Identification of Urban Functional Areas and Urban Spatial Structure Analysis by Fusing Multi-Source Data Features: A Case Study of Zhengzhou, China

Abstract

The identification and delineation of urban functional zones (UFZs), which are the basic units of urban organisms, are crucial for understanding complex urban systems and the rational allocation and management of resources. Points of interest (POI) data are weak in identifying UFZs in areas with low building density and sparse data, whereas remote sensing data lack the necessary semantic information for functional zoning, and single-source data cannot perform a highly comprehensive characterization of complex UFZs. To address these issues, this study proposes a method for identifying UFZs by fusing multi-attribute features from multi-source data and introduces nighttime light and land surface temperature (LST) indicators as functional zoning references, taking the main urban area of Zhengzhou as an example. The experimental results show that the POI data with integrated three-level semantic information can characterize the semantic information of functional areas well, and the incorporation of multi-spectral, nighttime light, and LST data can further improve the recognition accuracy by approximately 10.1% compared with the POI single-source data. The final recognition accuracy and kappa coefficient reached 84.00% and 0.8162, respectively, indicating that the method is largely consistent with the actual situation and is feasible. The analysis showed that the main urban area of Zhengzhou as a whole is characterized by the coordinated development of single and mixed functional areas, in which a distinct residential-commercial-public complex is formed, and the urban functional areas on the block scale have diverse attributes. This study can provide a decision-making reference for the future development planning and management of Zhengzhou, China.

Accurate Identification of Micro-scale Urban Functional Zones from the Perspective of Spatial Dialectic

“…Referring to existing literature 18,45,62,63 , many scholars in urban functional zones research currently prefer to use the confusion matrix for accuracy verification. Because it is not only relatively simple to calculate without complex data processing steps, but also provides clarity on the different types and numbers of errors during the classification process.…”

“…This subjectivity in POI reclassification undermines the objectivity and consistency of the results. Additionally, the weighting system used to compensate for the inherent lack 45,62,69 of spatial scale characteristics in point-type spatial data like POI data is also an important consideration. Conventional weight values are assigned based on manual experience or expert judgment.…”

“…Finally, it should be noted that some previous studies have categorized functional zones into single functional zones and mixed functional zones 50,51 , with further subdivisions 52,62,67 such as "Dual-functional Compound", "Tri-functional Compound", and "Quadruple-functional Compound". However, these classifications often overlook the impact of non-dominant functional components.…”

Penentuan Sistem Pusat Pelayanan Perkotaan Berdasarkan Data Point of Interest di Kota Pangkalpinang

“…Suatu pusat kota perlu memiliki fasilitas yang berkualitas tinggi dan memadai. Menurut skala pelayannya, fasiltas tersebut harus mampu disediakan untuk seluruh penduduk kota dan mencakup seluruh wilayah kota (Dhika et al, 2012;J. Wang et al, 2023).…”

Characterisation of Morphological Patterns for Land Surface Temperature Distribution in Urban Environments: An Approach to Identify Priority Areas

“…Remote sensing has also enabled the identification of vegetation cover, quantification of spatio-temporal changes in vegetation, assessment of ecosystem service provisioning, evaluation of socio-economic and vegetation dynamics, and measurement of Land Surface Temperature (LST) associated with temperature fluctuations, among various other applications [17]. Therefore, remote sensing emerges as a valuable alternative to ground-based assessments [18][19][20], playing a pivotal role in modern comprehensive urban studies that require observations of LST and vegetation dynamics [21].…”