Bongseok Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bongseok Kim has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Guang Lin
School of Mechanical Engineering, Purdue University, West Lafayette, USA
6 shared publications - Jiahao Zhang
Department of Mathematics, Purdue University, West Lafayette, IN 47906, USA
4 shared publications - Kyunghoon Lee
Pusan Natl Univ, Dept Aerosp Engn, Busan 46241, South Korea
2 shared publications - Shinseong Kang
Pusan Natl Univ, Dept Aerosp Engn, Busan 46241, South Korea
2 shared publications Suman Chakraborty
2 shared publications- Da-Young Kang
Department of Chemical and Biomolecular Engineering, Sogang University, Seoul 121-742, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 11 November 2026
- Published by Elsevier in Machine Learning with Applications
- Vol. 26
Symbolic machine learning for vapor–liquid equilibrium prediction in nitrogen + n-alkane mixtures
- 11 November 2026
- Published by Elsevier in Machine Learning with Applications
- Vol. 26
Open AccessSymbolic machine learning for vapor–liquid equilibrium prediction in nitrogen + n-alkane mixtures
- Open Access
- 9 September 2026
- Published by Elsevier in SSRN Electronic Journal
Active Learning with Bayesian Multi-Fidelity Laplace Neural Operators for Oscillatory Parametric PDEs
Surrogate models of parametric dynamical systems are essential for many-query and real-time predictions in engineering applications such as design optimization and digital twins.However, generating high-fidelity (HF) training data over a broad range of parameters and operating conditions remains computationally expensive.To address this challenge, we propose a Bayesian multi-fidelity Laplace neural operator (MF-LNO) for uncertainty-aware active learning of oscillatory parametric PDEs.Specifically, the proposed Bayesian MF-LNO iteratively calibrates the discrepancy between low- and high-fidelity data, where predictive uncertainty guides the adaptive acquisition of informative HF trajectories.Such predictive uncertainty is quantified via replica-exchange stochastic gradient Langevin dynamics (reSGLD), whose broad posterior exploration enables uncertainty to serve as an error indicator for adaptive HF sample acquisition.Numerical experiments on the Lorenz system, Duffing oscillator, and beam dynamics demonstrate that uncertainty-guided HF sample acquisition consistently outperforms random sampling, while the proposed Bayesian MF-LNO achieves higher prediction accuracy than MF-DeepONet with predictive uncertainty quantification.These results demonstrate that Bayesian multi-fidelity LNOs, combined with uncertainty-guided active learning, provide a data-efficient framework for operator learning in engineering dynamical systems.
- 9 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessActive Learning with Bayesian Multi-Fidelity Laplace Neural Operators for Oscillatory Parametric PDEs
Surrogate models of parametric dynamical systems are essential for many-query and real-time predictions in engineering applications such as design optimization and digital twins.However, generating high-fidelity (HF) training data over a broad range of parameters and operating conditions remains computationally expensive.To address this challenge, we propose a Bayesian multi-fidelity Laplace neural operator (MF-LNO) for uncertainty-aware active learning of oscillatory parametric PDEs.Specifically, the proposed Bayesian MF-LNO iteratively calibrates the discrepancy between low- and high-fidelity data, where predictive uncertainty guides the adaptive acquisition of informative HF trajectories.Such predictive uncertainty is quantified via replica-exchange stochastic gradient Langevin dynamics (reSGLD), whose broad posterior exploration enables uncertainty to serve as an error indicator for adaptive HF sample acquisition.Numerical experiments on the Lorenz system, Duffing oscillator, and beam dynamics demonstrate that uncertainty-guided HF sample acquisition consistently outperforms random sampling, while the proposed Bayesian MF-LNO achieves higher prediction accuracy than MF-DeepONet with predictive uncertainty quantification.These results demonstrate that Bayesian multi-fidelity LNOs, combined with uncertainty-guided active learning, provide a data-efficient framework for operator learning in engineering dynamical systems.
- 15 July 2026
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
Molecular Dynamics Investigation of Mass Transport during Evaporation for the Binary System of n-Dodecane and Nitrogen.
