Refined Urban Functional Zones Identification via Empirical Bayesian Kriging: A POI-Weighted Scoring Innovation
The refined identification of Urban Functional Zones (UFZs) is crucial for effective urban planning, resource allocation, and environmental monitoring. However, achieving high precision and comprehensive identification of UFZs has been challenging. The rapid proliferation and open accessibility of m...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10857297/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The refined identification of Urban Functional Zones (UFZs) is crucial for effective urban planning, resource allocation, and environmental monitoring. However, achieving high precision and comprehensive identification of UFZs has been challenging. The rapid proliferation and open accessibility of multi-source data, such as remote sensing imagery and socio-economic datasets, have introduced new opportunities for the dynamic identification of UFZs. This paper proposes a Point of Interest (POI)-weighted scoring method based on Empirical Bayesian Kriging (EBK), which is empirically demonstrated in Xuzhou, China. We integrate multi-source data, including remote sensing-based land use/cover information, road networks, POIs, and building geometry data, to classify UFZs based on their dependence on buildings. Results indicate that: 1) The EBK interpolation method not only accounts for the spatial and directional distance relationships between known and unknown sample points, but also produces more accurate raster images and provides more precise estimates in unmeasured ranges. 2) The method successfully identifies UFZs for 99.5% of the buildings in the central urban area of Xuzhou. Additionally, the incorporation of multi-source data enables the extraction of traffic and ecological zones, facilitating the identification of non-building-reliant zones within the city, thereby enhancing the completeness and comprehensiveness of urban spatial recognition. 3) The overall accuracy achieved is 84.4%, with a Kappa coefficient of 0.804 for the classification results, which represents a significant improvement in UFZs identification accuracy compared to traditional methods and offers a robust scientific basis for urban planning and resource optimization. |
|---|---|
| ISSN: | 2169-3536 |