Y. Lee

ORCID: 0000-0003-3673-2708
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Hydraulic Fracturing and Reservoir Analysis
  • Reservoir Engineering and Simulation Methods
  • Meteorological Phenomena and Simulations
  • Traffic Prediction and Management Techniques
  • Traffic control and management
  • Hydrocarbon exploration and reservoir analysis
  • Seismic Imaging and Inversion Techniques
  • Transportation Planning and Optimization

Seoul National University
2012-2023

Short-term prediction is one of the essential elements intelligent transportation systems (ITS). Although fine methodologies have been reported, most methods with current time-series data lead to inefficient predictions when or future either exhibit fluctuations abruptly change. In order deal this problem, a dynamic multi-interval traffic volume model, based on k-nearest neighbour non-parametric regression (KNN-NPR), introduced in study. an empirical study real-world data, input parameters...

10.1049/iet-its.2011.0123 article EN IET Intelligent Transport Systems 2012-08-20

Summary Ensemble Kalman filter (EnKF) has been utilized to characterize reservoirs with high uncertainty. However, it requires a large number of models and long simulation time for stable reliable results. Therefore, the authors propose new history matching scheme using convolutional auto encoder (CAE) principal component analysis (PCA). Our method firstly performs PCA latent codes CAE channel reservoir information. Then, chooses 45 among total 200 near representative model, which gives most...

10.3997/2214-4609.202310439 article EN 2023-01-01

Summary Due to limited geological information and complicated patterns of channels, an ensemble reservoir models are generated consider uncertainty in a channel reservoir. Conventional ensemble-based history matching methods have many limitations, including Gaussian distribution assumption initial model dependence on characterization. To overcome these we propose novel scheme that adapts Latent Variable Evolution. First, train generative adversarial networks (GAN) using models. We then...

10.3997/2214-4609.202310441 article EN 2023-01-01

Korea Institute of Atmospheric Prediction Systems(KIAPS) is currently developing a numerical weather prediction model, including data assimilation system, to replace the Unified Model(UM). The KIAPS Integrated Model(KIM) consists spectral element-based non-hydrostatic dynamical core using finite-volume method and physics packages. system adopted hybrid 4D-EnVAR. 4D-EnVAR means that combined KIM VARiational system(KVAR) Local Ensemble Transform Kalman Filter(LETKF) technique. members uses 50...

10.5194/ems2023-183 preprint EN 2023-07-06
Coming Soon ...