The study of interfacial fluxes under evaporative or condensation processes is ubiquitous in thermal systems, propulsion devices, and many other engineering applications. Most continuum-scale models fail to capture the true nature of thermodynamic property variation across the interface, particularly under high-temperature and high-pressure conditions. An improvement over the sharp interface assumption of such continuum-scale models is the consideration of a diffused interface and using kinetic boundary conditions (KBCs) to model mass transport across the liquid-vapor interface. Prior studies on KBCs mainly address monatomic fluids. Two of the main ingredients required to form KBCs are density and mass flux. Here, we study a Type-III binary mixture of n-dodecane and nitrogen using non-equilibrium molecular dynamics at near-critical temperatures. Interfacial properties such as thickness, density gradient, and surface tension were analyzed. A key result is the temporal evolution of the evaporation and reflected mass fluxes across the vapor-liquid interface. We observe that both the evaporation and reflection fluxes increase with increasing temperature, indicating enhanced molecular activity and mass transport across the interface at higher Tr. In contrast, the evaporation coefficient αevap decreases from about α ≈ 0.978 at Tr = 0.70 to α ≈ 0.905 at Tr = 0.95 because the reflected-out flux increases along with the evaporation flux, which reduces the net efficiency of molecular evaporation across the interface. To the authors' knowledge, this is one of the very few studies estimating mass transport coefficients for Type-III binary systems, laying the foundation for KBCs in hydrocarbon/nitrogen mixtures.
- 15 July 2026
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
Molecular Dynamics Investigation of Mass Transport during Evaporation for the Binary System of n-Dodecane and Nitrogen.
The study of interfacial fluxes under evaporative or condensation processes is ubiquitous in thermal systems, propulsion devices, and many other engineering applications. Most continuum-scale models fail to capture the true nature of thermodynamic property variation across the interface, particularly under high-temperature and high-pressure conditions. An improvement over the sharp interface assumption of such continuum-scale models is the consideration of a diffused interface and using kinetic boundary conditions (KBCs) to model mass transport across the liquid-vapor interface. Prior studies on KBCs mainly address monatomic fluids. Two of the main ingredients required to form KBCs are density and mass flux. Here, we study a Type-III binary mixture of n-dodecane and nitrogen using non-equilibrium molecular dynamics at near-critical temperatures. Interfacial properties such as thickness, density gradient, and surface tension were analyzed. A key result is the temporal evolution of the evaporation and reflected mass fluxes across the vapor-liquid interface. We observe that both the evaporation and reflection fluxes increase with increasing temperature, indicating enhanced molecular activity and mass transport across the interface at higher Tr. In contrast, the evaporation coefficient αevap decreases from about α ≈ 0.978 at Tr = 0.70 to α ≈ 0.905 at Tr = 0.95 because the reflected-out flux increases along with the evaporation flux, which reduces the net efficiency of molecular evaporation across the interface. To the authors' knowledge, this is one of the very few studies estimating mass transport coefficients for Type-III binary systems, laying the foundation for KBCs in hydrocarbon/nitrogen mixtures.
- Open Access
- 7 July 2026
- Published by Elsevier in SSRN Electronic Journal
A Hyperbolic Neural Closure for M1 Radiation Transfer
In radiation transfer simulations, an M1 method achieves substantial computationalsavings by replacing the full angular transport equation with a low-order momentsystem. Because this reduced system is not closed, a closure model is requiredto represent the unknown higher-order moments using lower-order moments. Whilemachine learning (ML)-based closures can improve accuracy beyond classical analyticclosures, unconstrained learned closures may produce non-real characteristic speedsand consequently cause numerical solver breakdown. To guarantee real eigenvaluesof the Jacobian associated with ML closures, we propose a hyperbolic neural closurefor the M1 radiative transfer system. Rather than directly predicting closure terms,we parameterize the Jacobian through two neural networks: (i) a symmetric matrixnetwork and (ii) a strictly convex entropy network whose Hessian defines a positivedefinite symmetrizer. These components are combined to yield a Jacobian that issimilar to a symmetric matrix, thereby ensuring real eigenvalues. The closure isthen reconstructed by numerical integration of the learned Jacobian field along aprescribed integration path. Numerical experiments show that the proposed closurenot only achieves higher closure accuracy than classical analytic closures, but alsoimproves solution accuracy and remains stable in discontinuous Galerkin simulationsfor radiative transfer problems.
