July 2529, 2021.
 A contributed talk at WCSMO14, June 1318, 2021.
 A contributed talk at ECCOMAS Thematic Conference, Computational Sciences and AI in Industry, CSAI2021, June 79, 2021
 Seminar talk at Machine Learning + X seminar, CRUNCH group, Brown University, June 4, 2021.
 A contributed talk at IOP Institute of Physics, PETER 2021, May 2527, 2021. (Please see the linked video from 1:40:00 to 3:03:38)
 Seminar talk at the Applied Mathematics Colloquium in the Institute of Analysis and Numerics, University of Muenster, May 19, 2021.
 A seminar talk at Thuerey Group, Technical University of Munich, May 6, 2021.
 A seminar talk at Colloquium at Center for Mathematics and Artificial Intelligence, April 16, 2021.
 A seminar talk at PMSL seminar, ExxonMobile, April 14, 2021.
 A seminar talk at CSC seminar, Max Planck Institute, April 13, 2021.
 A seminar talk at AJS  Analysis Junior Seminars, March 19, 2021.
 “A fast and accurate neural network reduced order model for advectiondominated physical simulations” at SIAM Conference on Computational Science and Engineering(CSE21), March 15, 2021, virtual conference.
 A seminar talk at MEMS (Mechanical Engineering & Materials Science) seminar at Duke University, February 3, 2021.
 A seminar talk at Cornell Sibley School Seminar Series at Cornell University, February 16, 2021.
 “Componentwise reduced order model lattice design” at 14th World Congress in Computational Mechanics and ECCOMAS Congress, January 1115, 2021, virtual conference.
 “Efficient nonlinear manifold reduced order model” at Machine Learning for Engineering Modeling, Simulation, and Design, Workshop at Neural Information Processing Systems, December 12, 2020, virtual conference.
 “Space–time reduced order model for Boltzmann transport equation” at 26th International Conference on Transport Theory, September 2227, 2019, Paris, France.
 “A practical space–time reduced order model for largescale dynamical problems” at 15th U.S. National Congress on Computational Mechanics, July 28August 1, 2019, Austin, Texas, USA.
 “Accelerating topology optimization process using reduced order models” at the World Congress of Structural and Multidisciplinary Optimization, May 2024, 2019, Beijing, China.
 “Accelerating Training phase in timedependent nonlinear model order reduction“ at SIAM Conference on Computational Science and Engineering, February 25  March 1, 2019, Spokane, Washington, USA.
 “STGNAT and SNS: Model order reduction techniques for nonlinear dynamical systems.” Linear Algebra and Optimization Seminar at Stanford University (October 11, 2018).
 “STGNAT and SNS: Model order reduction techniques for timedependent nonlinear system of equations.” Applied Mathematics Seminar at UC Berkeley/Lawrence Berkeley Laboratory, California (September 13, 2018).
 “Reduced representation for accelerating stressconstrained topology optimization.” 13th World Congress on Computational Mechanics, Marriot Marquis, New York City, NY (July 2027, 2018).
 “Tensor decompositions in reduced order models.” Machine Learning Reading Group, LLNL, California (May 22, 2018).
 “Tensor decompositions in reduced order models.” SIAM Conference on Applied Linear Algebra, Hong Kong Baptist University (May 48, 2018).
 “Space–time leastsquares Petrov–Galerkin projection for nonlinear model reduction.” 2017 West Coast ROM workshop at LBNL, California (November 17, 2017).
 “Space–time leastsquares Petrov–Galerkin projection in nonlinear model reduction.” PDE and Applied Math Seminar at UC Davis, California (October 12, 2017).
 “Gradientbased constrained optimization using a database of linear reducedorder models.” LLNL Design Optimization Symposium (September 22, 2017).
 “Space–time leastsquares Petrov–Galerkin projection for nonlinear model reduction.” at the 14th U.S. National Congress for Computational Mechanics, Montreal, Canada (July 1720, 2017).
 “Space–time leastsquares Petrov–Galerkin projection for nonlinear model reduction.” Scientific computing and matrix computations seminar at UC Berkeley, California (April 12, 2017).
