A nonparametric approach for detecting urban polycentric spatial structure in China using remote sensing nighttime light and point of interest data

Effectively identifying urban polycentric spatial structure (UPSS) is essential for data-driven evaluation of urban performance, and it serves as a scientific basis for urban spatial planning. However, existing identification methods have limitations such as subjectivity, poor spatial continuity, and a narrow application scale. Thus, from a morphology perspective, our study proposed a rapid, highly applicable, and spatiotemporally comparable nonparametric approach for detecting morphological urban polycentric spatial structure (MUPS) by integrating remote sensing nighttime light (NTL) and point of interest (POI) data. Taking China as an object, on the basis of recognizing urban entities using NTL data, a wavelet transform was initially introduced to fuse multi-source geospatial data, thereby enhancing the spatial intricacy within a city. Then, a local spatial autocorrelation model was utilized to identify pixel clusters. Finally, post-processing was performed to optimize urban centers, subsequently calculating MUPS. Results reveal that urban entities identified based on NTL have a significant advantage in characterizing the concentration of human activities, which can ensure the accuracy of extracting MUPS. Compared with existing relevant methods, the proposed nonparametric approach avoids the misalignment of multi-temporal urban center distribution, enhancing accuracy and stability. Differentiated spatiotemporal patterns were found in the evolutionary trajectories of MUPS in China, with a progressive intensification in the degree of spatial decentralization. Our study provides valuable insights into spatiotemporal analyses of MUPS at multiple scales and serves as a foundational resource for urban spatial planning.