Publications

Showing 4 results for Author: Byeonghwa Jeong

View All publications

  • Mar, 2026

    ORNL Report

    Satellite Embedding-Based Population Imputation for Areas with Missing Building Footprint Data: A Computer Vision-Based Approach

    High-resolution population modeling is important for supporting effective decision-making across diverse sectors. LandScan Mosaic generates population estimates at the level of individual buildings and aggregates them to 3 arc-second grids, and this approach performs well in regions where building footprint data are comprehensive and reliable. However, large portions of th…

  • Mar, 2026

    ORNL Report

    PopGNN: Graph Neural Network-Based Flexible Future Population Forecasting Model

    Accurate population forecasts is important to plan critical infrastructure and services, from housing and education to healthcare and transport. However, traditional population prediction studies have only employed traditional machine learning models limited to capture complex spatial interdependencies and patterns. Althogh recently computer vision-based framework was intr…

  • Jun, 2025

    Journal

    Popnet: computer vision based deep learning model for forecasting gridded population

    This study introduces Popnet, a deep learning model for forecasting 1 km-gridded populations, integrating U-Net, ConvLSTM, a Spatial Autocorrelation module and deep ensemble methods. Using spatial variables and population data from 2000 to 2020, Popnet predicts South Korea’s population trends by age groups (under 14, 15-64 and over 65) up to 2040. In validation, it outperf…

  • Apr, 2025

    Journal

    An open retail boundary dataset for South Korea using open data and computer vision technique

    Although delineating retail boundaries is important to explore and comprehend the dynamics of the retail sector, it is hard to find studies specifically addressing it in the South Korean context. This study fills this gap by proposing new retail boundaries across South Korea. To achieve this goal, we employed a variety of retailers and building datasets and proposed a uniq…