PostDoc., Sandia National Laboratories, Livermore, CA, 2015 – 2017
PostDoc., Farhat Research Group, Stanford, CA, 2013 – 2015
Ph.D., Computational and mathematical engineering, Stanford University, 2013
B.S., Civil and environmental engineering, Cornell University, 2007
A.S., Engineering, Montgomery County Community College, 2004
 Kadeethum, T., O'Malley, D., Choi, Y., Viswanathan, S., Bouklas, N., & Yoon, H. (2022). "Continuous conditional generative adversarial networks for datadriven solutions of poroelasticity with heterogeneous material properties," Computers and Geosciences, 105212.
 Jekel, C.F., Sterbentz, D.M., Aubry, S., Choi, Y., White, D.A., Belof, J.L., (2022). “Using Conservation Laws to Infer Deep Learning Model Accuracy of RichtmyerMeshkov Instabilities,” arXiv preprint, arXiv:2208.11477.
 Petra, C.G., Salazar de Troya, M.A., Petra, P., Choi, Y., Oxberry, G.M., & Tortorelli, D. (2022). “On the implementation of a quasiNewton interiorpoint algorithm in function spaces using finite element discretizations,” Optimization Methods and Software.
 McBane, S., Choi, Y., & Willcox, K. (2022). "Stressconstrained topology optimization of latticelike structures using componentwise reduced order models," Computer Methods in Applied Mechanics and Engineering, Volume 400, p115525.
 Huhn, Q.A., Tano, M.E., Ragusa, J.C., & Choi, Y. (2023). "Parametric dynamic mode decomposition for reduced order modeling," Journal of Computational Physics, Volume 475, p111852.
 He, X., Choi, Y., Fries, W.D., Belof, J., & Chen, J.S. (2022). "gLaSDI: parametric physicsinformed greedy latent space dynamics identification," arXiv preprint, arXiv:2204.12005.
 Lauzon, J.T., Cheung, S.W., Shin, Y., Choi, Y., Copeland, D.M., & Huynh, K. (2022). "SOPT: a points selection algorithm for hyperreduction in reduced order models," arXiv preprint, arXiv:2203.16494.
 Fries, W.D., He, X., & Choi, Y. (2022). "LaSDI: parametric latent space dynamics identification," Computer Methods in Applied Mechanics and Engineering, 115436.
 Kadeethum, T., Ballarin, F., O'Malley, D., Choi, Y., Bouklas, N., & Yoon, H. (2022). "Reduced order modeling with Barlow Twins selfsupervised learning: Navigating the space between linear and nonlinear solution manifolds," arXiv preprint, arXiv:2202.05460.
 Cheung, S. W., Choi, Y., Copeland, D., & Huynh, K. (2022). "Local Lagrangian reducedorder modeling for RayleighTaylor instability by solution manifold decomposition," arXiv preprint, arXiv:2201.07335.
 Kim, Y., Choi, Y., Widemann, D., & Zohdi, T. (2022). “A fast and accurate physicsinformed neural network reduced order model with shallow masked autoencoder,” Journal of Computational Physics, 110841.
 Copeland, D., Cheung, S. W., Huynh, K., & Choi, Y. (2022). “Reduced order models for Lagrangian hydrodynamics,” Computer Methods in Applied Mechanics and Engineering, 388, 114259.
 Kadeethum, T., Ballarin, F., Choi, Y., O'Malley, D., Yoon, H., & Bouklas, N. (2021). Nonintrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques. Advances in Water Resources, Volume 160.
 Kim, Y., Wang, K., Choi, Y. (2021). Efficient space–time reduced order model for linear dynamical systems in Python using less than 120 lines of code. Mathematics, Volume 9, Issue 14.
 Hoang, C., Choi, Y., & Carlberg, K. (2021). Domaindecomposition leastsquares PetrovGalerkin (DDLSPG) nonlinear model reduction. Computer Methods in Applied Mechanics and Engineering, Volume 384.
