Bibliographic Details
| Title: |
Popnet: computer vision based deep learning model for forecasting gridded population. |
| Authors: |
Jeong, Byeonghwa1 (AUTHOR), Lee, Bo Kyeong2 (AUTHOR) bklee@krihs.re.kr |
| Source: |
International Journal of Geographical Information Science. Jan2026, Vol. 40 Issue 1, p217-236. 20p. |
| Subject Terms: |
*Population forecasting, *Deep learning, *Demographic change, *Geographic spatial analysis, *Computer vision |
| Geographic Terms: |
South Korea |
| Abstract: |
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 outperforms traditional machine learning and state-of-the-art computer vision models. The output of this model discovered significant polarisation: population growth in urban areas, especially the capital region, and severe depopulation in rural areas. Popnet is a robust tool for offering significant insights to policymakers and related stakeholders about the detailed future population, which allows them to establish detailed, localised planning and resource allocations. [ABSTRACT FROM AUTHOR] |
| Database: |
Academic Search Index |