Sunwoong Yang

My research focuses on developing Digital Twins for industrial CAE applications using specialized Scientific Machine Learning (SciML) techniques that effectively leverage small datasets. I aim to bridge the gap between theoretical SciML advancements and their practical implementation in industrial environments to enhance uncertainty-aware decision-making and design optimization processes.

Personal Website: https://sites.google.com/view/aerodat/

Google Scholar: https://scholar.google.com/citations?user=JmBzYnEAAAAJ&hl=en

LinkedIn: https://www.linkedin.com/in/sunwoong-yang-0438a8218/

Personal Blog: https://yang95.tistory.com/

• J. Kim, J. Park, N. Kim, Y. Yu, K. Chang, C.S. Woo, S. Yang (co-corresponding author), and N. Kang, Physics-Constrained Graph Neural Networks for Spatio-Temporal Prediction of Drop Impact on OLED Display Panels, Expert Systems with Applications, 2025, Multi-layered OLED display panel, Ball drop impact test, Surrogate model, Spatio-temporal dynamics prediction, Physics-constrained graph neural network, Design optimization
• S. Yang, H. Kim, Y. Hong, K. Yee, R. Maulik, and N. Kang, Data-driven Physics-Informed Neural Networks: A Digital Twin Perspective, Computer Methods in Applied Mechanics and Engineering, 2024, Digital twins, Physics-informed neural networks, Adaptive sampling, Data-driven approach, Multi-fidelity data, Parametric Navier-Stokes equations, Uncertainty quantification
• S. Yang, and K. Yee, Towards Reliable Uncertainty Quantification via Deep Ensembles in Multi-output Regression Tasks, Engineering Applications of Artificial Intelligence, 2024, uncertainty quantification, Deep ensembles, Bayesian optimization, uncertainty calibration
• Y. Hong, D. Lee, S. Yang, H. Kook, and K. Yee, Exploration of stacked rotor designs for aerodynamics in hover, Aerospace Science and Technology, 108557, 2023, stacked rotor, CFD, blade-vortex interaction, hovering, design exploration
• S. Yang, S. Lee, and K. Yee, Inverse design optimization framework via a two-step deep learning approach: application to a wind turbine airfoil, Engineering with Computers, 2023, inverse design, generative modeling, design optimization, surrogate modeling
• Y.E. Kang, S. Yang (co-first author), and K. Yee, Physics-aware reduced-order modeling of transonic flow via β-variational autoencoder, Physics of Fluids, 34, 076103, 2022, generative modeling, reduced-order modeling, feature extraction
• S. Yang, and K. Yee, Comment on “Novel approach for selecting low-fidelity scale factor in multifidelity metamodeling”, AIAA Journal, 60, 4, 2022, surrogate modeling, multi-fidelity modeling
• S. Yang, and K. Yee, Design rule extraction using multi-fidelity surrogate model for unmanned combat aerial vehicles, Journal of Aircraft, 59, 4, 2022, CFD, shape & Bayesian optimization, data mining, multi-fidelity surrogate modeling