 Kadeethum, T., O’Malley, D., Fuhg, J.N., Choi, Y., Lee, J., Viswanathan, H.S., & Bouklas, N. (2021). A framework for datadriven solution and parameter estimation of PDEs using conditional generative adversarial networks. Nature Computational Science, 1, 819–829. doi.org/10.1038/s43588021001713
 McBane, S. & Choi, Y. (2021). Componentwise reduced order model latticetype structure design. Computer Methods in Applied Mechanics and Engineering, 381, 113813.
 Choi, Y., Brown, P., Arrighi, B., Anderson, R., & Huynh, K. (2021). Spacetime reduced order model for largescale linear dynamical systems with application to Boltzmann transport problems. Journal of Computational Physics, Volume 424, 109845.
 Kim, Y., Wang, K., & Choi, Y. (2020). Efficient space–time reduced order model for linear dynamical systems in Python using less than 120 lines of code. arXiv preprint, arXiv:2011.10648.
 Anders, P., Garcia, F., Appelo, D., Guenther, S., Choi, Y., & Vogt, R. (2020). Quantum Physics without the Physics. arXiv preprint, arXiv:2012.03865.
 Kim, Y., Choi, Y., Widemann, D., & Zohdi, T. (2020). Efficient nonlinear manifold reduced order model. 2020 Conference on Neural Information Processing Systems.
 Choi, Y., Boncoraglio, G., Anderson, S., Amsallem, D., & Farhat, C. (2020). Gradientbased constrained optimization using a database of linear reducedorder models. Journal of Computational Physics, Volume 423, 109787.
 Choi, Y., Coombs, D., & Anderson, R. (2020). SNS: A Solutionbased Nonlinear Subspace method for timedependent nonlinear model order reduction. SIAM Journal of Scientific Computing, 42(2), A1116–A1146.
 White, D., Choi, Y., & Kudo, J. (2020). A dual mesh method with adaptivity for stress constrained topology optimization.Structural and Multidisciplinary Optimization, 61:749–762
 Choi, Y., Oxberry, G., White, D., & Kirchdoerfer, T. (2019). Accelerating topology optimization using reduced order models. World Congress of Structural and Multidisciplinary Optimization.
 Choi, Y. & Carlberg, K. (2019). Space–time leastsquares Petrov–Galerkin projection for nonlinear model reduction. SIAM Journal on Scientific Computing, 41(1):A26A58.
 Carlberg, K., Choi, Y., & Sargsyan, S. (2018). Conservative model reduction for finitevolume models. Journal of Computational Physics, 371, 280314.
 Choi, Y., Farhat, C., Murray, W., & Saunders, M. (2015). A practical factorization of a Schur complement for PDEconstrained distributed optimal control. Journal of Scientific Computing, 65(2), 576597.
 Amsallem, D., Neumann, D., Choi, Y., & Farhat, C. (2015). Linearized Aeroelastic Computations in the Frequency Domain Based on Computational Fluid Dynamics. arXiv preprint, arXiv:1506.07441.
 Amsallem, D., Zahr, M., Choi, Y., & Farhat, C. (2015). Design optimization using hyperreducedorder models. Structural and Multidisciplinary Optimization, 51(4), 919940.
 Choi, Y. (2012). Simultaneous analysis and design in PDEconstrained optimization (Doctoral dissertation, Stanford University).
 Wein, L. M., Choi, Y., & Denuit, S. (2010). Analyzing Evacuation Versus ShelterinPlace Strategies After a Terrorist Nuclear Detonation. Risk Analysis, 30(9), 13151327.
 Best Instructor Award from the AHPCRC summer institute at Stanford University in 2015
 Dean’s Office Award for the Stanford Opportunity Job Fair Research Poster in 2013
 Best Instructor Award from the AHPCRC summer institute at Stanford University in 2011
 Best Paper Award from the Society for Risk Analysis in 2010
 Recipient of Stanford ICME Ph.D Fellowship in 2007
 Elaine and Herman Blumenthal Award for Academic Excellence
 The Mathematics Faculty Award for Excellence
 CRLA Regular Tutoring Certificate
 A member of Phi Theta Kappa Honor Society
 A member of Golden Key Honor Society
 A member of Tau Beta Pi Engineering Honor Society