- 7 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Hyperbolic Neural Closure for M1 Radiation Transfer
In radiation transfer simulations, an M1 method achieves substantial computationalsavings by replacing the full angular transport equation with a low-order momentsystem. Because this reduced system is not closed, a closure model is requiredto represent the unknown higher-order moments using lower-order moments. Whilemachine learning (ML)-based closures can improve accuracy beyond classical analyticclosures, unconstrained learned closures may produce non-real characteristic speedsand consequently cause numerical solver breakdown. To guarantee real eigenvaluesof the Jacobian associated with ML closures, we propose a hyperbolic neural closurefor the M1 radiative transfer system. Rather than directly predicting closure terms,we parameterize the Jacobian through two neural networks: (i) a symmetric matrixnetwork and (ii) a strictly convex entropy network whose Hessian defines a positivedefinite symmetrizer. These components are combined to yield a Jacobian that issimilar to a symmetric matrix, thereby ensuring real eigenvalues. The closure isthen reconstructed by numerical integration of the learned Jacobian field along aprescribed integration path. Numerical experiments show that the proposed closurenot only achieves higher closure accuracy than classical analytic closures, but alsoimproves solution accuracy and remains stable in discontinuous Galerkin simulationsfor radiative transfer problems.
- Open Access
- 12 April 2026
- Published by Elsevier in SSRN Electronic Journal
BEKAN: Boundary condition–guaranteed evolutionary Kolmogorov–Arnold networks with radial basis functions for solving PDE problems
Deep learning has gained attention for solving partial differential equations (PDEs), but the limited interpretability of neural networks hinders precise enforcement of boundary conditions. To address this challenge, we propose BEKAN, a boundary condition-guaranteed evolutionary Kolmogorov-Arnold network with radial basis functions. BEKAN introduces three distinct and combinable approaches for rigorously incorporating Dirichlet, periodic, and Neumann boundary conditions.For Dirichlet problems, we construct boundary-embedded univariate basis functions using smooth Gaussian RBFs, encoding constraints directly at the activation level. For periodic problems, we design a sinusoidal periodic layer that exactly enforces periodicity. For Neumann problems, we formulate a least-squares evolutionary update that drives network parameters toward satisfying derivative constraints on boundaries. BEKAN also extends to general mixed boundary conditions, since the enforcement mechanisms for the three boundary types operate independently and can be assigned to distinct boundary segments. By integrating boundary-embedded RBFs, periodic layers, and evolutionary dynamics, BEKAN achieves accurate PDE simulations with rigorous boundary enforcement. Extensive numerical experiments on Dirichlet, Neumann, periodic, and mixed boundary value problems demonstrate that BEKAN consistently outperforms multilayer perceptron (MLP) and B-spline KAN baselines in both accuracy and boundary-condition satisfaction. This framework extends KAN capabilities for scientific machine learning, offering a robust and interpretable approach for solving complex PDEs under strict physical constraints.
