A novel method for grading urban socio-economic development levels based on NTL data and Landsat data
The normalization of assessing urban socio-economic development levels contributed to the formulation of sound urban development strategies. Traditional methods predominantly dependent on socio-economic statistics, frequently resulted in exorbitant data collection costs, significant time lags, and i...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10106049.2025.2527932 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The normalization of assessing urban socio-economic development levels contributed to the formulation of sound urban development strategies. Traditional methods predominantly dependent on socio-economic statistics, frequently resulted in exorbitant data collection costs, significant time lags, and incomplete spatial coverage. To address the deficiencies of current methods in terms of objectivity and real-time monitoring, this study integrated NTL and Landsat data with deep learning techniques to develop an automation identification methodology. This study developed a novel deep learning framework by integrating the VGG16 and U-Net architectures. Experimental results demonstrate that the proposed hybrid model achieves strong performance in predicting urban socio-economic development levels, with an accuracy of 86.2%. Analyses of the seven major urban agglomerations in the Yellow River Basin (2011–2022) revealed divergent trends: the Central Plains and Shandong Peninsula Urban Agglomerations maintained continuous development throughout the 12-year period, while the other five exhibited minimal changes in socio-economic development levels. |
|---|---|
| ISSN: | 1010-6049 1752-0762 |