Last updated: May 09, 2024
Professional, Data Analysis PJT, Analytical Sciences Center, LG Chem
LG Science Park, Seoul, Republic of Korea
lsw91.main@gmail.com | (+82) 10-2291-6467 | GitHub | Google Scholar
Postdoctoral Researcher in Applied Science Research Institute (Apr. 2021)
Ph.D. in Chemical and Biomolecular Engineering (Feb. 2020)
Dissertation: Nanoporous Materials Discovery for Energy and Environmental Applications using Machine Learning (Advisor: Jihan Kim)
M.S. in Chemical Engineering (Feb. 2016)
Thesis: Prediction of chemical potential and phase transition of molecular crystals using Monte Carlo simulations (Advisor: Jaeeon Chang)
B.S. in Chemical Engineering (Feb. 2014)
*The number of citations is obtained by scraping Google Scholar
| Title | Citations | Year |
|---|---|---|
| (Contributed Equally) Inverse design of porous materials using
artificial neural networks, B Kim, S Lee, J Kim, Science advances 6
(1), eaax9324, 2020 deep learning molecular simulations materials discovery |
263 | 2020 |
| Computational screening of trillions of metal–organic frameworks for
high-performance methane storage, S Lee, B Kim, H Cho et al., ACS
Applied Materials & Interfaces 13 (20), 23647-23654,
2021 deep learning molecular simulations materials discovery |
107 | 2021 |
| User-friendly graphical user interface software for ideal adsorbed
solution theory calculations, S Lee, JH Lee, J Kim, Korean Journal
of Chemical Engineering 35, 214-221, 2018 numerical analysis software design thermodynamics |
93 | 2018 |
| Predicting performance limits of methane gas storage in zeolites
with an artificial neural network, S Lee, B Kim, J Kim, Journal of
Materials Chemistry A 7 (6), 2709-2716, 2019 deep learning molecular simulations materials discovery |
44 | 2019 |
| (Contributed Equally) Computational Analysis of Linker Defective
Metal–Organic Frameworks for Membrane Separation Applications, H Kim, S
Lee, J Kim, Langmuir 35 (11), 3917-3924, 2019 molecular simulations porous materials |
10 | 2019 |
| (Contributed Equally) Performance Evaluation of Deep Learning
Architectures for Load and Temperature Forecasting under Dataset Size
Constraints and Seasonality, W Choi, S Lee, Energy and Buildings,
113027, 2023 deep learning forecasting energy management systems |
8 | 2023 |
| (Contributed Equally) Machine learning-based discovery of molecules,
crystals, and composites: A perspective review, S Lee, H Byun, M Cheon,
J Kim, JH Lee, Korean Journal of Chemical Engineering, 1-12,
2021 machine learning materials discovery |
8 | 2021 |
| Chemical potential and solid-solid equilibrium of near-spherical
Lennard-Jones dumbbell crystal, S Lee, M Kim, J Chang, Korean
Journal of Chemical Engineering 33, 1047-1058, 2016 molecular simulations numerical analysis statistical mechanics |
1 | 2016 |
| (Contributed Equally) Interpretable deep learning model for load and
temperature forecasting: Depending on encoding length, models may be
cheating on wrong answers, W Choi, S Lee, Energy and Buildings,
113410, 2023 deep learning forecasting energy management systems |
2023 | |
| Explainable kinetic modeling for aerobic biodegradation of
poly(lactic acid) using Bayesian inferences, S Lee, J Park, J Lee et
al., Under review Bayesian inferences kinetic modeling bio-plastics |
2024 |
| Title | Citations | Year |
|---|---|---|
| Applications of machine learning in metal-organic frameworks, S Chong, S Lee, B Kim, J Kim, Coordination Chemistry Reviews 423, 213487, 2020 | 128 | 2020 |
| Finding hidden signals in chemical sensors using deep learning, SY Cho, Y Lee, S Lee et al., Analytical chemistry 92 (9), 6529-6537, 2020 | 42 | 2020 |
| Size-Matching Ligand Insertion in MOF-74 for Enhanced CO2 Capture under Humid Conditions, BL Suh, S Lee, J Kim, The Journal of Physical Chemistry C 121 (44), 24444-24451, 2017 | 34 | 2017 |
| Finely tuned inverse design of metal–organic frameworks with user-desired Xe/Kr selectivity, Y Lim, J Park, S Lee, J Kim, Journal of Materials Chemistry A 9 (37), 21175-21183, 2021 | 25 | 2021 |
| Computational design of metal–organic frameworks with unprecedented high hydrogen working capacity and high synthesizability, J Park, Y Lim, S Lee, J Kim, Chemistry of Materials 35 (1), 9-16, 2022 | 15 | 2022 |
| New model for S-shaped isotherm data and its application to process modeling using IAST, S Ga, S Lee, G Park, J Kim, M Realff, JH Lee, Chemical Engineering Journal 420, 127580, 2021 | 14 | 2021 |
| Isotherm parameter library and evaluation software for CO2 capture adsorbents, S Ga, S Lee, J Kim, JH Lee, Computers & Chemical Engineering 143, 107105, 2020 | 10 | 2020 |
| Deep learning-based initial guess for minimum energy path calculations, H Park, S Lee, J Kim, Korean Journal of Chemical Engineering 38, 406-410, 2021 | 1 | 2021 |
| Real-time probabilistic backfill thermal property estimation method enabling estimation convergence judgment, W Choi, S Lee, BH Dinh, YS Kim, Case Studies in Thermal Engineering 48, 103108, 2023 | 2023 | |
| Automatic Object Extraction from Electronic Documents Using Deep Neural Network, H Jang, Y Chae, S Lee, J Jo, KIPS Transactions on Software and Data Engineering 7 (11), 411-418, 2018 | 2018 |
A deep learning library designed for time series forecasting, built on the PyTorch framework
A Python library for the construction of porous materials using topology and building blocks
User-friendly software for ideal adsorbed solution theory calculations
An energy shape calculator for the porous materials
A software tool that facilitates the calculation of chemical equilibrium using perturbed chain statistical associating fluid theory
A molecular Monte Carlo simulator employed for free energy calculations of molecules in both fluid and solid states
A Matplotlib styling and utility package crafted for the creation of publication-ready figures
(private, LG Chem)
A library designed for managing labeled images, specifically tailored for instance segmentations. This library includes tools for format conversion, patch detection aggregation, and image augmentation.
GitHub Repository (Graph-network version)
A deep neural network engineered for predicting MOF (Metal-Organic Framework) properties based on topology and building blocks
A generative adversarial network (GAN) designed for the inverse design of zeolites
A generative adversarial network (GAN) created for generating energy shapes of porous materials
(private, LG Chem, with LG AI Research)
An architecture developed for predicting oxidation states and coordination numbers from XANES data, leveraging knowledge transfer from crystal structures
●: Usable with some time investment
●●: Proficiently usable
●●●: Usable at an expert level
Construction of MOF Structures from Topology and Building Blocks, 2019 KIChE Fall Meeting and International Symposium
Evaluating Performance Limits of Methane Storage Separations of Porous Materials Using Artificial Neural Network, IUMRS-ICEM 2018
IAST++: Software for Ideal Adsorbed Solution Theory (IAST) Calculations with User-friendly Interface, 2017 KIChE Fall Meeting and International Symposium
Sensitivity Analysis of CO2 Capture Materials in Post-combustion Flue Gas, ChemIndix 2016
Order-disorder transition and free energy of the crystal of Lennard-Jones diatomics, 2014 KIChE Fall Meeting
Gold Prize (2nd), Engineering Mathematics Competition, University of Seoul, Nov. 2012