- 12 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessBEKAN: Boundary condition–guaranteed evolutionary Kolmogorov–Arnold networks with radial basis functions for solving PDE problems
Deep learning has gained attention for solving partial differential equations (PDEs), but the limited interpretability of neural networks hinders precise enforcement of boundary conditions. To address this challenge, we propose BEKAN, a boundary condition-guaranteed evolutionary Kolmogorov-Arnold network with radial basis functions. BEKAN introduces three distinct and combinable approaches for rigorously incorporating Dirichlet, periodic, and Neumann boundary conditions.For Dirichlet problems, we construct boundary-embedded univariate basis functions using smooth Gaussian RBFs, encoding constraints directly at the activation level. For periodic problems, we design a sinusoidal periodic layer that exactly enforces periodicity. For Neumann problems, we formulate a least-squares evolutionary update that drives network parameters toward satisfying derivative constraints on boundaries. BEKAN also extends to general mixed boundary conditions, since the enforcement mechanisms for the three boundary types operate independently and can be assigned to distinct boundary segments. By integrating boundary-embedded RBFs, periodic layers, and evolutionary dynamics, BEKAN achieves accurate PDE simulations with rigorous boundary enforcement. Extensive numerical experiments on Dirichlet, Neumann, periodic, and mixed boundary value problems demonstrate that BEKAN consistently outperforms multilayer perceptron (MLP) and B-spline KAN baselines in both accuracy and boundary-condition satisfaction. This framework extends KAN capabilities for scientific machine learning, offering a robust and interpretable approach for solving complex PDEs under strict physical constraints.
- Open Access
- 20 February 2026
- Published by Elsevier in SSRN Electronic Journal
Weak-Form Evolutionary Kolmogorov–Arnold Networks for Solving Partial Differential Equations
Partial differential equations (PDEs) form a central component of scientific computing.Among recent advances in deep learning, evolutionary neural networks have been developed to successively capture the temporal dynamics of time-dependent PDEs via parameter evolution. The parameter updates are obtained by solving a linear system derived from the governing equation residuals at each time step.However, strong-form evolutionary approaches can yield ill-conditioned linear systems due to pointwise residual discretization, and their computational cost scales unfavorably with the number of training samples.To address these limitations, we propose a weak-form evolutionary Kolmogorov–Arnold Network (KAN) for the scalable and accurate prediction of PDE solutions.We decouple the linear system size from the number of training samples through the weak formulation, leading to improved scalability compared to strong-form approaches.We also rigorously enforce boundary conditions by constructing the trial space with boundary-constrained KANs to satisfy Dirichlet and periodic conditions, and by incorporating derivative boundary conditions directly into the weak formulation for Neumann conditions.In conclusion, the proposed weak-form evolutionary KAN framework provides a stable and scalable approach for PDEs and contributes to scientific machine learning with potential relevance to future engineering applications.
- 20 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessWeak-Form Evolutionary Kolmogorov–Arnold Networks for Solving Partial Differential Equations
Partial differential equations (PDEs) form a central component of scientific computing.Among recent advances in deep learning, evolutionary neural networks have been developed to successively capture the temporal dynamics of time-dependent PDEs via parameter evolution. The parameter updates are obtained by solving a linear system derived from the governing equation residuals at each time step.However, strong-form evolutionary approaches can yield ill-conditioned linear systems due to pointwise residual discretization, and their computational cost scales unfavorably with the number of training samples.To address these limitations, we propose a weak-form evolutionary Kolmogorov–Arnold Network (KAN) for the scalable and accurate prediction of PDE solutions.We decouple the linear system size from the number of training samples through the weak formulation, leading to improved scalability compared to strong-form approaches.We also rigorously enforce boundary conditions by constructing the trial space with boundary-constrained KANs to satisfy Dirichlet and periodic conditions, and by incorporating derivative boundary conditions directly into the weak formulation for Neumann conditions.In conclusion, the proposed weak-form evolutionary KAN framework provides a stable and scalable approach for PDEs and contributes to scientific machine learning with potential relevance to future engineering applications.
- 28 April 2025
- Published by Elsevier in Engineering Structures
- Vol. 336
Condition-based fatigue life monitoring of a high-pressure hydrogen storage vessel using a reduced basis digital twin
- 28 April 2025
- Published by Elsevier in Engineering Structures
- Vol. 336
Condition-based fatigue life monitoring of a high-pressure hydrogen storage vessel using a reduced basis digital twin
- 22 May 2024
- Published by Elsevier in Aerospace Science and Technology
- Vol. 151
Component-based wing structure reconfiguration and analysis on the fly
- 22 May 2024
- Published by Elsevier in Aerospace Science and Technology
- Vol. 151
Component-based wing structure reconfiguration and analysis on the fly