SLSeungjoon Lee

Seungjoon Lee

*This is an algorithmically generated author record based on publicly available information.

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


Seungjoon Lee has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Physics-informed machine learning models for Go/No-Go criteria on reactive metamaterials

    by Seungjoon Lee, Kibaek Lee, Alberto Hernández, D. Scott Stewart

    We present a physics-informed machine learning framework for predicting Go/No-Go criteria for reactive metamaterials and study shock propagation through a one-dimensional laminate structure. The laminate material was composed of an HMX bed with equally distributed 2mm thick copper pillars. The Wide-Ranging equation of state (WR EOS) was used to model HMX while the Romenski EOS was used for the elastic regime of copper, with the assumption of perfect plasticity. The shock was initiated by using an aluminum impactor and gauges were placed at the entry of the first copper pillar and exit of the last pillar. A modified machine learning model was then developed to predict the Go/No-Go criteria for the laminate structure. The proposed model only uses short-time measurements for predicting this behavior, that leads to large reductions in computational cost at higher dimensions. This framework suggests a data-driven guideline for the design of optimal laminate structures (e.g. number of copper pillars, thickness, and distribution).

  • Numerical simulation of atomic layer deposition for thin deposit formation in a mesoporous substrate

    by Liwei Zhuang, Peter Corkery, Dennis T. Lee, Seungjoon Lee, Mahdi Kooshkbaghi, Zhen‐Liang Xu, Gance Dai, Ioannis G. Kevrekidis, Michael Tsapatsis

    ZnO deposition in porous γ‐Al2O3 via atomic layer deposition (ALD) is the critical first step for the fabrication of zeolitic imidazolate framework membranes using the ligand‐induced perm‐selectivation process (Science, 361 (2018), 1008–1011). A detailed computational fluid dynamics (CFD) model of the ALD reactor is developed using a finite‐volume‐based code and validated. It accounts for the transport processes within the feeding system and reaction chamber. The simulated precursor spatiotemporal profiles assuming no ALD reaction were used as boundary conditions in modeling diethylzinc reaction/diffusion in porous γ‐Al2O3, the predictions of which agreed with experimental electron microscopy measurements. Further simulations confirmed that the present deposition flux is much less than the upper limit of flux, below which the decoupling of reactor/substrate is an accurate assumption. The modeling approach demonstrated here allows for the design of ALD processes for thin‐film membrane formation including the synthesis of metal–organic framework membranes.


  • Data-driven blended equations of state for condensed-phase explosives

    by Kibaek Lee, Alberto M. Hernández, D. Scott Stewart, Seungjoon Lee

    We present a data-driven blended equation of state (EOS) approach for condensed phase high explosive materials. We first calibrate four different high explosive materials (Nitromethane, HMX, PETN and TATB) using a single or blending multiple Fried Howard Gibbs (FHG) EOS by an ad hoc trial and error method that has been used in the past, and which leads to a predictive model that can be used in engineering calculations. This ad-hoc calibration is then re-calibrated based on Bayesian optimisation via Gaussian Process regression. The two calibrations are then compared qualitatively and quantitatively and are shown to be in good to excellent agreement.


  • Open Access

    Coarse-scale PDEs from fine-scale observations via machine learning

    by Seungjoon Lee, Mahdi Kooshkbaghi, Konstantinos Spiliotis, Constantinos I. Siettos, Ioannis G. Kevrekidis

    Complex spatiotemporal dynamics of physicochemical processes are often modeled at a microscopic level (through, e.g., atomistic, agent-based, or lattice models) based on first principles. Some of these processes can also be successfully modeled at the macroscopic level using, e.g., partial differential equations (PDEs) describing the evolution of the right few macroscopic observables (e.g., concentration and momentum fields). Deriving good macroscopic descriptions (the so-called “closure problem”) is often a time-consuming process requiring deep understanding/intuition about the system of interest. Recent developments in data science provide alternative ways to effectively extract/learn accurate macroscopic descriptions approximating the underlying microscopic observations. In this paper, we introduce a data-driven framework for the identification of unavailable coarse-scale PDEs from microscopic observations via machine-learning algorithms. Specifically, using Gaussian processes, artificial neural networks, and/or diffusion maps, the proposed framework uncovers the relation between the relevant macroscopic space fields and their time evolution (the right-hand side of the explicitly unavailable macroscopic PDE). Interestingly, several choices equally representative of the data can be discovered. The framework will be illustrated through the data-driven discovery of macroscopic, concentration-level PDEs resulting from a fine-scale, lattice Boltzmann level model of a reaction/transport process. Once the coarse evolution law is identified, it can be simulated to produce long-term macroscopic predictions. Different features (pros as well as cons) of alternative machine-learning algorithms for performing this task (Gaussian processes and artificial neural networks) are presented and discussed.


  • Some manifold learning considerations toward explicit model predictive control

    by Robert J. Lovelett, Felix Dietrich, Seungjoon Lee, Ioannis G. Kevrekidis

    Model predictive control (MPC) is a de facto standard control algorithm across the process industries. There remain, however, applications where MPC is impractical because an optimization problem is solved at each time step. We present a link between explicit MPC formulations and manifold learning to enable facilitated prediction of the MPC policy. Our method uses a similarity measure informed by control policies and system state variables, to “learn” an intrinsic parametrization of the MPC controller using a diffusion maps algorithm, which will also discover a low‐dimensional control law when it exists as a smooth, nonlinear combination of the state variables. We use function approximation algorithms to project points from state space to the intrinsic space, and from the intrinsic space to policy space. The approach is illustrated first by “learning” the intrinsic variables for MPC control of constrained linear systems, and then by designing controllers for an unstable nonlinear reactor.


  • Open Access

    Linking Gaussian process regression with data-driven manifold embeddings for nonlinear data fusion

    by Seungjoon Lee, Felix Dietrich, George E. Karniadakis, Ioannis G. Kevrekidis

    In statistical modelling with Gaussian process regression, it has been shown that combining (few) high-fidelity data with (many) low-fidelity data can enhance prediction accuracy, compared to prediction based on the few high-fidelity data only. Such information fusion techniques for multi-fidelity data commonly approach the high-fidelity model f h ( t ) as a function of two variables ( t , s ), and then use f l ( t ) as the s data. More generally, the high-fidelity model can be written as a function of several variables ( t , s 1 , s 2 ….); the low-fidelity model f l and, say, some of its derivatives can then be substituted for these variables. In this paper, we will explore mathematical algorithms for multi-fidelity information fusion that use such an approach towards improving the representation of the high-fidelity function with only a few training data points. Given that f h may not be a simple function—and sometimes not even a function—of f l , we demonstrate that using additional functions of t , such as derivatives or shifts of f l , can drastically improve the approximation of f h through Gaussian processes. We also point out a connection with ‘embedology’ techniques from topology and dynamical systems. Our illustrative examples range from instructive caricatures to computational biology models, such as Hodgkin–Huxley neural oscillations.