• S. Yang, Y. Wang, A. Vishwasrao, R. Vinuesa, N.W. Kang, Improved Temporal Prediction of Transient Flow Fields using Graph Neural Networks, The Korean Society of Mechanical Engineers, 2024, oral
• J. Kim, S. Yang, N.W. Kang, Comparison of Spatio-Temporal Prediction Performance of 2D Cylinder Flow: Meshgraphnet vs Neural Implicit Representation, The Korean Society of Mechanical Engineers, 2024, poster
• S. Kim, S. Yang, N.W. Kang, Improvement and Optimization of Ensemble-based Multi-Fidelity Approaches, The Korean Society of Mechanical Engineers, 2024, poster
• S. Yang, R. Vinuesa, N.W. Kang, Prediction of Vortex Shedding from a Circular Cylinder using Graph Neural Networks, Korean Society for Computational Fluids Engineering, 2024, oral
• S. Yang, R. Vinuesa, N.W. Kang, Temporal Flow Fields Prediction using Mesh-agnostic Graph U-Nets, The Korean Society of Mechanical Engineers, 2024, oral
• S. Yang, R. Vinuesa, N. Kang, Prediction of Vortex Shedding from a Circular Cylinder using Graph Neural Networks, Korean Society for Computational Fluids Engineering, 2024, oral
• S. Yang, R. Vinuesa, N. Kang, Temporal Flow Fields Prediction using Mesh-agnostic Graph U-Nets, The Korean Society of Mechanical Engineers, 2024, oral
• S. Kim, S. Yang, N. Kang, Feasibility Study of Multi-fidelity LSTM for Time-series Prediction, The Korean Society of Mechanical Engineers, 2024, poster
• J. Kim, J. Park, S. Yang, N. Kang, Physics-Informed Graph Neural Network Based Surrogate Model for Predicting the Durability of OLED Displays under Drop Impact, The Korean Society of Mechanical Engineers, 2024, oral
• D. Lee, S. Yang, J. Oh, S. Cho, S. Kim, N. Kang, Digital Twin for Wave Energy Converter: Uncertainty Quantification of Real-time Wave Height Prediction using Deep Learning, The Korean Society of Mechanical Engineers, 2024, oral
• S. Lee, S. Yang, N. Kang, Manipulator Mechanism Design Optimization using Surrogate Model-based Optimization and Sensitivity Analysis for Design Rule Extraction Methodology, The Korean Society of Mechanical Engineers, 2024, oral
• S. Yang, H. Kim, Y. Hong, K. Yee, N. Kang, Fluid-oriented Physics-informed Neural Networks via Adaptive Sampling and Data-driven Approaches, The Korean Society of Mechanical Engineers, 2023, oral
• S. Yang, H. Kim, Y. Hong, K. Yee, N. Kang, Prediction of 2D Flow Field using Vorticity-pressure-aware Physics-informed Neural Networks, Korean Society for Computational Fluids Engineering, 2023, oral
• Y. Hong, D. Lee, S. Yang, H. Kook, K. Yee, Investigation of Steady and Unsteady effects of Hovering Stacked Rotor, Korean Society for Computational Fluids Engineering, 2023, oral
• S. Yang, Y.E. Kang, K. Yee, Physics-aware prediction of high-dimensional data: theoretical background, The Korean Society for Aeronautical and Space Sciences, 2022, oral
• Y.E. Kang, S. Yang, K. Yee, Physics-aware prediction of high-dimensional data: practical applications, The Korean Society for Aeronautical and Space Sciences, 2022, oral
• S. Yang, K. Yee, Towards Quantifying Calibrated Uncertainty in Missile Performance Regression Tasks via Deep Ensembles, The Korean Society for Aeronautical and Space Sciences, 2022, poster
• S. Yang, Y.E. Kang, K. Yee, Physics-aware prediction of high-dimensional data: theoretical background, The Korean Society of Mechanical Engineers, 2022, oral
• Y.E. Kang, S. Yang, K. Yee, Physics-aware prediction of high-dimensional data: practical applications, The Korean Society of Mechanical Engineers, 2022, oral
• S. Yang, Y.E. Kang, K. Yee, Extraction of Physical Generating Factors from Given Dataset, AIIS Retreat, 2022, poster
• S. Yang, Y.E. Kang, K. Yee, Physics-aware Reduced-order Modeling of Transonic Flow via β-variational Autoencoder, Korea Data Mining Society, 2022, oral
• K. Kang, Y. Kim, E. Kang, J. Huh, S. Yang, K. Yee, Comparison of fusion methods for modeling missile aerodynamic database based on multi-fidelity aerodynamic data, Korea Institute of Military Science and Technology, 2022, oral
• S. Yang, K. Yee, Application of deep ensembles to quantifying predictive uncertainty in aerospace engineering, The Korean Society of Mechanical Engineers, 2022, oral
• Best paper award
• S. Yang, K. Yee, Application of deep ensembles to quantifying predictive uncertainty in aerodynamic data, The Korean Society for Aeronautical and Space Sciences, 2022, poster
• Y.E. Kang, S. Yang, K. Yee, Investigation on beta-VAE based reduced-order modeling of transonic flowfield, The Korean Society for Aeronautical and Space Sciences, 2022, poster
• S. Yang, S. Yoo, S. Jeong, K. Yee, Missile performance prediction via multi-fidelity modelling, The Korean Society for Aeronautical and Space Sciences, 2021, oral
• S. Yang, S. Lee, K. Yee, Inverse design optimization framework using variational autoencoder: application to wind turbine airfoil optimization, The Korean Society for Aeronautical and Space Sciences, 2021, oral
• S. Yang, Y.E. Kang, K. Yee, Multi-fidelity optimization via regression-based hierarchical Kriging, The Korean Society of Mechanical Engineers, 2021, oral
• S. Yang, S. Lee, K. Yee, Development of inverse design framework using deep generative model, Korean Institute of Intelligent Systems, 2021, oral
• S. Shin, S. Yang, S. Lee, K. Yee, Airfoil inverse design performance comparison among MLP, CNN, and RNN, The Korean Society of Mechanical Engineers, 2020, oral
• S. Yang, Y. Hong, S. Park, K. Yee, Airfoil optimization of UCAV considering cruise flight performance and low-speed longitudinal stability, The Korean Society for Aeronautical and Space Sciences, 2020, poster
• S. Yang, S. Park, K. Yee, Multi-objective and multivariate aerodynamic design analysis of double delta wing UCAV, Korean Society for Computational Fluids Engineering, 2020, oral
• S. Yang, K. Yee, Trade-off study of the multi-objective unmanned combat aerial vehicle optimization via variable-fidelity modeling and data mining, The National Congress of Fluids Engineering, 2020, oral
• S. Yang, Y. Hong, S. Park, K. Yee, Multi-objective multi-fidelity design optimization of cranked wing type UCAV considering longitudinal stability, The Korean Society for Aeronautical and Space Sciences, 2019, poster

• Machine Learning: Science and Technology, published by the IOP Publishing
• International Journal of Aeronautical & Space Sciences, published by the Springer
• Measurement Science and Technology, published by the IOP Publishing
• Physica Scripta, published by the IOP Publishing
• Scientific Reports, published by the Nature